diff options
202 files changed, 14661 insertions, 9346 deletions
diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c index 1573dae4259d..250629a09423 100644 --- a/tools/lib/api/fs/cgroup.c +++ b/tools/lib/api/fs/cgroup.c @@ -14,7 +14,7 @@ struct cgroupfs_cache_entry { }; /* just cache last used one */ -static struct cgroupfs_cache_entry cached; +static struct cgroupfs_cache_entry *cached; int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys) { @@ -24,9 +24,9 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys) char *p, *path; char mountpoint[PATH_MAX]; - if (!strcmp(cached.subsys, subsys)) { - if (strlen(cached.mountpoint) < maxlen) { - strcpy(buf, cached.mountpoint); + if (cached && !strcmp(cached->subsys, subsys)) { + if (strlen(cached->mountpoint) < maxlen) { + strcpy(buf, cached->mountpoint); return 0; } return -1; @@ -91,8 +91,13 @@ int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys) free(line); fclose(fp); - strncpy(cached.subsys, subsys, sizeof(cached.subsys) - 1); - strcpy(cached.mountpoint, mountpoint); + if (!cached) + cached = calloc(1, sizeof(*cached)); + + if (cached) { + strncpy(cached->subsys, subsys, sizeof(cached->subsys) - 1); + strcpy(cached->mountpoint, mountpoint); + } if (mountpoint[0] && strlen(mountpoint) < maxlen) { strcpy(buf, mountpoint); diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 82f53d81a7a7..22d34a0be8b4 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -88,7 +88,7 @@ static const char * const bpf_fs__known_mountpoints[] = { struct fs { const char *name; const char * const *mounts; - char path[PATH_MAX]; + char *path; bool found; bool checked; long magic; @@ -151,17 +151,23 @@ static bool fs__read_mounts(struct fs *fs) bool found = false; char type[100]; FILE *fp; + char path[PATH_MAX + 1]; fp = fopen("/proc/mounts", "r"); if (fp == NULL) - return NULL; + return false; while (!found && fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n", - fs->path, type) == 2) { + path, type) == 2) { - if (strcmp(type, fs->name) == 0) + if (strcmp(type, fs->name) == 0) { + free(fs->path); + fs->path = strdup(path); + if (!fs->path) + return false; found = true; + } } fclose(fp); @@ -188,8 +194,11 @@ static bool fs__check_mounts(struct fs *fs) ptr = fs->mounts; while (*ptr) { if (fs__valid_mount(*ptr, fs->magic) == 0) { + free(fs->path); + fs->path = strdup(*ptr); + if (!fs->path) + return false; fs->found = true; - strcpy(fs->path, *ptr); return true; } ptr++; @@ -227,10 +236,12 @@ static bool fs__env_override(struct fs *fs) if (!override_path) return false; + free(fs->path); + fs->path = strdup(override_path); + if (!fs->path) + return false; fs->found = true; fs->checked = true; - strncpy(fs->path, override_path, sizeof(fs->path) - 1); - fs->path[sizeof(fs->path) - 1] = '\0'; return true; } diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index 7ba3e81274e8..30745f35d0d2 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -13,17 +13,12 @@ #include "tracing_path.h" -static char tracing_mnt[PATH_MAX] = "/sys/kernel/debug"; static char tracing_path[PATH_MAX] = "/sys/kernel/tracing"; -static char tracing_events_path[PATH_MAX] = "/sys/kernel/tracing/events"; static void __tracing_path_set(const char *tracing, const char *mountpoint) { - snprintf(tracing_mnt, sizeof(tracing_mnt), "%s", mountpoint); snprintf(tracing_path, sizeof(tracing_path), "%s/%s", mountpoint, tracing); - snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s", - mountpoint, tracing, "events"); } static const char *tracing_path_tracefs_mount(void) @@ -149,15 +144,15 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size, /* sdt markers */ if (!strncmp(filename, "sdt_", 4)) { snprintf(buf, size, - "Error:\tFile %s/%s not found.\n" + "Error:\tFile %s/events/%s not found.\n" "Hint:\tSDT event cannot be directly recorded on.\n" "\tPlease first use 'perf probe %s:%s' before recording it.\n", - tracing_events_path, filename, sys, name); + tracing_path, filename, sys, name); } else { snprintf(buf, size, - "Error:\tFile %s/%s not found.\n" + "Error:\tFile %s/events/%s not found.\n" "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", - tracing_events_path, filename); + tracing_path, filename); } break; } @@ -169,9 +164,9 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size, break; case EACCES: { snprintf(buf, size, - "Error:\tNo permissions to read %s/%s\n" + "Error:\tNo permissions to read %s/events/%s\n" "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n", - tracing_events_path, filename, tracing_path_mount()); + tracing_path, filename, tracing_path_mount()); } break; default: diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 1229b18bcdb1..2a5a29217374 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -99,6 +99,11 @@ static int cmp_cpu(const void *a, const void *b) return cpu_a->cpu - cpu_b->cpu; } +static struct perf_cpu __perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) +{ + return RC_CHK_ACCESS(cpus)->map[idx]; +} + static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus) { size_t payload_size = nr_cpus * sizeof(struct perf_cpu); @@ -111,8 +116,12 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu /* Remove dups */ j = 0; for (i = 0; i < nr_cpus; i++) { - if (i == 0 || RC_CHK_ACCESS(cpus)->map[i].cpu != RC_CHK_ACCESS(cpus)->map[i - 1].cpu) - RC_CHK_ACCESS(cpus)->map[j++].cpu = RC_CHK_ACCESS(cpus)->map[i].cpu; + if (i == 0 || + __perf_cpu_map__cpu(cpus, i).cpu != + __perf_cpu_map__cpu(cpus, i - 1).cpu) { + RC_CHK_ACCESS(cpus)->map[j++].cpu = + __perf_cpu_map__cpu(cpus, i).cpu; + } } perf_cpu_map__set_nr(cpus, j); assert(j <= nr_cpus); @@ -269,26 +278,31 @@ out: return cpus; } +static int __perf_cpu_map__nr(const struct perf_cpu_map *cpus) +{ + return RC_CHK_ACCESS(cpus)->nr; +} + struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) { struct perf_cpu result = { .cpu = -1 }; - if (cpus && idx < RC_CHK_ACCESS(cpus)->nr) - return RC_CHK_ACCESS(cpus)->map[idx]; + if (cpus && idx < __perf_cpu_map__nr(cpus)) + return __perf_cpu_map__cpu(cpus, idx); return result; } int perf_cpu_map__nr(const struct perf_cpu_map *cpus) { - return cpus ? RC_CHK_ACCESS(cpus)->nr : 1; + return cpus ? __perf_cpu_map__nr(cpus) : 1; } bool perf_cpu_map__empty(const struct perf_cpu_map *map) { - return map ? RC_CHK_ACCESS(map)->map[0].cpu == -1 : true; + return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true; } int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) @@ -299,10 +313,10 @@ int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) return -1; low = 0; - high = RC_CHK_ACCESS(cpus)->nr; + high = __perf_cpu_map__nr(cpus); while (low < high) { int idx = (low + high) / 2; - struct perf_cpu cpu_at_idx = RC_CHK_ACCESS(cpus)->map[idx]; + struct perf_cpu cpu_at_idx = __perf_cpu_map__cpu(cpus, idx); if (cpu_at_idx.cpu == cpu.cpu) return idx; @@ -321,6 +335,32 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu) return perf_cpu_map__idx(cpus, cpu) != -1; } +bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, const struct perf_cpu_map *rhs) +{ + int nr; + + if (lhs == rhs) + return true; + + if (!lhs || !rhs) + return false; + + nr = __perf_cpu_map__nr(lhs); + if (nr != __perf_cpu_map__nr(rhs)) + return false; + + for (int idx = 0; idx < nr; idx++) { + if (__perf_cpu_map__cpu(lhs, idx).cpu != __perf_cpu_map__cpu(rhs, idx).cpu) + return false; + } + return true; +} + +bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map) +{ + return map && __perf_cpu_map__cpu(map, 0).cpu == -1; +} + struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) { struct perf_cpu result = { @@ -328,7 +368,9 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) }; // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. - return RC_CHK_ACCESS(map)->nr > 0 ? RC_CHK_ACCESS(map)->map[RC_CHK_ACCESS(map)->nr - 1] : result; + return __perf_cpu_map__nr(map) > 0 + ? __perf_cpu_map__cpu(map, __perf_cpu_map__nr(map) - 1) + : result; } /** Is 'b' a subset of 'a'. */ @@ -336,15 +378,15 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu { if (a == b || !b) return true; - if (!a || RC_CHK_ACCESS(b)->nr > RC_CHK_ACCESS(a)->nr) + if (!a || __perf_cpu_map__nr(b) > __perf_cpu_map__nr(a)) return false; - for (int i = 0, j = 0; i < RC_CHK_ACCESS(a)->nr; i++) { - if (RC_CHK_ACCESS(a)->map[i].cpu > RC_CHK_ACCESS(b)->map[j].cpu) + for (int i = 0, j = 0; i < __perf_cpu_map__nr(a); i++) { + if (__perf_cpu_map__cpu(a, i).cpu > __perf_cpu_map__cpu(b, j).cpu) return false; - if (RC_CHK_ACCESS(a)->map[i].cpu == RC_CHK_ACCESS(b)->map[j].cpu) { + if (__perf_cpu_map__cpu(a, i).cpu == __perf_cpu_map__cpu(b, j).cpu) { j++; - if (j == RC_CHK_ACCESS(b)->nr) + if (j == __perf_cpu_map__nr(b)) return true; } } @@ -374,27 +416,27 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, return perf_cpu_map__get(other); } - tmp_len = RC_CHK_ACCESS(orig)->nr + RC_CHK_ACCESS(other)->nr; + tmp_len = __perf_cpu_map__nr(orig) + __perf_cpu_map__nr(other); tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); if (!tmp_cpus) return NULL; /* Standard merge algorithm from wikipedia */ i = j = k = 0; - while (i < RC_CHK_ACCESS(orig)->nr && j < RC_CHK_ACCESS(other)->nr) { - if (RC_CHK_ACCESS(orig)->map[i].cpu <= RC_CHK_ACCESS(other)->map[j].cpu) { - if (RC_CHK_ACCESS(orig)->map[i].cpu == RC_CHK_ACCESS(other)->map[j].cpu) + while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) { + if (__perf_cpu_map__cpu(orig, i).cpu <= __perf_cpu_map__cpu(other, j).cpu) { + if (__perf_cpu_map__cpu(orig, i).cpu == __perf_cpu_map__cpu(other, j).cpu) j++; - tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++]; + tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++); } else - tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++]; + tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++); } - while (i < RC_CHK_ACCESS(orig)->nr) - tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++]; + while (i < __perf_cpu_map__nr(orig)) + tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++); - while (j < RC_CHK_ACCESS(other)->nr) - tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++]; + while (j < __perf_cpu_map__nr(other)) + tmp_cpus[k++] = __perf_cpu_map__cpu(other, j++); assert(k <= tmp_len); merged = cpu_map__trim_new(k, tmp_cpus); @@ -402,3 +444,38 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, perf_cpu_map__put(orig); return merged; } + +struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig, + struct perf_cpu_map *other) +{ + struct perf_cpu *tmp_cpus; + int tmp_len; + int i, j, k; + struct perf_cpu_map *merged = NULL; + + if (perf_cpu_map__is_subset(other, orig)) + return perf_cpu_map__get(orig); + if (perf_cpu_map__is_subset(orig, other)) + return perf_cpu_map__get(other); + + tmp_len = max(__perf_cpu_map__nr(orig), __perf_cpu_map__nr(other)); + tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); + if (!tmp_cpus) + return NULL; + + i = j = k = 0; + while (i < __perf_cpu_map__nr(orig) && j < __perf_cpu_map__nr(other)) { + if (__perf_cpu_map__cpu(orig, i).cpu < __perf_cpu_map__cpu(other, j).cpu) + i++; + else if (__perf_cpu_map__cpu(orig, i).cpu > __perf_cpu_map__cpu(other, j).cpu) + j++; + else { + j++; + tmp_cpus[k++] = __perf_cpu_map__cpu(orig, i++); + } + } + if (k) + merged = cpu_map__trim_new(k, tmp_cpus); + free(tmp_cpus); + return merged; +} diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 81e8b5fcd8ba..b8b066d0dc5e 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -36,18 +36,33 @@ void perf_evlist__init(struct perf_evlist *evlist) static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, struct perf_evsel *evsel) { - /* - * We already have cpus for evsel (via PMU sysfs) so - * keep it, if there's no target cpu list defined. - */ if (evsel->system_wide) { + /* System wide: set the cpu map of the evsel to all online CPUs. */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__new(NULL); + } else if (evlist->has_user_cpus && evsel->is_pmu_core) { + /* + * User requested CPUs on a core PMU, ensure the requested CPUs + * are valid by intersecting with those of the PMU. + */ + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus); } else if (!evsel->own_cpus || evlist->has_user_cpus || - (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) { + (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { + /* + * The PMU didn't specify a default cpu map, this isn't a core + * event and the user requested CPUs or the evlist user + * requested CPUs have the "any CPU" (aka dummy) CPU value. In + * which case use the user requested CPUs rather than the PMU + * ones. + */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } else if (evsel->cpus != evsel->own_cpus) { + /* + * No user requested cpu map but the PMU cpu map doesn't match + * the evsel's. Reset it back to the PMU cpu map. + */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evsel->own_cpus); } diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index a99a75d9e78f..5cd220a61962 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -41,7 +41,14 @@ struct perf_sample_id { struct perf_evsel { struct list_head node; struct perf_event_attr attr; + /** The commonly used cpu map of CPUs the event should be opened upon, etc. */ struct perf_cpu_map *cpus; + /** + * The cpu map read from the PMU. For core PMUs this is the list of all + * CPUs the event can be opened upon. For other PMUs this is the default + * cpu map for opening the event on, for example, the first CPU on a + * socket for an uncore event. + */ struct perf_cpu_map *own_cpus; struct perf_thread_map *threads; struct xyarray *fd; @@ -55,9 +62,9 @@ struct perf_evsel { int nr_members; /* * system_wide is for events that need to be on every CPU, irrespective - * of user requested CPUs or threads. Map propagation will set cpus to - * this event's own_cpus, whereby they will contribute to evlist - * all_cpus. + * of user requested CPUs or threads. Tha main example of this is the + * dummy event. Map propagation will set cpus for this event to all CPUs + * as software PMU events like dummy, have a CPU map that is empty. */ bool system_wide; /* @@ -65,6 +72,8 @@ struct perf_evsel { * i.e. it cannot be the 'any CPU' value of -1. */ bool requires_cpu; + /** Is the PMU for the event a core one? Effects the handling of own_cpus. */ + bool is_pmu_core; int idx; }; diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 3f43f770cdac..e38d859a384d 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -11,8 +11,16 @@ struct perf_cpu { int cpu; }; +struct perf_cache { + int cache_lvl; + int cache; +}; + struct perf_cpu_map; +/** + * perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value. + */ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); @@ -20,12 +28,23 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, struct perf_cpu_map *other); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig, + struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); +/** + * perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value. + */ LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map); LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); +LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, + const struct perf_cpu_map *rhs); +/** + * perf_cpu_map__any_cpu - Does the map contain the "any CPU"/dummy -1 value? + */ +LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 51b9338f4c11..ba2dcf64f4e6 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -380,7 +380,8 @@ enum { PERF_STAT_CONFIG_TERM__AGGR_MODE = 0, PERF_STAT_CONFIG_TERM__INTERVAL = 1, PERF_STAT_CONFIG_TERM__SCALE = 2, - PERF_STAT_CONFIG_TERM__MAX = 3, + PERF_STAT_CONFIG_TERM__AGGR_LEVEL = 3, + PERF_STAT_CONFIG_TERM__MAX = 4, }; struct perf_record_stat_config_entry { diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c index 5dbea456973e..7739b5217cf6 100644 --- a/tools/lib/subcmd/exec-cmd.c +++ b/tools/lib/subcmd/exec-cmd.c @@ -36,38 +36,40 @@ static int is_absolute_path(const char *path) return path[0] == '/'; } -static const char *get_pwd_cwd(void) +static const char *get_pwd_cwd(char *buf, size_t sz) { - static char cwd[PATH_MAX + 1]; char *pwd; struct stat cwd_stat, pwd_stat; - if (getcwd(cwd, PATH_MAX) == NULL) + if (getcwd(buf, sz) == NULL) return NULL; pwd = getenv("PWD"); - if (pwd && strcmp(pwd, cwd)) { - stat(cwd, &cwd_stat); + if (pwd && strcmp(pwd, buf)) { + stat(buf, &cwd_stat); if (!stat(pwd, &pwd_stat) && pwd_stat.st_dev == cwd_stat.st_dev && pwd_stat.st_ino == cwd_stat.st_ino) { - strlcpy(cwd, pwd, PATH_MAX); + strlcpy(buf, pwd, sz); } } - return cwd; + return buf; } -static const char *make_nonrelative_path(const char *path) +static const char *make_nonrelative_path(char *buf, size_t sz, const char *path) { - static char buf[PATH_MAX + 1]; - if (is_absolute_path(path)) { - if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + if (strlcpy(buf, path, sz) >= sz) die("Too long path: %.*s", 60, path); } else { - const char *cwd = get_pwd_cwd(); + const char *cwd = get_pwd_cwd(buf, sz); + if (!cwd) die("Cannot determine the current working directory"); - if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX) + + if (strlen(cwd) + strlen(path) + 2 >= sz) die("Too long path: %.*s", 60, path); + + strcat(buf, "/"); + strcat(buf, path); } return buf; } @@ -133,8 +135,11 @@ static void add_path(char **out, const char *path) if (path && *path) { if (is_absolute_path(path)) astrcat(out, path); - else - astrcat(out, make_nonrelative_path(path)); + else { + char buf[PATH_MAX]; + + astrcat(out, make_nonrelative_path(buf, sizeof(buf), path)); + } astrcat(out, ":"); } diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index ba5d942e4c6a..4407b106d977 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -250,11 +250,20 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ mv $@+ $@ +# Generate date from either KBUILD_BUILD_TIMESTAMP or git log of +# the doc input file +PERF_DATE = $(strip \ + $(if $(KBUILD_BUILD_TIMESTAMP), \ + $(shell date -u -d '$(KBUILD_BUILD_TIMESTAMP)' +%Y-%m-%d), \ + $(shell git log -1 --pretty="format:%cd" \ + --date=short --no-show-signature $<))) + ifdef USE_ASCIIDOCTOR $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b manpage -d manpage \ - $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ + $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \ + -adocdate=$(PERF_DATE) -o $@+ $< && \ mv $@+ $@ endif @@ -266,9 +275,7 @@ $(OUTPUT)%.xml : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b docbook -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \ - -aperf_date=$(shell git log -1 --pretty="format:%cd" \ - --date=short --no-show-signature $<) \ - -o $@+ $< && \ + -aperf_date=$(PERF_DATE) -o $@+ $< && \ mv $@+ $@ XSLT = docbook.xsl diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 777a0d8ba7d1..ff9a52e44688 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -130,7 +130,7 @@ OPTIONS -F:: --fields:: Comma separated list of fields to print. Options are: - comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, + comm, tid, pid, time, cpu, event, trace, ip, sym, dso, dsoff, addr, symoff, srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat, diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 29bdcfa93f04..785f0e2bcfac 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -308,6 +308,14 @@ use --per-die in addition to -a. (system-wide). The output includes the die number and the number of online processors on that die. This is useful to gauge the amount of aggregation. +--per-cache:: +Aggregate counts per cache instance for system-wide mode measurements. By +default, the aggregation happens for the cache level at the highest index +in the system. To specify a particular level, mention the cache level +alongside the option in the format [Ll][1-9][0-9]*. For example: +Using option "--per-cache=l3" or "--per-cache=L3" will aggregate the +information at the boundary of the level 3 cache in the system. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. This is a useful mode to detect imbalance between physical cores. To enable this mode, @@ -379,6 +387,14 @@ Aggregate counts per processor socket for system-wide mode measurements. --per-die:: Aggregate counts per processor die for system-wide mode measurements. +--per-cache:: +Aggregate counts per cache instance for system-wide mode measurements. By +default, the aggregation happens for the cache level at the highest index +in the system. To specify a particular level, mention the cache level +alongside the option in the format [Ll][1-9][0-9]*. For example: Using +option "--per-cache=l3" or "--per-cache=L3" will aggregate the +information at the boundary of the level 3 cache in the system. + --per-core:: Aggregate counts per physical processor for system-wide mode measurements. diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index adec6c9ee11d..3b8eca0ffb17 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -14,6 +14,7 @@ #include "../../../util/debug.h" #include "../../../util/evlist.h" #include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "cs-etm.h" #include "arm-spe.h" #include "hisi-ptt.h" @@ -40,7 +41,7 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) return NULL; } - arm_spe_pmus[*nr_spes] = perf_pmu__find(arm_spe_pmu_name); + arm_spe_pmus[*nr_spes] = perf_pmus__find(arm_spe_pmu_name); if (arm_spe_pmus[*nr_spes]) { pr_debug2("%s %d: arm_spe_pmu %d type %d name %s\n", __func__, __LINE__, *nr_spes, @@ -87,7 +88,7 @@ static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err) rewinddir(dir); while ((dent = readdir(dir))) { if (strstr(dent->d_name, HISI_PTT_PMU_NAME) && idx < *nr_ptts) { - hisi_ptt_pmus[idx] = perf_pmu__find(dent->d_name); + hisi_ptt_pmus[idx] = perf_pmus__find(dent->d_name); if (hisi_ptt_pmus[idx]) idx++; } @@ -131,7 +132,7 @@ struct auxtrace_record if (!evlist) return NULL; - cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); + cs_etm_pmu = perf_pmus__find(CORESIGHT_ETM_PMU_NAME); arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err); diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 9ca040bfb1aa..7c51fa182b51 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -25,7 +25,7 @@ #include "../../../util/evsel.h" #include "../../../util/perf_api_probe.h" #include "../../../util/evsel_config.h" -#include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/cs-etm.h" #include <internal/lib.h> // page_size #include "../../../util/session.h" @@ -881,7 +881,7 @@ struct auxtrace_record *cs_etm_record_init(int *err) struct perf_pmu *cs_etm_pmu; struct cs_etm_recording *ptr; - cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); + cs_etm_pmu = perf_pmus__find(CORESIGHT_ETM_PMU_NAME); if (!cs_etm_pmu) { *err = -EINVAL; diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index ef1ed645097c..561de0cb6b95 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -3,6 +3,7 @@ #include <internal/cpumap.h> #include "../../../util/cpumap.h" #include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include <api/fs/fs.h> #include <math.h> @@ -10,10 +11,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) { struct perf_pmu *pmu = NULL; - while ((pmu = perf_pmu__scan(pmu))) { - if (!is_pmu_core(pmu->name)) - continue; - + while ((pmu = perf_pmus__scan_core(pmu))) { /* * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index b951374bc49d..4908d54dd33b 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -43,6 +43,20 @@ const char *const powerpc_triplets[] = { NULL }; +const char *const riscv32_triplets[] = { + "riscv32-unknown-linux-gnu-", + "riscv32-linux-android-", + "riscv32-linux-gnu-", + NULL +}; + +const char *const riscv64_triplets[] = { + "riscv64-unknown-linux-gnu-", + "riscv64-linux-android-", + "riscv64-linux-gnu-", + NULL +}; + const char *const s390_triplets[] = { "s390-ibm-linux-", "s390x-linux-gnu-", @@ -164,6 +178,10 @@ static int perf_env__lookup_binutils_path(struct perf_env *env, path_list = arm64_triplets; else if (!strcmp(arch, "powerpc")) path_list = powerpc_triplets; + else if (!strcmp(arch, "riscv32")) + path_list = riscv32_triplets; + else if (!strcmp(arch, "riscv64")) + path_list = riscv64_triplets; else if (!strcmp(arch, "sh")) path_list = sh_triplets; else if (!strcmp(arch, "s390")) diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index ea1220d66b67..d9a0ac1cdf30 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -5,7 +5,7 @@ #include "util/debug.h" #include "util/evsel.h" #include "util/evlist.h" -#include "util/pmu.h" +#include "util/pmus.h" #include "book3s_hv_exits.h" #include "book3s_hcalls.h" @@ -204,7 +204,7 @@ int kvm_add_default_arch_event(int *argc, const char **argv) parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN); if (!event) { - if (pmu_have_event("trace_imc", "trace_cycles")) { + if (perf_pmus__have_event("trace_imc", "trace_cycles")) { argv[j++] = strdup("-e"); argv[j++] = strdup("trace_imc/trace_cycles/"); *argc += 2; diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 305872692bfd..5c7bec25fee4 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -35,12 +35,14 @@ static struct ins x86__instructions[] = { { .name = "cs", .ops = &mov_ops, }, { .name = "dec", .ops = &dec_ops, }, { .name = "decl", .ops = &dec_ops, }, + { .name = "decq", .ops = &dec_ops, }, { .name = "divsd", .ops = &mov_ops, }, { .name = "divss", .ops = &mov_ops, }, { .name = "gs", .ops = &mov_ops, }, { .name = "imul", .ops = &mov_ops, }, { .name = "inc", .ops = &dec_ops, }, { .name = "incl", .ops = &dec_ops, }, + { .name = "incq", .ops = &dec_ops, }, { .name = "ja", .ops = &jump_ops, }, { .name = "jae", .ops = &jump_ops, }, { .name = "jb", .ops = &jump_ops, }, @@ -123,6 +125,8 @@ static struct ins x86__instructions[] = { { .name = "test", .ops = &mov_ops, }, { .name = "testb", .ops = &mov_ops, }, { .name = "testl", .ops = &mov_ops, }, + { .name = "testq", .ops = &mov_ops, }, + { .name = "tzcnt", .ops = &mov_ops, }, { .name = "ucomisd", .ops = &mov_ops, }, { .name = "ucomiss", .ops = &mov_ops, }, { .name = "vaddsd", .ops = &mov_ops, }, diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 902e9ea9b99e..33d39c1d3e64 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -11,6 +11,7 @@ int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest); int test__bp_modify(struct test_suite *test, int subtest); int test__x86_sample_parsing(struct test_suite *test, int subtest); +int test__hybrid(struct test_suite *test, int subtest); extern struct test_suite *arch_tests[]; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 6f4e8636c3bf..08cc8b9c931e 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -3,5 +3,6 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o perf-y += sample-parsing.o +perf-y += hybrid.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-test.o perf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index aae6ea0fe52b..147ad0638bbb 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -22,6 +22,15 @@ struct test_suite suite__intel_pt = { DEFINE_SUITE("x86 bp modify", bp_modify); #endif DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); +static struct test_case hybrid_tests[] = { + TEST_CASE_REASON("x86 hybrid event parsing", hybrid, "not hybrid"), + { .name = NULL, } +}; + +struct test_suite suite__hybrid = { + .desc = "x86 hybrid", + .test_cases = hybrid_tests, +}; struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT @@ -35,5 +44,6 @@ struct test_suite *arch_tests[] = { &suite__bp_modify, #endif &suite__x86_sample_parsing, + &suite__hybrid, NULL, }; diff --git a/tools/perf/arch/x86/tests/hybrid.c b/tools/perf/arch/x86/tests/hybrid.c new file mode 100644 index 000000000000..eb152770f148 --- /dev/null +++ b/tools/perf/arch/x86/tests/hybrid.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "arch-tests.h" +#include "debug.h" +#include "evlist.h" +#include "evsel.h" +#include "pmu.h" +#include "pmus.h" +#include "tests/tests.h" + +static bool test_config(const struct evsel *evsel, __u64 expected_config) +{ + return (evsel->core.attr.config & PERF_HW_EVENT_MASK) == expected_config; +} + +static bool test_perf_config(const struct perf_evsel *evsel, __u64 expected_config) +{ + return (evsel->attr.config & PERF_HW_EVENT_MASK) == expected_config; +} + +static bool test_hybrid_type(const struct evsel *evsel, __u64 expected_config) +{ + return (evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT) == expected_config; +} + +static int test__hybrid_hw_event_with_pmu(struct evlist *evlist) +{ + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + return TEST_OK; +} + +static int test__hybrid_hw_group_event(struct evlist *evlist) +{ + struct evsel *evsel, *leader; + + evsel = leader = evlist__first(evlist); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + + evsel = evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + return TEST_OK; +} + +static int test__hybrid_sw_hw_group_event(struct evlist *evlist) +{ + struct evsel *evsel, *leader; + + evsel = leader = evlist__first(evlist); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + + evsel = evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + return TEST_OK; +} + +static int test__hybrid_hw_sw_group_event(struct evlist *evlist) +{ + struct evsel *evsel, *leader; + + evsel = leader = evlist__first(evlist); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + + evsel = evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + return TEST_OK; +} + +static int test__hybrid_group_modifier1(struct evlist *evlist) +{ + struct evsel *evsel, *leader; + + evsel = leader = evlist__first(evlist); + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + + evsel = evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW)); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); + return TEST_OK; +} + +static int test__hybrid_raw1(struct evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_evsel(&evlist->core, evsel) { + struct perf_pmu *pmu = perf_pmus__find_by_type(evsel->attr.type); + + TEST_ASSERT_VAL("missing pmu", pmu); + TEST_ASSERT_VAL("unexpected pmu", !strncmp(pmu->name, "cpu_", 4)); + TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, 0x1a)); + } + return TEST_OK; +} + +static int test__hybrid_raw2(struct evlist *evlist) +{ + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0x1a)); + return TEST_OK; +} + +static int test__hybrid_cache_event(struct evlist *evlist) +{ + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff)); + return TEST_OK; +} + +static int test__checkevent_pmu(struct evlist *evlist) +{ + + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong config", 10 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config1", 1 == evsel->core.attr.config1); + TEST_ASSERT_VAL("wrong config2", 3 == evsel->core.attr.config2); + TEST_ASSERT_VAL("wrong config3", 0 == evsel->core.attr.config3); + /* + * The period value gets configured within evlist__config, + * while this test executes only parse events method. + */ + TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); + + return TEST_OK; +} + +struct evlist_test { + const char *name; + bool (*valid)(void); + int (*check)(struct evlist *evlist); +}; + +static const struct evlist_test test__hybrid_events[] = { + { + .name = "cpu_core/cpu-cycles/", + .check = test__hybrid_hw_event_with_pmu, + /* 0 */ + }, + { + .name = "{cpu_core/cpu-cycles/,cpu_core/instructions/}", + .check = test__hybrid_hw_group_event, + /* 1 */ + }, + { + .name = "{cpu-clock,cpu_core/cpu-cycles/}", + .check = test__hybrid_sw_hw_group_event, + /* 2 */ + }, + { + .name = "{cpu_core/cpu-cycles/,cpu-clock}", + .check = test__hybrid_hw_sw_group_event, + /* 3 */ + }, + { + .name = "{cpu_core/cpu-cycles/k,cpu_core/instructions/u}", + .check = test__hybrid_group_modifier1, + /* 4 */ + }, + { + .name = "r1a", + .check = test__hybrid_raw1, + /* 5 */ + }, + { + .name = "cpu_core/r1a/", + .check = test__hybrid_raw2, + /* 6 */ + }, + { + .name = "cpu_core/config=10,config1,config2=3,period=1000/u", + .check = test__checkevent_pmu, + /* 7 */ + }, + { + .name = "cpu_core/LLC-loads/", + .check = test__hybrid_cache_event, + /* 8 */ + }, +}; + +static int test_event(const struct evlist_test *e) +{ + struct parse_events_error err; + struct evlist *evlist; + int ret; + + if (e->valid && !e->valid()) { + pr_debug("... SKIP\n"); + return TEST_OK; + } + + evlist = evlist__new(); + if (evlist == NULL) { + pr_err("Failed allocation"); + return TEST_FAIL; + } + parse_events_error__init(&err); + ret = parse_events(evlist, e->name, &err); + if (ret) { + pr_debug("failed to parse event '%s', err %d, str '%s'\n", + e->name, ret, err.str); + parse_events_error__print(&err, e->name); + ret = TEST_FAIL; + if (strstr(err.str, "can't access trace events")) + ret = TEST_SKIP; + } else { + ret = e->check(evlist); + } + parse_events_error__exit(&err); + evlist__delete(evlist); + + return ret; +} + +static int combine_test_results(int existing, int latest) +{ + if (existing == TEST_FAIL) + return TEST_FAIL; + if (existing == TEST_SKIP) + return latest == TEST_OK ? TEST_SKIP : latest; + return latest; +} + +static int test_events(const struct evlist_test *events, int cnt) +{ + int ret = TEST_OK; + + for (int i = 0; i < cnt; i++) { + const struct evlist_test *e = &events[i]; + int test_ret; + + pr_debug("running test %d '%s'\n", i, e->name); + test_ret = test_event(e); + if (test_ret != TEST_OK) { + pr_debug("Event test failure: test %d '%s'", i, e->name); + ret = combine_test_results(ret, test_ret); + } + } + + return ret; +} + +int test__hybrid(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + if (perf_pmus__num_core_pmus() == 1) + return TEST_SKIP; + + return test_events(test__hybrid_events, ARRAY_SIZE(test__hybrid_events)); +} diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 735257d205b5..7b5eb8baf0f2 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -18,14 +18,14 @@ struct test_data { const char *asm_rep; }; -struct test_data test_data_32[] = { +const struct test_data test_data_32[] = { #include "insn-x86-dat-32.c" {{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee \trdpkru"}, {{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef \twrpkru"}, {{0}, 0, 0, NULL, NULL, NULL}, }; -struct test_data test_data_64[] = { +const struct test_data test_data_64[] = { #include "insn-x86-dat-64.c" {{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee \trdpkru"}, {{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef \twrpkru"}, @@ -97,7 +97,7 @@ static int get_branch(const char *branch_str) return -1; } -static int test_data_item(struct test_data *dat, int x86_64) +static int test_data_item(const struct test_data *dat, int x86_64) { struct intel_pt_insn intel_pt_insn; int op, branch, ret; @@ -147,9 +147,9 @@ static int test_data_item(struct test_data *dat, int x86_64) return 0; } -static int test_data_set(struct test_data *dat_set, int x86_64) +static int test_data_set(const struct test_data *dat_set, int x86_64) { - struct test_data *dat; + const struct test_data *dat; int ret = 0; for (dat = dat_set; dat->expected_length; dat++) { diff --git a/tools/perf/arch/x86/tests/intel-pt-test.c b/tools/perf/arch/x86/tests/intel-pt-test.c index 70b7f79396b1..09d61fa736e3 100644 --- a/tools/perf/arch/x86/tests/intel-pt-test.c +++ b/tools/perf/arch/x86/tests/intel-pt-test.c @@ -22,7 +22,7 @@ * @new_ctx: expected new packet context * @ctx_unchanged: the packet context must not change */ -static struct test_data { +static const struct test_data { int len; u8 bytes[INTEL_PT_PKT_MAX_SZ]; enum intel_pt_pkt_ctx ctx; @@ -186,7 +186,7 @@ static struct test_data { {0, {0}, 0, {0, 0, 0}, 0, 0 }, }; -static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len) +static int dump_packet(const struct intel_pt_pkt *packet, const u8 *bytes, int len) { char desc[INTEL_PT_PKT_DESC_MAX]; int ret, i; @@ -206,14 +206,14 @@ static int dump_packet(struct intel_pt_pkt *packet, u8 *bytes, int len) return TEST_OK; } -static void decoding_failed(struct test_data *d) +static void decoding_failed(const struct test_data *d) { pr_debug("Decoding failed!\n"); pr_debug("Decoding: "); dump_packet(&d->packet, d->bytes, d->len); } -static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len, +static int fail(const struct test_data *d, struct intel_pt_pkt *packet, int len, enum intel_pt_pkt_ctx new_ctx) { decoding_failed(d); @@ -242,7 +242,7 @@ static int fail(struct test_data *d, struct intel_pt_pkt *packet, int len, return TEST_FAIL; } -static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet, +static int test_ctx_unchanged(const struct test_data *d, struct intel_pt_pkt *packet, enum intel_pt_pkt_ctx ctx) { enum intel_pt_pkt_ctx old_ctx = ctx; @@ -258,7 +258,7 @@ static int test_ctx_unchanged(struct test_data *d, struct intel_pt_pkt *packet, return TEST_OK; } -static int test_one(struct test_data *d) +static int test_one(const struct test_data *d) { struct intel_pt_pkt packet; enum intel_pt_pkt_ctx ctx = d->ctx; @@ -307,7 +307,7 @@ static int test_one(struct test_data *d) */ int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - struct test_data *d = data; + const struct test_data *d = data; int ret; for (d = data; d->len; d++) { diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 330d03216b0e..354780ff1605 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -10,6 +10,7 @@ #include "../../../util/header.h" #include "../../../util/debug.h" #include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/auxtrace.h" #include "../../../util/intel-pt.h" #include "../../../util/intel-bts.h" @@ -25,8 +26,8 @@ struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, bool found_pt = false; bool found_bts = false; - intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); - intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); + intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME); + intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME); evlist__for_each_entry(evlist, evsel) { if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type) diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index d4193479a364..cbd582182932 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -1,38 +1,42 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include "util/pmu.h" +#include "util/pmus.h" #include "util/evlist.h" #include "util/parse-events.h" #include "util/event.h" -#include "util/pmu-hybrid.h" #include "topdown.h" +#include "evsel.h" static int ___evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { - struct perf_cpu_map *cpus; - struct evsel *evsel, *n; - struct perf_pmu *pmu; LIST_HEAD(head); size_t i = 0; for (i = 0; i < nr_attrs; i++) event_attr_init(attrs + i); - if (!perf_pmu__has_hybrid()) + if (perf_pmus__num_core_pmus() == 1) return evlist__add_attrs(evlist, attrs, nr_attrs); for (i = 0; i < nr_attrs; i++) { + struct perf_pmu *pmu = NULL; + if (attrs[i].type == PERF_TYPE_SOFTWARE) { - evsel = evsel__new(attrs + i); + struct evsel *evsel = evsel__new(attrs + i); + if (evsel == NULL) goto out_delete_partial_list; list_add_tail(&evsel->core.node, &head); continue; } - perf_pmu__for_each_hybrid_pmu(pmu) { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + struct perf_cpu_map *cpus; + struct evsel *evsel; + evsel = evsel__new(attrs + i); if (evsel == NULL) goto out_delete_partial_list; @@ -50,8 +54,12 @@ static int ___evlist__add_default_attrs(struct evlist *evlist, return 0; out_delete_partial_list: - __evlist__for_each_entry_safe(&head, n, evsel) - evsel__delete(evsel); + { + struct evsel *evsel, *n; + + __evlist__for_each_entry_safe(&head, n, evsel) + evsel__delete(evsel); + } return -1; } @@ -67,8 +75,7 @@ int arch_evlist__add_default_attrs(struct evlist *evlist, int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) { - if (topdown_sys_has_perf_metrics() && - (!lhs->pmu_name || !strncmp(lhs->pmu_name, "cpu", 3))) { + if (topdown_sys_has_perf_metrics() && evsel__sys_has_perf_metrics(lhs)) { /* Ensure the topdown slots comes first. */ if (strcasestr(lhs->name, "slots")) return -1; diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c index ea3972d785d1..25da46c8cca9 100644 --- a/tools/perf/arch/x86/util/evsel.c +++ b/tools/perf/arch/x86/util/evsel.c @@ -4,6 +4,7 @@ #include "util/evsel.h" #include "util/env.h" #include "util/pmu.h" +#include "util/pmus.h" #include "linux/string.h" #include "evsel.h" #include "util/debug.h" @@ -16,26 +17,6 @@ void arch_evsel__set_sample_weight(struct evsel *evsel) evsel__set_sample_bit(evsel, WEIGHT_STRUCT); } -void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr) -{ - struct perf_env env = { .total_mem = 0, } ; - - if (!perf_env__cpuid(&env)) - return; - - /* - * On AMD, precise cycles event sampling internally uses IBS pmu. - * But IBS does not have filtering capabilities and perf by default - * sets exclude_guest = 1. This makes IBS pmu event init fail and - * thus perf ends up doing non-precise sampling. Avoid it by clearing - * exclude_guest. - */ - if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD")) - attr->exclude_guest = 0; - - free(env.cpuid); -} - /* Check whether the evsel's PMU supports the perf metrics */ bool evsel__sys_has_perf_metrics(const struct evsel *evsel) { @@ -50,7 +31,7 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel) * should be good enough to detect the perf metrics feature. */ if ((evsel->core.attr.type == PERF_TYPE_RAW) && - pmu_have_event(pmu_name, "slots")) + perf_pmus__have_event(pmu_name, "slots")) return true; return false; @@ -118,8 +99,8 @@ void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr) if (!evsel_pmu) return; - ibs_fetch_pmu = perf_pmu__find("ibs_fetch"); - ibs_op_pmu = perf_pmu__find("ibs_op"); + ibs_fetch_pmu = perf_pmus__find("ibs_fetch"); + ibs_op_pmu = perf_pmus__find("ibs_op"); if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) { if (attr->config & IBS_FETCH_L3MISSONLY) { diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 439c2956f3e7..d2c8cac11470 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -17,7 +17,7 @@ #include "../../../util/evlist.h" #include "../../../util/mmap.h" #include "../../../util/session.h" -#include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/debug.h" #include "../../../util/record.h" #include "../../../util/tsc.h" @@ -416,7 +416,7 @@ out_err: struct auxtrace_record *intel_bts_recording_init(int *err) { - struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); + struct perf_pmu *intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME); struct intel_bts_recording *btsr; if (!intel_bts_pmu) diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 17336da08b58..74b70fd379df 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -23,7 +23,7 @@ #include "../../../util/mmap.h" #include <subcmd/parse-options.h> #include "../../../util/parse-events.h" -#include "../../../util/pmu.h" +#include "../../../util/pmus.h" #include "../../../util/debug.h" #include "../../../util/auxtrace.h" #include "../../../util/perf_api_probe.h" @@ -1185,7 +1185,7 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) struct auxtrace_record *intel_pt_recording_init(int *err) { - struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); + struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME); struct intel_pt_recording *ptr; if (!intel_pt_pmu) diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c index f683ac702247..32879d12a8d5 100644 --- a/tools/perf/arch/x86/util/mem-events.c +++ b/tools/perf/arch/x86/util/mem-events.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "util/pmu.h" +#include "util/pmus.h" #include "util/env.h" #include "map_symbol.h" #include "mem-events.h" @@ -55,13 +56,13 @@ struct perf_mem_event *perf_mem_events__ptr(int i) bool is_mem_loads_aux_event(struct evsel *leader) { - if (perf_pmu__find("cpu")) { - if (!pmu_have_event("cpu", "mem-loads-aux")) - return false; - } else if (perf_pmu__find("cpu_core")) { - if (!pmu_have_event("cpu_core", "mem-loads-aux")) - return false; - } + struct perf_pmu *pmu = perf_pmus__find("cpu"); + + if (!pmu) + pmu = perf_pmus__find("cpu_core"); + + if (pmu && !perf_pmu__have_event(pmu, "mem-loads-aux")) + return false; return leader->core.attr.config == MEM_LOADS_AUX; } @@ -82,7 +83,7 @@ char *perf_mem_events__name(int i, char *pmu_name) pmu_name = (char *)"cpu"; } - if (pmu_have_event(pmu_name, "mem-loads-aux")) { + if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) { scnprintf(mem_loads_name, sizeof(mem_loads_name), MEM_LOADS_AUX_NAME, pmu_name, pmu_name, perf_mem_events__loads_ldlat); diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 0ed177991ad0..8ad4112ad10c 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -10,7 +10,7 @@ #include "../../../util/debug.h" #include "../../../util/event.h" #include "../../../util/pmu.h" -#include "../../../util/pmu-hybrid.h" +#include "../../../util/pmus.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -286,20 +286,25 @@ uint64_t arch__intr_reg_mask(void) .disabled = 1, .exclude_kernel = 1, }; - struct perf_pmu *pmu; int fd; /* * In an unnamed union, init it here to build on older gcc versions */ attr.sample_period = 1; - if (perf_pmu__has_hybrid()) { + if (perf_pmus__num_core_pmus() > 1) { + struct perf_pmu *pmu = NULL; + __u64 type = PERF_TYPE_RAW; + /* * The same register set is supported among different hybrid PMUs. * Only check the first available one. */ - pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list); - attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + type = pmu->type; + break; + } + attr.config |= type << PERF_PMU_TYPE_SHIFT; } event_attr_init(&attr); diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index 9ad5e5c7bd27..3f9a267d4501 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -2,6 +2,7 @@ #include "api/fs/fs.h" #include "util/evsel.h" #include "util/pmu.h" +#include "util/pmus.h" #include "util/topdown.h" #include "topdown.h" #include "evsel.h" @@ -22,8 +23,8 @@ bool topdown_sys_has_perf_metrics(void) * The slots event is only available when the core PMU * supports the perf metrics feature. */ - pmu = perf_pmu__find_by_type(PERF_TYPE_RAW); - if (pmu && pmu_have_event(pmu->name, "slots")) + pmu = perf_pmus__find_by_type(PERF_TYPE_RAW); + if (pmu && perf_pmu__have_event(pmu, "slots")) has_perf_metrics = true; cached = true; diff --git a/tools/perf/bench/pmu-scan.c b/tools/perf/bench/pmu-scan.c index f0f007843bb8..c7d207f8e13c 100644 --- a/tools/perf/bench/pmu-scan.c +++ b/tools/perf/bench/pmu-scan.c @@ -22,6 +22,7 @@ struct pmu_scan_result { int nr_aliases; int nr_formats; int nr_caps; + bool is_core; }; static const struct option options[] = { @@ -40,13 +41,11 @@ static struct pmu_scan_result *results; static int save_result(void) { - struct perf_pmu *pmu; + struct perf_pmu *pmu = NULL; struct list_head *list; struct pmu_scan_result *r; - perf_pmu__scan(NULL); - - perf_pmus__for_each_pmu(pmu) { + while ((pmu = perf_pmus__scan(pmu)) != NULL) { r = realloc(results, (nr_pmus + 1) * sizeof(*r)); if (r == NULL) return -ENOMEM; @@ -55,6 +54,7 @@ static int save_result(void) r = results + nr_pmus; r->name = strdup(pmu->name); + r->is_core = pmu->is_core; r->nr_caps = pmu->nr_caps; r->nr_aliases = 0; @@ -70,11 +70,11 @@ static int save_result(void) nr_pmus++; } - perf_pmu__destroy(); + perf_pmus__destroy(); return 0; } -static int check_result(void) +static int check_result(bool core_only) { struct pmu_scan_result *r; struct perf_pmu *pmu; @@ -83,7 +83,10 @@ static int check_result(void) for (int i = 0; i < nr_pmus; i++) { r = &results[i]; - pmu = perf_pmu__find(r->name); + if (core_only && !r->is_core) + continue; + + pmu = perf_pmus__find(r->name); if (pmu == NULL) { pr_err("Cannot find PMU %s\n", r->name); return -1; @@ -132,7 +135,6 @@ static int run_pmu_scan(void) struct timeval start, end, diff; double time_average, time_stddev; u64 runtime_us; - unsigned int i; int ret; init_stats(&stats); @@ -144,26 +146,30 @@ static int run_pmu_scan(void) return -1; } - for (i = 0; i < iterations; i++) { - gettimeofday(&start, NULL); - perf_pmu__scan(NULL); - gettimeofday(&end, NULL); - - timersub(&end, &start, &diff); - runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; - update_stats(&stats, runtime_us); - - ret = check_result(); - perf_pmu__destroy(); - if (ret < 0) - break; + for (int j = 0; j < 2; j++) { + bool core_only = (j == 0); + + for (unsigned int i = 0; i < iterations; i++) { + gettimeofday(&start, NULL); + if (core_only) + perf_pmus__scan_core(NULL); + else + perf_pmus__scan(NULL); + gettimeofday(&end, NULL); + timersub(&end, &start, &diff); + runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + update_stats(&stats, runtime_us); + + ret = check_result(core_only); + perf_pmus__destroy(); + if (ret < 0) + break; + } + time_average = avg_stats(&stats); + time_stddev = stddev_stats(&stats); + pr_info(" Average%s PMU scanning took: %.3f usec (+- %.3f usec)\n", + core_only ? " core" : "", time_average, time_stddev); } - - time_average = avg_stats(&stats); - time_stddev = stddev_stats(&stats); - pr_info(" Average PMU scanning took: %.3f usec (+- %.3f usec)\n", - time_average, time_stddev); - delete_result(); return 0; } diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 63cdf6ea6f6d..425a7e2fd6fb 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -342,7 +342,7 @@ static void hists__find_annotations(struct hists *hists, notes = symbol__annotation(he->ms.sym); if (notes->src == NULL) { find_next: - if (key == K_LEFT) + if (key == K_LEFT || key == '<') nd = rb_prev(nd); else nd = rb_next(nd); @@ -378,9 +378,11 @@ find_next: return; /* fall through */ case K_RIGHT: + case '>': next = rb_next(nd); break; case K_LEFT: + case '<': next = rb_prev(nd); break; default: diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 08455e26b606..05dfd98af170 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -41,8 +41,7 @@ #include "symbol.h" #include "ui/ui.h" #include "ui/progress.h" -#include "pmu.h" -#include "pmu-hybrid.h" +#include "pmus.h" #include "string2.h" #include "util/util.h" @@ -3259,10 +3258,8 @@ static int perf_c2c__record(int argc, const char **argv) argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_KEEP_UNKNOWN); - if (!perf_pmu__has_hybrid()) - rec_argc = argc + 11; /* max number of arguments */ - else - rec_argc = argc + 11 * perf_pmu__hybrid_pmu_num(); + /* Max number of arguments multiplied by number of PMUs that can support them. */ + rec_argc = argc + 11 * perf_pmus__num_mem_pmus(); rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 2603015f98be..2e8363778935 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -12,6 +12,7 @@ #include "util/debug.h" #include "util/config.h" #include <linux/string.h> +#include <limits.h> #include <stdio.h> #include <stdlib.h> @@ -157,7 +158,8 @@ int cmd_config(int argc, const char **argv) { int i, ret = -1; struct perf_config_set *set; - char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); + char path[PATH_MAX]; + char *user_config = mkpath(path, sizeof(path), "%s/.perfconfig", getenv("HOME")); const char *config_filename; bool changed = false; diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 34cbe3e959aa..f5674d824a40 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -90,7 +90,7 @@ struct daemon { char *base; struct list_head sessions; FILE *out; - char perf[PATH_MAX]; + char *perf; int signal_fd; time_t start; }; @@ -1490,6 +1490,14 @@ static int __cmd_ping(struct daemon *daemon, struct option parent_options[], return send_cmd(daemon, &cmd); } +static char *alloc_perf_exe_path(void) +{ + char path[PATH_MAX]; + + perf_exe(path, sizeof(path)); + return strdup(path); +} + int cmd_daemon(int argc, const char **argv) { struct option daemon_options[] = { @@ -1502,8 +1510,12 @@ int cmd_daemon(int argc, const char **argv) "field separator", "print counts with custom separator", ","), OPT_END() }; + int ret = -1; + + __daemon.perf = alloc_perf_exe_path(); + if (!__daemon.perf) + return -ENOMEM; - perf_exe(__daemon.perf, sizeof(__daemon.perf)); __daemon.out = stdout; argc = parse_options(argc, argv, daemon_options, daemon_usage, @@ -1511,22 +1523,22 @@ int cmd_daemon(int argc, const char **argv) if (argc) { if (!strcmp(argv[0], "start")) - return __cmd_start(&__daemon, daemon_options, argc, argv); + ret = __cmd_start(&__daemon, daemon_options, argc, argv); if (!strcmp(argv[0], "signal")) - return __cmd_signal(&__daemon, daemon_options, argc, argv); + ret = __cmd_signal(&__daemon, daemon_options, argc, argv); else if (!strcmp(argv[0], "stop")) - return __cmd_stop(&__daemon, daemon_options, argc, argv); + ret = __cmd_stop(&__daemon, daemon_options, argc, argv); else if (!strcmp(argv[0], "ping")) - return __cmd_ping(&__daemon, daemon_options, argc, argv); - - pr_err("failed: unknown command '%s'\n", argv[0]); - return -1; - } - - if (setup_config(&__daemon)) { - pr_err("failed: config not found\n"); - return -1; + ret = __cmd_ping(&__daemon, daemon_options, argc, argv); + else + pr_err("failed: unknown command '%s'\n", argv[0]); + } else { + ret = setup_config(&__daemon); + if (ret) + pr_err("failed: config not found\n"); + else + ret = send_cmd_list(&__daemon); } - - return send_cmd_list(&__daemon); + zfree(&__daemon.perf); + return ret; } diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index f9906f52e4fa..ac2e6c75f912 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -650,6 +650,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace) break; if (fwrite(buf, n, 1, stdout) != 1) break; + /* flush output since stdout is in full buffering mode due to pager */ + fflush(stdout); } } diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 3e7f52054fac..b2a368ae295a 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -19,6 +19,7 @@ #include <linux/string.h> #include <linux/zalloc.h> #include <errno.h> +#include <limits.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -389,9 +390,10 @@ static int get_html_page_path(char **page_path, const char *page) { struct stat st; const char *html_path = system_path(PERF_HTML_PATH); + char path[PATH_MAX]; /* Check that we have a perf documentation directory. */ - if (stat(mkpath("%s/perf.html", html_path), &st) + if (stat(mkpath(path, sizeof(path), "%s/perf.html", html_path), &st) || !S_ISREG(st.st_mode)) { pr_err("'%s': not a documentation directory.", html_path); return -1; diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 1f5dbd5f0ba4..03b5d26b2489 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -11,8 +11,8 @@ #include "builtin.h" #include "util/print-events.h" +#include "util/pmus.h" #include "util/pmu.h" -#include "util/pmu-hybrid.h" #include "util/debug.h" #include "util/metricgroup.h" #include "util/string2.h" @@ -192,9 +192,14 @@ static void default_print_metric(void *ps, if (group && print_state->metricgroups) { if (print_state->name_only) printf("%s ", group); - else if (print_state->metrics) - printf("\n%s:\n", group); - else + else if (print_state->metrics) { + const char *gdesc = describe_metricgroup(group); + + if (gdesc) + printf("\n%s: [%s]\n", group, gdesc); + else + printf("\n%s:\n", group); + } else printf("%s\n", group); } zfree(&print_state->last_metricgroups); @@ -429,7 +434,7 @@ int cmd_list(int argc, const char **argv) .print_event = default_print_event, .print_metric = default_print_metric, }; - const char *hybrid_name = NULL; + const char *cputype = NULL; const char *unit_name = NULL; bool json = false; struct option list_options[] = { @@ -443,8 +448,8 @@ int cmd_list(int argc, const char **argv) "Print information on the perf event names and expressions used internally by events."), OPT_BOOLEAN(0, "deprecated", &default_ps.deprecated, "Print deprecated events."), - OPT_STRING(0, "cputype", &hybrid_name, "hybrid cpu type", - "Limit PMU or metric printing to the given hybrid PMU (e.g. core or atom)."), + OPT_STRING(0, "cputype", &cputype, "cpu type", + "Limit PMU or metric printing to the given PMU (e.g. cpu, core or atom)."), OPT_STRING(0, "unit", &unit_name, "PMU name", "Limit PMU or metric printing to the specified PMU."), OPT_INCR(0, "debug", &verbose, @@ -484,10 +489,15 @@ int cmd_list(int argc, const char **argv) assert(default_ps.visited_metrics); if (unit_name) default_ps.pmu_glob = strdup(unit_name); - else if (hybrid_name) { - default_ps.pmu_glob = perf_pmu__hybrid_type_to_pmu(hybrid_name); - if (!default_ps.pmu_glob) - pr_warning("WARNING: hybrid cputype is not supported!\n"); + else if (cputype) { + const struct perf_pmu *pmu = perf_pmus__pmu_for_pmu_filter(cputype); + + if (!pmu) { + pr_err("ERROR: cputype is not supported!\n"); + ret = -1; + goto out; + } + default_ps.pmu_glob = pmu->name; } } print_cb.print_start(ps); @@ -517,7 +527,7 @@ int cmd_list(int argc, const char **argv) strcmp(argv[i], "hwcache") == 0) print_hwcache_events(&print_cb, ps); else if (strcmp(argv[i], "pmu") == 0) - print_pmu_events(&print_cb, ps); + perf_pmus__print_pmu_events(&print_cb, ps); else if (strcmp(argv[i], "sdt") == 0) print_sdt_events(&print_cb, ps); else if (strcmp(argv[i], "metric") == 0 || strcmp(argv[i], "metrics") == 0) { @@ -557,7 +567,7 @@ int cmd_list(int argc, const char **argv) event_symbols_sw, PERF_COUNT_SW_MAX); print_tool_events(&print_cb, ps); print_hwcache_events(&print_cb, ps); - print_pmu_events(&print_cb, ps); + perf_pmus__print_pmu_events(&print_cb, ps); print_tracepoint_events(&print_cb, ps); print_sdt_events(&print_cb, ps); default_ps.metrics = true; diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 70b14ba5fdd5..fc8356bd6e3a 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -48,7 +48,7 @@ static struct target target; #define LOCKHASH_BITS 12 #define LOCKHASH_SIZE (1UL << LOCKHASH_BITS) -static struct hlist_head lockhash_table[LOCKHASH_SIZE]; +static struct hlist_head *lockhash_table; #define __lockhashfn(key) hash_long((unsigned long)key, LOCKHASH_BITS) #define lockhashentry(key) (lockhash_table + __lockhashfn((key))) @@ -1871,7 +1871,6 @@ static int __cmd_contention(int argc, const char **argv) }; struct lock_contention con = { .target = &target, - .result = &lockhash_table[0], .map_nr_entries = bpf_map_entries, .max_stack = max_stack_depth, .stack_skip = stack_skip, @@ -1880,10 +1879,17 @@ static int __cmd_contention(int argc, const char **argv) .owner = show_lock_owner, }; + lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table)); + if (!lockhash_table) + return -ENOMEM; + + con.result = &lockhash_table[0]; + session = perf_session__new(use_bpf ? NULL : &data, &eops); if (IS_ERR(session)) { pr_err("Initializing perf session failed\n"); - return PTR_ERR(session); + err = PTR_ERR(session); + goto out_delete; } con.machine = &session->machines.host; @@ -1983,6 +1989,7 @@ out_delete: evlist__delete(con.evlist); lock_contention_finish(); perf_session__delete(session); + zfree(&lockhash_table); return err; } @@ -2348,6 +2355,10 @@ int cmd_lock(int argc, const char **argv) unsigned int i; int rc = 0; + lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table)); + if (!lockhash_table) + return -ENOMEM; + for (i = 0; i < LOCKHASH_SIZE; i++) INIT_HLIST_HEAD(lockhash_table + i); @@ -2369,7 +2380,7 @@ int cmd_lock(int argc, const char **argv) rc = __cmd_report(false); } else if (!strcmp(argv[0], "script")) { /* Aliased to 'perf script' */ - return cmd_script(argc, argv); + rc = cmd_script(argc, argv); } else if (!strcmp(argv[0], "info")) { if (argc) { argc = parse_options(argc, argv, @@ -2403,5 +2414,6 @@ int cmd_lock(int argc, const char **argv) usage_with_options(lock_usage, lock_options); } + zfree(&lockhash_table); return rc; } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 65465930ef8e..960bfd4b732a 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -17,8 +17,7 @@ #include "util/dso.h" #include "util/map.h" #include "util/symbol.h" -#include "util/pmu.h" -#include "util/pmu-hybrid.h" +#include "util/pmus.h" #include "util/sample.h" #include "util/string2.h" #include "util/util.h" @@ -93,10 +92,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_KEEP_UNKNOWN); - if (!perf_pmu__has_hybrid()) - rec_argc = argc + 9; /* max number of arguments */ - else - rec_argc = argc + 9 * perf_pmu__hybrid_pmu_num(); + /* Max number of arguments multiplied by number of PMUs that can support them. */ + rec_argc = argc + 9 * perf_pmus__num_mem_pmus(); if (mem->cpu_list) rec_argc += 2; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 4df05b992093..019fef8da6a8 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -47,29 +47,29 @@ static struct { char *target; struct strfilter *filter; struct nsinfo *nsi; -} params; +} *params; /* Parse an event definition. Note that any error must die. */ static int parse_probe_event(const char *str) { - struct perf_probe_event *pev = ¶ms.events[params.nevents]; + struct perf_probe_event *pev = ¶ms->events[params->nevents]; int ret; - pr_debug("probe-definition(%d): %s\n", params.nevents, str); - if (++params.nevents == MAX_PROBES) { + pr_debug("probe-definition(%d): %s\n", params->nevents, str); + if (++params->nevents == MAX_PROBES) { pr_err("Too many probes (> %d) were specified.", MAX_PROBES); return -1; } - pev->uprobes = params.uprobes; - if (params.target) { - pev->target = strdup(params.target); + pev->uprobes = params->uprobes; + if (params->target) { + pev->target = strdup(params->target); if (!pev->target) return -ENOMEM; - params.target_used = true; + params->target_used = true; } - pev->nsi = nsinfo__get(params.nsi); + pev->nsi = nsinfo__get(params->nsi); /* Parse a perf-probe command into event */ ret = parse_perf_probe_command(str, pev); @@ -84,12 +84,12 @@ static int params_add_filter(const char *str) int ret = 0; pr_debug2("Add filter: %s\n", str); - if (!params.filter) { - params.filter = strfilter__new(str, &err); - if (!params.filter) + if (!params->filter) { + params->filter = strfilter__new(str, &err); + if (!params->filter) ret = err ? -EINVAL : -ENOMEM; } else - ret = strfilter__or(params.filter, str, &err); + ret = strfilter__or(params->filter, str, &err); if (ret == -EINVAL) { pr_err("Filter parse error at %td.\n", err - str + 1); @@ -112,17 +112,17 @@ static int set_target(const char *ptr) * TODO: Support relative path, and $PATH, $LD_LIBRARY_PATH, * short module name. */ - if (!params.target && ptr && *ptr == '/') { - params.target = strdup(ptr); - if (!params.target) + if (!params->target && ptr && *ptr == '/') { + params->target = strdup(ptr); + if (!params->target) return -ENOMEM; - params.target_used = false; + params->target_used = false; found = 1; buf = ptr + (strlen(ptr) - 3); if (strcmp(buf, ".ko")) - params.uprobes = true; + params->uprobes = true; } @@ -172,15 +172,15 @@ static int opt_set_target(const struct option *opt, const char *str, if (str) { if (!strcmp(opt->long_name, "exec")) - params.uprobes = true; + params->uprobes = true; else if (!strcmp(opt->long_name, "module")) - params.uprobes = false; + params->uprobes = false; else return ret; /* Expand given path to absolute path, except for modulename */ - if (params.uprobes || strchr(str, '/')) { - tmp = nsinfo__realpath(str, params.nsi); + if (params->uprobes || strchr(str, '/')) { + tmp = nsinfo__realpath(str, params->nsi); if (!tmp) { pr_warning("Failed to get the absolute path of %s: %m\n", str); return ret; @@ -190,9 +190,9 @@ static int opt_set_target(const struct option *opt, const char *str, if (!tmp) return -ENOMEM; } - free(params.target); - params.target = tmp; - params.target_used = false; + free(params->target); + params->target = tmp; + params->target_used = false; ret = 0; } @@ -217,7 +217,7 @@ static int opt_set_target_ns(const struct option *opt __maybe_unused, } nsip = nsinfo__new(ns_pid); if (nsip && nsinfo__need_setns(nsip)) - params.nsi = nsinfo__get(nsip); + params->nsi = nsinfo__get(nsip); nsinfo__put(nsip); ret = 0; @@ -238,14 +238,14 @@ static int opt_show_lines(const struct option *opt, if (!str) return 0; - if (params.command == 'L') { + if (params->command == 'L') { pr_warning("Warning: more than one --line options are" " detected. Only the first one is valid.\n"); return 0; } - params.command = opt->short_name; - ret = parse_line_range_desc(str, ¶ms.line_range); + params->command = opt->short_name; + ret = parse_line_range_desc(str, ¶ms->line_range); return ret; } @@ -253,7 +253,7 @@ static int opt_show_lines(const struct option *opt, static int opt_show_vars(const struct option *opt, const char *str, int unset __maybe_unused) { - struct perf_probe_event *pev = ¶ms.events[params.nevents]; + struct perf_probe_event *pev = ¶ms->events[params->nevents]; int ret; if (!str) @@ -264,7 +264,7 @@ static int opt_show_vars(const struct option *opt, pr_err(" Error: '--vars' doesn't accept arguments.\n"); return -EINVAL; } - params.command = opt->short_name; + params->command = opt->short_name; return ret; } @@ -276,7 +276,7 @@ static int opt_add_probe_event(const struct option *opt, const char *str, int unset __maybe_unused) { if (str) { - params.command = opt->short_name; + params->command = opt->short_name; return parse_probe_event(str); } @@ -287,7 +287,7 @@ static int opt_set_filter_with_command(const struct option *opt, const char *str, int unset) { if (!unset) - params.command = opt->short_name; + params->command = opt->short_name; if (str) return params_add_filter(str); @@ -306,20 +306,29 @@ static int opt_set_filter(const struct option *opt __maybe_unused, static int init_params(void) { - return line_range__init(¶ms.line_range); + int ret; + + params = calloc(1, sizeof(*params)); + if (!params) + return -ENOMEM; + + ret = line_range__init(¶ms->line_range); + if (ret) + zfree(¶ms); + return ret; } static void cleanup_params(void) { int i; - for (i = 0; i < params.nevents; i++) - clear_perf_probe_event(params.events + i); - line_range__clear(¶ms.line_range); - free(params.target); - strfilter__delete(params.filter); - nsinfo__put(params.nsi); - memset(¶ms, 0, sizeof(params)); + for (i = 0; i < params->nevents; i++) + clear_perf_probe_event(params->events + i); + line_range__clear(¶ms->line_range); + free(params->target); + strfilter__delete(params->filter); + nsinfo__put(params->nsi); + zfree(¶ms); } static void pr_err_with_code(const char *msg, int err) @@ -346,7 +355,7 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs) if (ret < 0) goto out_cleanup; - if (params.command == 'D') { /* it shows definition */ + if (params->command == 'D') { /* it shows definition */ if (probe_conf.bootconfig) ret = show_bootconfig_events(pevs, npevs); else @@ -635,7 +644,7 @@ __cmd_probe(int argc, const char **argv) usage_with_options_msg(probe_usage, options, "'-' is not supported.\n"); } - if (params.command && params.command != 'a') { + if (params->command && params->command != 'a') { usage_with_options_msg(probe_usage, options, "another command except --add is set.\n"); } @@ -644,7 +653,7 @@ __cmd_probe(int argc, const char **argv) pr_err_with_code(" Error: Command Parse Error.", ret); return ret; } - params.command = 'a'; + params->command = 'a'; } ret = symbol__validate_sym_arguments(); @@ -664,54 +673,54 @@ __cmd_probe(int argc, const char **argv) * nor change running kernel. So if user gives offline vmlinux, * ignore its buildid. */ - if (!strchr("lda", params.command) && symbol_conf.vmlinux_name) + if (!strchr("lda", params->command) && symbol_conf.vmlinux_name) symbol_conf.ignore_vmlinux_buildid = true; - switch (params.command) { + switch (params->command) { case 'l': - if (params.uprobes) { + if (params->uprobes) { pr_err(" Error: Don't use --list with --exec.\n"); parse_options_usage(probe_usage, options, "l", true); parse_options_usage(NULL, options, "x", true); return -EINVAL; } - ret = show_perf_probe_events(params.filter); + ret = show_perf_probe_events(params->filter); if (ret < 0) pr_err_with_code(" Error: Failed to show event list.", ret); return ret; case 'F': - ret = show_available_funcs(params.target, params.nsi, - params.filter, params.uprobes); + ret = show_available_funcs(params->target, params->nsi, + params->filter, params->uprobes); if (ret < 0) pr_err_with_code(" Error: Failed to show functions.", ret); return ret; #ifdef HAVE_DWARF_SUPPORT case 'L': - ret = show_line_range(¶ms.line_range, params.target, - params.nsi, params.uprobes); + ret = show_line_range(¶ms->line_range, params->target, + params->nsi, params->uprobes); if (ret < 0) pr_err_with_code(" Error: Failed to show lines.", ret); return ret; case 'V': - if (!params.filter) - params.filter = strfilter__new(DEFAULT_VAR_FILTER, + if (!params->filter) + params->filter = strfilter__new(DEFAULT_VAR_FILTER, NULL); - ret = show_available_vars(params.events, params.nevents, - params.filter); + ret = show_available_vars(params->events, params->nevents, + params->filter); if (ret < 0) pr_err_with_code(" Error: Failed to show vars.", ret); return ret; #endif case 'd': - ret = perf_del_probe_events(params.filter); + ret = perf_del_probe_events(params->filter); if (ret < 0) { pr_err_with_code(" Error: Failed to delete events.", ret); return ret; } break; case 'D': - if (probe_conf.bootconfig && params.uprobes) { + if (probe_conf.bootconfig && params->uprobes) { pr_err(" Error: --bootconfig doesn't support uprobes.\n"); return -EINVAL; } @@ -719,25 +728,25 @@ __cmd_probe(int argc, const char **argv) case 'a': /* Ensure the last given target is used */ - if (params.target && !params.target_used) { + if (params->target && !params->target_used) { pr_err(" Error: -x/-m must follow the probe definitions.\n"); parse_options_usage(probe_usage, options, "m", true); parse_options_usage(NULL, options, "x", true); return -EINVAL; } - ret = perf_add_probe_events(params.events, params.nevents); + ret = perf_add_probe_events(params->events, params->nevents); if (ret < 0) { /* * When perf_add_probe_events() fails it calls * cleanup_perf_probe_events(pevs, npevs), i.e. - * cleanup_perf_probe_events(params.events, params.nevents), which + * cleanup_perf_probe_events(params->events, params->nevents), which * will call clear_perf_probe_event(), so set nevents to zero * to avoid cleanup_params() to call clear_perf_probe_event() again * on the same pevs. */ - params.nevents = 0; + params->nevents = 0; pr_err_with_code(" Error: Failed to add events.", ret); return ret; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index efa03e4ac2c9..aec18db7ff23 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -48,9 +48,9 @@ #include "util/bpf-event.h" #include "util/util.h" #include "util/pfm.h" +#include "util/pmu.h" +#include "util/pmus.h" #include "util/clockid.h" -#include "util/pmu-hybrid.h" -#include "util/evlist-hybrid.h" #include "util/off_cpu.h" #include "util/bpf-filter.h" #include "asm/bug.h" @@ -1294,7 +1294,7 @@ static int record__open(struct record *rec) * of waiting or event synthesis. */ if (opts->target.initial_delay || target__has_cpu(&opts->target) || - perf_pmu__has_hybrid()) { + perf_pmus__num_core_pmus() > 1) { pos = evlist__get_tracking_event(evlist); if (!evsel__is_dummy_event(pos)) { /* Set up dummy event. */ @@ -2193,7 +2193,7 @@ static void record__uniquify_name(struct record *rec) char *new_name; int ret; - if (!perf_pmu__has_hybrid()) + if (perf_pmus__num_core_pmus() == 1) return; evlist__for_each_entry(evlist, pos) { @@ -3335,6 +3335,14 @@ const char record_callchain_help[] = CALLCHAIN_RECORD_HELP static bool dry_run; +static struct parse_events_option_args parse_events_option_args = { + .evlistp = &record.evlist, +}; + +static struct parse_events_option_args switch_output_parse_events_option_args = { + .evlistp = &record.sb_evlist, +}; + /* * XXX Will stay a global variable till we fix builtin-script.c to stop messing * with it and switch to use the library functions in perf_evlist that came @@ -3343,7 +3351,7 @@ static bool dry_run; * using pipes, etc. */ static struct option __record_options[] = { - OPT_CALLBACK('e', "event", &record.evlist, "event", + OPT_CALLBACK('e', "event", &parse_events_option_args, "event", "event selector. use 'perf list' to list available events", parse_events_option), OPT_CALLBACK(0, "filter", &record.evlist, "filter", @@ -3496,7 +3504,8 @@ static struct option __record_options[] = { &record.switch_output.set, "signal or size[BKMG] or time[smhd]", "Switch output when receiving SIGUSR2 (signal) or cross a size or time threshold", "signal"), - OPT_CALLBACK_SET(0, "switch-output-event", &record.sb_evlist, &record.switch_output_event_set, "switch output event", + OPT_CALLBACK_SET(0, "switch-output-event", &switch_output_parse_events_option_args, + &record.switch_output_event_set, "switch output event", "switch output event selector. use 'perf list' to list available events", parse_events_option_new_evlist), OPT_INTEGER(0, "switch-max-files", &record.switch_output.num_files, @@ -4152,18 +4161,11 @@ int cmd_record(int argc, const char **argv) record.opts.tail_synthesize = true; if (rec->evlist->core.nr_entries == 0) { - if (perf_pmu__has_hybrid()) { - err = evlist__add_default_hybrid(rec->evlist, - !record.opts.no_samples); - } else { - err = __evlist__add_default(rec->evlist, - !record.opts.no_samples); - } + bool can_profile_kernel = perf_event_paranoid_check(1); - if (err < 0) { - pr_err("Not enough memory for event selector list\n"); + err = parse_event(rec->evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu"); + if (err) goto out; - } } if (rec->opts.target.tid && !rec->opts.no_inherit_set) @@ -4189,13 +4191,7 @@ int cmd_record(int argc, const char **argv) /* Enable ignoring missing threads when -u/-p option is defined. */ rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid; - if (evlist__fix_hybrid_cpus(rec->evlist, rec->opts.target.cpu_list)) { - pr_err("failed to use cpu list %s\n", - rec->opts.target.cpu_list); - goto out; - } - - rec->opts.target.hybrid = perf_pmu__has_hybrid(); + evlist__warn_user_requested_cpus(rec->evlist, rec->opts.target.cpu_list); if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP) arch__add_leaf_frame_record_opts(&rec->opts); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c57be48d65bb..029d5a597233 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -133,6 +133,7 @@ enum perf_output_field { PERF_OUTPUT_VCPU = 1ULL << 38, PERF_OUTPUT_CGROUP = 1ULL << 39, PERF_OUTPUT_RETIRE_LAT = 1ULL << 40, + PERF_OUTPUT_DSOFF = 1ULL << 41, }; struct perf_script { @@ -174,6 +175,7 @@ struct output_option { {.str = "ip", .field = PERF_OUTPUT_IP}, {.str = "sym", .field = PERF_OUTPUT_SYM}, {.str = "dso", .field = PERF_OUTPUT_DSO}, + {.str = "dsoff", .field = PERF_OUTPUT_DSOFF}, {.str = "addr", .field = PERF_OUTPUT_ADDR}, {.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET}, {.str = "srcline", .field = PERF_OUTPUT_SRCLINE}, @@ -574,6 +576,9 @@ static void set_print_ip_opts(struct perf_event_attr *attr) if (PRINT_FIELD(DSO)) output[type].print_ip_opts |= EVSEL__PRINT_DSO; + if (PRINT_FIELD(DSOFF)) + output[type].print_ip_opts |= EVSEL__PRINT_DSOFF; + if (PRINT_FIELD(SYMOFFSET)) output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET; @@ -627,6 +632,10 @@ static int perf_session__check_output_opt(struct perf_session *session) if (evsel == NULL) continue; + /* 'dsoff' implys 'dso' field */ + if (output[j].fields & PERF_OUTPUT_DSOFF) + output[j].fields |= PERF_OUTPUT_DSO; + set_print_ip_opts(&evsel->core.attr); tod |= output[j].fields & PERF_OUTPUT_TOD; } @@ -929,18 +938,12 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, } printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); } @@ -972,18 +975,12 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, thread__find_symbol_fb(thread, sample->cpumode, to, &alt); printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "%c", '/'); printed += symbol__fprintf_symname_offs(alt.sym, &alt, fp); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); } @@ -1019,17 +1016,11 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, to = map__dso_map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alf.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alf.map, PRINT_FIELD(DSOFF), alf.addr, fp); printed += fprintf(fp, "/0x%"PRIx64, to); - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, "("); - printed += map__fprintf_dsoname(alt.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(alt.map, PRINT_FIELD(DSOFF), alt.addr, fp); printed += print_bstack_flags(fp, entries + i); } @@ -1393,11 +1384,8 @@ static int perf_sample__fprintf_addr(struct perf_sample *sample, printed += symbol__fprintf_symname(al.sym, fp); } - if (PRINT_FIELD(DSO)) { - printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(al.map, fp); - printed += fprintf(fp, ")"); - } + if (PRINT_FIELD(DSO)) + printed += map__fprintf_dsoname_dsoff(al.map, PRINT_FIELD(DSOFF), al.addr, fp); out: return printed; } @@ -3883,7 +3871,7 @@ int cmd_script(int argc, const char **argv) "comma separated output fields prepend with 'type:'. " "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " - "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," + "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff" "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,data_src,weight,bpf-output,brstackinsn," "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth," diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b9ad32f21e57..c87c6897edc9 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -44,10 +44,10 @@ #include "util/cgroup.h" #include <subcmd/parse-options.h> #include "util/parse-events.h" +#include "util/pmus.h" #include "util/pmu.h" #include "util/event.h" #include "util/evlist.h" -#include "util/evlist-hybrid.h" #include "util/evsel.h" #include "util/debug.h" #include "util/color.h" @@ -69,7 +69,6 @@ #include "util/pfm.h" #include "util/bpf_counter.h" #include "util/iostat.h" -#include "util/pmu-hybrid.h" #include "util/util.h" #include "asm/bug.h" @@ -101,6 +100,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv); static struct evlist *evsel_list; +static struct parse_events_option_args parse_events_option_args = { + .evlistp = &evsel_list, +}; + static bool all_counters_use_bpf = true; static struct target target = { @@ -138,6 +141,7 @@ struct perf_stat { struct perf_cpu_map *cpus; struct perf_thread_map *threads; enum aggr_mode aggr_mode; + u32 aggr_level; }; static struct perf_stat perf_stat; @@ -147,6 +151,7 @@ static volatile sig_atomic_t done = 0; static struct perf_stat_config stat_config = { .aggr_mode = AGGR_GLOBAL, + .aggr_level = MAX_CACHE_LVL + 1, .scale = true, .unit_width = 4, /* strlen("unit") */ .run_count = 1, @@ -183,9 +188,6 @@ static void evlist__check_cpu_maps(struct evlist *evlist) { struct evsel *evsel, *warned_leader = NULL; - if (evlist__has_hybrid(evlist)) - evlist__warn_hybrid_group(evlist); - evlist__for_each_entry(evlist, evsel) { struct evsel *leader = evsel__leader(evsel); @@ -1085,10 +1087,11 @@ static int parse_stat_cgroups(const struct option *opt, return parse_cgroups(opt, str, unset); } -static int parse_hybrid_type(const struct option *opt, +static int parse_cputype(const struct option *opt, const char *str, int unset __maybe_unused) { + const struct perf_pmu *pmu; struct evlist *evlist = *(struct evlist **)opt->value; if (!list_empty(&evlist->core.entries)) { @@ -1096,19 +1099,69 @@ static int parse_hybrid_type(const struct option *opt, return -1; } - evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str); - if (!evlist->hybrid_pmu_name) { + pmu = perf_pmus__pmu_for_pmu_filter(str); + if (!pmu) { fprintf(stderr, "--cputype %s is not supported!\n", str); return -1; } + parse_events_option_args.pmu_filter = pmu->name; return 0; } +static int parse_cache_level(const struct option *opt, + const char *str, + int unset __maybe_unused) +{ + int level; + u32 *aggr_mode = (u32 *)opt->value; + u32 *aggr_level = (u32 *)opt->data; + + /* + * If no string is specified, aggregate based on the topology of + * Last Level Cache (LLC). Since the LLC level can change from + * architecture to architecture, set level greater than + * MAX_CACHE_LVL which will be interpreted as LLC. + */ + if (str == NULL) { + level = MAX_CACHE_LVL + 1; + goto out; + } + + /* + * The format to specify cache level is LX or lX where X is the + * cache level. + */ + if (strlen(str) != 2 || (str[0] != 'l' && str[0] != 'L')) { + pr_err("Cache level must be of form L[1-%d], or l[1-%d]\n", + MAX_CACHE_LVL, + MAX_CACHE_LVL); + return -EINVAL; + } + + level = atoi(&str[1]); + if (level < 1) { + pr_err("Cache level must be of form L[1-%d], or l[1-%d]\n", + MAX_CACHE_LVL, + MAX_CACHE_LVL); + return -EINVAL; + } + + if (level > MAX_CACHE_LVL) { + pr_err("perf only supports max cache level of %d.\n" + "Consider increasing MAX_CACHE_LVL\n", MAX_CACHE_LVL); + return -EINVAL; + } +out: + *aggr_mode = AGGR_CACHE; + *aggr_level = level; + return 0; +} + static struct option stat_options[] = { OPT_BOOLEAN('T', "transaction", &transaction_run, "hardware transaction statistics"), - OPT_CALLBACK('e', "event", &evsel_list, "event", + OPT_CALLBACK('e', "event", &parse_events_option_args, "event", "event selector. use 'perf list' to list available events", parse_events_option), OPT_CALLBACK(0, "filter", &evsel_list, "filter", @@ -1182,6 +1235,9 @@ static struct option stat_options[] = { "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-die", &stat_config.aggr_mode, "aggregate counts per processor die", AGGR_DIE), + OPT_CALLBACK_OPTARG(0, "per-cache", &stat_config.aggr_mode, &stat_config.aggr_level, + "cache level", "aggregate count at this cache level (Default: LLC)", + parse_cache_level), OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode, @@ -1226,7 +1282,7 @@ static struct option stat_options[] = { OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type", "Only enable events on applying cpu with this type " "for hybrid platform (e.g. core or atom)", - parse_hybrid_type), + parse_cputype), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", @@ -1243,8 +1299,132 @@ static struct option stat_options[] = { OPT_END() }; +/** + * Calculate the cache instance ID from the map in + * /sys/devices/system/cpu/cpuX/cache/indexY/shared_cpu_list + * Cache instance ID is the first CPU reported in the shared_cpu_list file. + */ +static int cpu__get_cache_id_from_map(struct perf_cpu cpu, char *map) +{ + int id; + struct perf_cpu_map *cpu_map = perf_cpu_map__new(map); + + /* + * If the map contains no CPU, consider the current CPU to + * be the first online CPU in the cache domain else use the + * first online CPU of the cache domain as the ID. + */ + if (perf_cpu_map__empty(cpu_map)) + id = cpu.cpu; + else + id = perf_cpu_map__cpu(cpu_map, 0).cpu; + + /* Free the perf_cpu_map used to find the cache ID */ + perf_cpu_map__put(cpu_map); + + return id; +} + +/** + * cpu__get_cache_id - Returns 0 if successful in populating the + * cache level and cache id. Cache level is read from + * /sys/devices/system/cpu/cpuX/cache/indexY/level where as cache instance ID + * is the first CPU reported by + * /sys/devices/system/cpu/cpuX/cache/indexY/shared_cpu_list + */ +static int cpu__get_cache_details(struct perf_cpu cpu, struct perf_cache *cache) +{ + int ret = 0; + u32 cache_level = stat_config.aggr_level; + struct cpu_cache_level caches[MAX_CACHE_LVL]; + u32 i = 0, caches_cnt = 0; + + cache->cache_lvl = (cache_level > MAX_CACHE_LVL) ? 0 : cache_level; + cache->cache = -1; + + ret = build_caches_for_cpu(cpu.cpu, caches, &caches_cnt); + if (ret) { + /* + * If caches_cnt is not 0, cpu_cache_level data + * was allocated when building the topology. + * Free the allocated data before returning. + */ + if (caches_cnt) + goto free_caches; + + return ret; + } + + if (!caches_cnt) + return -1; + + /* + * Save the data for the highest level if no + * level was specified by the user. + */ + if (cache_level > MAX_CACHE_LVL) { + int max_level_index = 0; + + for (i = 1; i < caches_cnt; ++i) { + if (caches[i].level > caches[max_level_index].level) + max_level_index = i; + } + + cache->cache_lvl = caches[max_level_index].level; + cache->cache = cpu__get_cache_id_from_map(cpu, caches[max_level_index].map); + + /* Reset i to 0 to free entire caches[] */ + i = 0; + goto free_caches; + } + + for (i = 0; i < caches_cnt; ++i) { + if (caches[i].level == cache_level) { + cache->cache_lvl = cache_level; + cache->cache = cpu__get_cache_id_from_map(cpu, caches[i].map); + } + + cpu_cache_level__free(&caches[i]); + } + +free_caches: + /* + * Free all the allocated cpu_cache_level data. + */ + while (i < caches_cnt) + cpu_cache_level__free(&caches[i++]); + + return ret; +} + +/** + * aggr_cpu_id__cache - Create an aggr_cpu_id with cache instache ID, cache + * level, die and socket populated with the cache instache ID, cache level, + * die and socket for cpu. The function signature is compatible with + * aggr_cpu_id_get_t. + */ +static struct aggr_cpu_id aggr_cpu_id__cache(struct perf_cpu cpu, void *data) +{ + int ret; + struct aggr_cpu_id id; + struct perf_cache cache; + + id = aggr_cpu_id__die(cpu, data); + if (aggr_cpu_id__is_empty(&id)) + return id; + + ret = cpu__get_cache_details(cpu, &cache); + if (ret) + return id; + + id.cache_lvl = cache.cache_lvl; + id.cache = cache.cache; + return id; +} + static const char *const aggr_mode__string[] = { [AGGR_CORE] = "core", + [AGGR_CACHE] = "cache", [AGGR_DIE] = "die", [AGGR_GLOBAL] = "global", [AGGR_NODE] = "node", @@ -1266,6 +1446,12 @@ static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __m return aggr_cpu_id__die(cpu, /*data=*/NULL); } +static struct aggr_cpu_id perf_stat__get_cache_id(struct perf_stat_config *config __maybe_unused, + struct perf_cpu cpu) +{ + return aggr_cpu_id__cache(cpu, /*data=*/NULL); +} + static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused, struct perf_cpu cpu) { @@ -1318,6 +1504,12 @@ static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *con return perf_stat__get_aggr(config, perf_stat__get_die, cpu); } +static struct aggr_cpu_id perf_stat__get_cache_id_cached(struct perf_stat_config *config, + struct perf_cpu cpu) +{ + return perf_stat__get_aggr(config, perf_stat__get_cache_id, cpu); +} + static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config, struct perf_cpu cpu) { @@ -1349,6 +1541,8 @@ static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode) return aggr_cpu_id__socket; case AGGR_DIE: return aggr_cpu_id__die; + case AGGR_CACHE: + return aggr_cpu_id__cache; case AGGR_CORE: return aggr_cpu_id__core; case AGGR_NODE: @@ -1372,6 +1566,8 @@ static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode) return perf_stat__get_socket_cached; case AGGR_DIE: return perf_stat__get_die_cached; + case AGGR_CACHE: + return perf_stat__get_cache_id_cached; case AGGR_CORE: return perf_stat__get_core_cached; case AGGR_NODE: @@ -1484,6 +1680,60 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, voi return id; } +static void perf_env__get_cache_id_for_cpu(struct perf_cpu cpu, struct perf_env *env, + u32 cache_level, struct aggr_cpu_id *id) +{ + int i; + int caches_cnt = env->caches_cnt; + struct cpu_cache_level *caches = env->caches; + + id->cache_lvl = (cache_level > MAX_CACHE_LVL) ? 0 : cache_level; + id->cache = -1; + + if (!caches_cnt) + return; + + for (i = caches_cnt - 1; i > -1; --i) { + struct perf_cpu_map *cpu_map; + int map_contains_cpu; + + /* + * If user has not specified a level, find the fist level with + * the cpu in the map. Since building the map is expensive, do + * this only if levels match. + */ + if (cache_level <= MAX_CACHE_LVL && caches[i].level != cache_level) + continue; + + cpu_map = perf_cpu_map__new(caches[i].map); + map_contains_cpu = perf_cpu_map__idx(cpu_map, cpu); + perf_cpu_map__put(cpu_map); + + if (map_contains_cpu != -1) { + id->cache_lvl = caches[i].level; + id->cache = cpu__get_cache_id_from_map(cpu, caches[i].map); + return; + } + } +} + +static struct aggr_cpu_id perf_env__get_cache_aggr_by_cpu(struct perf_cpu cpu, + void *data) +{ + struct perf_env *env = data; + struct aggr_cpu_id id = aggr_cpu_id__empty(); + + if (cpu.cpu != -1) { + u32 cache_level = (perf_stat.aggr_level) ?: stat_config.aggr_level; + + id.socket = env->cpu[cpu.cpu].socket_id; + id.die = env->cpu[cpu.cpu].die_id; + perf_env__get_cache_id_for_cpu(cpu, env, cache_level, &id); + } + + return id; +} + static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data) { struct perf_env *env = data; @@ -1552,6 +1802,12 @@ static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *confi return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env); } +static struct aggr_cpu_id perf_stat__get_cache_file(struct perf_stat_config *config __maybe_unused, + struct perf_cpu cpu) +{ + return perf_env__get_cache_aggr_by_cpu(cpu, &perf_stat.session->header.env); +} + static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu cpu) { @@ -1583,6 +1839,8 @@ static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode) return perf_env__get_socket_aggr_by_cpu; case AGGR_DIE: return perf_env__get_die_aggr_by_cpu; + case AGGR_CACHE: + return perf_env__get_cache_aggr_by_cpu; case AGGR_CORE: return perf_env__get_core_aggr_by_cpu; case AGGR_NODE: @@ -1606,6 +1864,8 @@ static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode) return perf_stat__get_socket_file; case AGGR_DIE: return perf_stat__get_die_file; + case AGGR_CACHE: + return perf_stat__get_cache_file; case AGGR_CORE: return perf_stat__get_core_file; case AGGR_NODE: @@ -1777,6 +2037,7 @@ static int add_default_attributes(void) }; struct perf_event_attr default_null_attrs[] = {}; + const char *pmu = parse_events_option_args.pmu_filter ?: "all"; /* Set attrs if no event is selected and !null_run: */ if (stat_config.null_run) @@ -1788,11 +2049,11 @@ static int add_default_attributes(void) * will use this approach. To determine transaction support * on an architecture test for such a metric name. */ - if (!metricgroup__has_metric("transaction")) { + if (!metricgroup__has_metric(pmu, "transaction")) { pr_err("Missing transaction metrics"); return -1; } - return metricgroup__parse_groups(evsel_list, "transaction", + return metricgroup__parse_groups(evsel_list, pmu, "transaction", stat_config.metric_no_group, stat_config.metric_no_merge, stat_config.metric_no_threshold, @@ -1817,7 +2078,7 @@ static int add_default_attributes(void) smi_reset = true; } - if (!metricgroup__has_metric("smi")) { + if (!metricgroup__has_metric(pmu, "smi")) { pr_err("Missing smi metrics"); return -1; } @@ -1825,7 +2086,7 @@ static int add_default_attributes(void) if (!force_metric_only) stat_config.metric_only = true; - return metricgroup__parse_groups(evsel_list, "smi", + return metricgroup__parse_groups(evsel_list, pmu, "smi", stat_config.metric_no_group, stat_config.metric_no_merge, stat_config.metric_no_threshold, @@ -1858,7 +2119,8 @@ static int add_default_attributes(void) "Please print the result regularly, e.g. -I1000\n"); } str[8] = stat_config.topdown_level + '0'; - if (metricgroup__parse_groups(evsel_list, str, + if (metricgroup__parse_groups(evsel_list, + pmu, str, /*metric_no_group=*/false, /*metric_no_merge=*/false, /*metric_no_threshold=*/true, @@ -1878,11 +2140,11 @@ static int add_default_attributes(void) if (evlist__add_default_attrs(evsel_list, default_attrs0) < 0) return -1; - if (pmu_have_event("cpu", "stalled-cycles-frontend")) { + if (perf_pmus__have_event("cpu", "stalled-cycles-frontend")) { if (evlist__add_default_attrs(evsel_list, frontend_attrs) < 0) return -1; } - if (pmu_have_event("cpu", "stalled-cycles-backend")) { + if (perf_pmus__have_event("cpu", "stalled-cycles-backend")) { if (evlist__add_default_attrs(evsel_list, backend_attrs) < 0) return -1; } @@ -1892,19 +2154,14 @@ static int add_default_attributes(void) * Add TopdownL1 metrics if they exist. To minimize * multiplexing, don't request threshold computation. */ - /* - * TODO: TopdownL1 is disabled on hybrid CPUs to avoid a crashes - * caused by exposing latent bugs. This is fixed properly in: - * https://lore.kernel.org/lkml/[email protected]/ - */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + if (metricgroup__has_metric(pmu, "TopdownL1")) { struct evlist *metric_evlist = evlist__new(); struct evsel *metric_evsel; if (!metric_evlist) return -1; - if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + if (metricgroup__parse_groups(metric_evlist, pmu, "TopdownL1", /*metric_no_group=*/false, /*metric_no_merge=*/false, /*metric_no_threshold=*/true, @@ -2124,7 +2381,8 @@ static struct perf_stat perf_stat = { .stat = perf_event__process_stat_event, .stat_round = process_stat_round_event, }, - .aggr_mode = AGGR_UNSET, + .aggr_mode = AGGR_UNSET, + .aggr_level = 0, }; static int __cmd_report(int argc, const char **argv) @@ -2136,6 +2394,10 @@ static int __cmd_report(int argc, const char **argv) "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-die", &perf_stat.aggr_mode, "aggregate counts per processor die", AGGR_DIE), + OPT_CALLBACK_OPTARG(0, "per-cache", &perf_stat.aggr_mode, &perf_stat.aggr_level, + "cache level", + "aggregate count at this cache level (Default: LLC)", + parse_cache_level), OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), OPT_SET_UINT(0, "per-node", &perf_stat.aggr_mode, @@ -2428,7 +2690,9 @@ int cmd_stat(int argc, const char **argv) * knowing the target is system-wide. */ if (metrics) { - metricgroup__parse_groups(evsel_list, metrics, + const char *pmu = parse_events_option_args.pmu_filter ?: "all"; + + metricgroup__parse_groups(evsel_list, pmu, metrics, stat_config.metric_no_group, stat_config.metric_no_merge, stat_config.metric_no_threshold, @@ -2457,12 +2721,8 @@ int cmd_stat(int argc, const char **argv) } } - if (evlist__fix_hybrid_cpus(evsel_list, target.cpu_list)) { - pr_err("failed to use cpu list %s\n", target.cpu_list); - goto out; - } + evlist__warn_user_requested_cpus(evsel_list, target.cpu_list); - target.hybrid = perf_pmu__has_hybrid(); if (evlist__create_maps(evsel_list, &target) < 0) { if (target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index bce1cf896f9c..829d99fecfd0 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -315,10 +315,10 @@ static void pid_put_sample(struct timechart *tchart, int pid, int type, #define MAX_CPUS 4096 -static u64 cpus_cstate_start_times[MAX_CPUS]; -static int cpus_cstate_state[MAX_CPUS]; -static u64 cpus_pstate_start_times[MAX_CPUS]; -static u64 cpus_pstate_state[MAX_CPUS]; +static u64 *cpus_cstate_start_times; +static int *cpus_cstate_state; +static u64 *cpus_pstate_start_times; +static u64 *cpus_pstate_state; static int process_comm_event(struct perf_tool *tool, union perf_event *event, @@ -1981,12 +1981,34 @@ int cmd_timechart(int argc, const char **argv) "perf timechart record [<options>]", NULL }; + int ret; + + cpus_cstate_start_times = calloc(MAX_CPUS, sizeof(*cpus_cstate_start_times)); + if (!cpus_cstate_start_times) + return -ENOMEM; + cpus_cstate_state = calloc(MAX_CPUS, sizeof(*cpus_cstate_state)); + if (!cpus_cstate_state) { + ret = -ENOMEM; + goto out; + } + cpus_pstate_start_times = calloc(MAX_CPUS, sizeof(*cpus_pstate_start_times)); + if (!cpus_pstate_start_times) { + ret = -ENOMEM; + goto out; + } + cpus_pstate_state = calloc(MAX_CPUS, sizeof(*cpus_pstate_state)); + if (!cpus_pstate_state) { + ret = -ENOMEM; + goto out; + } + argc = parse_options_subcommand(argc, argv, timechart_options, timechart_subcommands, timechart_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (tchart.power_only && tchart.tasks_only) { pr_err("-P and -T options cannot be used at the same time.\n"); - return -1; + ret = -1; + goto out; } if (argc && strlen(argv[0]) > 2 && strstarts("record", argv[0])) { @@ -1996,17 +2018,25 @@ int cmd_timechart(int argc, const char **argv) if (tchart.power_only && tchart.tasks_only) { pr_err("-P and -T options cannot be used at the same time.\n"); - return -1; + ret = -1; + goto out; } if (tchart.io_only) - return timechart__io_record(argc, argv); + ret = timechart__io_record(argc, argv); else - return timechart__record(&tchart, argc, argv); + ret = timechart__record(&tchart, argc, argv); + goto out; } else if (argc) usage_with_options(timechart_usage, timechart_options); setup_pager(); - return __cmd_timechart(&tchart, output_name); + ret = __cmd_timechart(&tchart, output_name); +out: + zfree(&cpus_cstate_start_times); + zfree(&cpus_cstate_state); + zfree(&cpus_pstate_start_times); + zfree(&cpus_pstate_state); + return ret; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index eb5740154bc0..27a7f068207d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1440,12 +1440,15 @@ int cmd_top(int argc, const char **argv) .max_stack = sysctl__max_stack(), .nr_threads_synthesize = UINT_MAX, }; + struct parse_events_option_args parse_events_option_args = { + .evlistp = &top.evlist, + }; bool branch_call_mode = false; struct record_opts *opts = &top.record_opts; struct target *target = &opts->target; const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; const struct option options[] = { - OPT_CALLBACK('e', "event", &top.evlist, "event", + OPT_CALLBACK('e', "event", &parse_events_option_args, "event", "event selector. use 'perf list' to list available events", parse_events_option), OPT_U64('c', "count", &opts->user_interval, "event period to sample"), @@ -1650,10 +1653,12 @@ int cmd_top(int argc, const char **argv) if (annotate_check_args(&top.annotation_opts) < 0) goto out_delete_evlist; - if (!top.evlist->core.nr_entries && - evlist__add_default(top.evlist) < 0) { - pr_err("Not enough memory for event selector list\n"); - goto out_delete_evlist; + if (!top.evlist->core.nr_entries) { + bool can_profile_kernel = perf_event_paranoid_check(1); + int err = parse_event(top.evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu"); + + if (err) + goto out_delete_evlist; } status = evswitch__init(&top.evswitch, top.evlist, stderr); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 8ee3a45c3c54..62c7c99a0fe4 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -914,7 +914,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, #include "trace/beauty/socket_type.c" #include "trace/beauty/waitid_options.c" -static struct syscall_fmt syscall_fmts[] = { +static const struct syscall_fmt syscall_fmts[] = { { .name = "access", .arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, }, { .name = "arch_prctl", @@ -1176,18 +1176,21 @@ static int syscall_fmt__cmp(const void *name, const void *fmtp) return strcmp(name, fmt->name); } -static struct syscall_fmt *__syscall_fmt__find(struct syscall_fmt *fmts, const int nmemb, const char *name) +static const struct syscall_fmt *__syscall_fmt__find(const struct syscall_fmt *fmts, + const int nmemb, + const char *name) { return bsearch(name, fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp); } -static struct syscall_fmt *syscall_fmt__find(const char *name) +static const struct syscall_fmt *syscall_fmt__find(const char *name) { const int nmemb = ARRAY_SIZE(syscall_fmts); return __syscall_fmt__find(syscall_fmts, nmemb, name); } -static struct syscall_fmt *__syscall_fmt__find_by_alias(struct syscall_fmt *fmts, const int nmemb, const char *alias) +static const struct syscall_fmt *__syscall_fmt__find_by_alias(const struct syscall_fmt *fmts, + const int nmemb, const char *alias) { int i; @@ -1199,7 +1202,7 @@ static struct syscall_fmt *__syscall_fmt__find_by_alias(struct syscall_fmt *fmts return NULL; } -static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias) +static const struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias) { const int nmemb = ARRAY_SIZE(syscall_fmts); return __syscall_fmt__find_by_alias(syscall_fmts, nmemb, alias); @@ -1224,7 +1227,7 @@ struct syscall { bool nonexistent; struct tep_format_field *args; const char *name; - struct syscall_fmt *fmt; + const struct syscall_fmt *fmt; struct syscall_arg_fmt *arg_fmt; }; @@ -1673,7 +1676,7 @@ static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args) return 0; } -static struct syscall_arg_fmt syscall_arg_fmts__by_name[] = { +static const struct syscall_arg_fmt syscall_arg_fmts__by_name[] = { { .name = "msr", .scnprintf = SCA_X86_MSR, .strtoul = STUL_X86_MSR, }, { .name = "vector", .scnprintf = SCA_X86_IRQ_VECTORS, .strtoul = STUL_X86_IRQ_VECTORS, }, }; @@ -1684,13 +1687,14 @@ static int syscall_arg_fmt__cmp(const void *name, const void *fmtp) return strcmp(name, fmt->name); } -static struct syscall_arg_fmt * -__syscall_arg_fmt__find_by_name(struct syscall_arg_fmt *fmts, const int nmemb, const char *name) +static const struct syscall_arg_fmt * +__syscall_arg_fmt__find_by_name(const struct syscall_arg_fmt *fmts, const int nmemb, + const char *name) { return bsearch(name, fmts, nmemb, sizeof(struct syscall_arg_fmt), syscall_arg_fmt__cmp); } -static struct syscall_arg_fmt *syscall_arg_fmt__find_by_name(const char *name) +static const struct syscall_arg_fmt *syscall_arg_fmt__find_by_name(const char *name) { const int nmemb = ARRAY_SIZE(syscall_arg_fmts__by_name); return __syscall_arg_fmt__find_by_name(syscall_arg_fmts__by_name, nmemb, name); @@ -1735,8 +1739,9 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field * 7 unsigned long */ arg->scnprintf = SCA_FD; - } else { - struct syscall_arg_fmt *fmt = syscall_arg_fmt__find_by_name(field->name); + } else { + const struct syscall_arg_fmt *fmt = + syscall_arg_fmt__find_by_name(field->name); if (fmt) { arg->scnprintf = fmt->scnprintf; @@ -4458,7 +4463,7 @@ static void evsel__set_syscall_arg_fmt(struct evsel *evsel, const char *name) struct syscall_arg_fmt *fmt = evsel__syscall_arg_fmt(evsel); if (fmt) { - struct syscall_fmt *scfmt = syscall_fmt__find(name); + const struct syscall_fmt *scfmt = syscall_fmt__find(name); if (scfmt) { int skip = 0; @@ -4525,7 +4530,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str, int len = strlen(str) + 1, err = -1, list, idx; char *strace_groups_dir = system_path(STRACE_GROUPS_DIR); char group_name[PATH_MAX]; - struct syscall_fmt *fmt; + const struct syscall_fmt *fmt; if (strace_groups_dir == NULL) return -1; @@ -4591,8 +4596,11 @@ do_concat: err = 0; if (lists[0]) { + struct parse_events_option_args parse_events_option_args = { + .evlistp = &trace->evlist, + }; struct option o = { - .value = &trace->evlist, + .value = &parse_events_option_args, }; err = parse_events_option(&o, lists[0], 0); } diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/branch.json new file mode 100644 index 000000000000..c751d57f2e19 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/branch.json @@ -0,0 +1,17 @@ +[ + { + "ArchStdEvent": "BR_IMMED_SPEC" + }, + { + "ArchStdEvent": "BR_RETURN_SPEC" + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC" + }, + { + "ArchStdEvent": "BR_MIS_PRED" + }, + { + "ArchStdEvent": "BR_PRED" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/bus.json new file mode 100644 index 000000000000..8623be121818 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/bus.json @@ -0,0 +1,32 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES" + }, + { + "ArchStdEvent": "BUS_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS_RD" + }, + { + "ArchStdEvent": "BUS_ACCESS_WR" + }, + { + "ArchStdEvent": "BUS_ACCESS_SHARED" + }, + { + "ArchStdEvent": "BUS_ACCESS_NOT_SHARED" + }, + { + "ArchStdEvent": "BUS_ACCESS_NORMAL" + }, + { + "ArchStdEvent": "BUS_ACCESS_PERIPH" + }, + { + "ArchStdEvent": "BUS_ACCESS" + }, + { + "ArchStdEvent": "CNT_CYCLES" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json new file mode 100644 index 000000000000..fc0633054211 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json @@ -0,0 +1,104 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1I_TLB_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL" + }, + { + "ArchStdEvent": "L1I_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L2D_CACHE_WB" + }, + { + "ArchStdEvent": "L1D_TLB" + }, + { + "ArchStdEvent": "L1I_TLB" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL" + }, + { + "ArchStdEvent": "L2I_TLB_REFILL" + }, + { + "ArchStdEvent": "L2D_TLB" + }, + { + "ArchStdEvent": "L2I_TLB" + }, + { + "ArchStdEvent": "DTLB_WALK" + }, + { + "ArchStdEvent": "ITLB_WALK" + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS" + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS" + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json new file mode 100644 index 000000000000..95c30243f2b2 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json @@ -0,0 +1,698 @@ +[ + { + "PublicDescription": "Level 2 prefetch requests, refilled to L2 cache", + "EventCode": "0x10A", + "EventName": "L2_PREFETCH_REFILL", + "BriefDescription": "Level 2 prefetch requests, refilled to L2 cache" + }, + { + "PublicDescription": "Level 2 prefetch requests, late", + "EventCode": "0x10B", + "EventName": "L2_PREFETCH_UPGRADE", + "BriefDescription": "Level 2 prefetch requests, late" + }, + { + "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB", + "EventCode": "0x110", + "EventName": "BPU_HIT_BTB", + "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB" + }, + { + "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB", + "EventCode": "0x111", + "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB", + "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor", + "EventCode": "0x112", + "EventName": "BPU_HIT_INDIRECT_PREDICTOR", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor", + "EventCode": "0x113", + "EventName": "BPU_HIT_RSB", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor" + }, + { + "PublicDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB", + "EventCode": "0x114", + "EventName": "BPU_UNCONDITIONAL_BRANCH_MISS_BTB", + "BriefDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB" + }, + { + "PublicDescription": "Predictable branch speculatively executed, unpredicted", + "EventCode": "0x115", + "EventName": "BPU_BRANCH_NO_HIT", + "BriefDescription": "Predictable branch speculatively executed, unpredicted" + }, + { + "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict", + "EventCode": "0x116", + "EventName": "BPU_HIT_BTB_AND_MISPREDICT", + "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict" + }, + { + "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict", + "EventCode": "0x117", + "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB_AND_MISPREDICT", + "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict", + "EventCode": "0x118", + "EventName": "BPU_INDIRECT_BRANCH_HIT_BTB_AND_MISPREDICT", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict", + "EventCode": "0x119", + "EventName": "BPU_HIT_RSB_AND_MISPREDICT", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict", + "EventCode": "0x11a", + "EventName": "BPU_MISS_RSB_AND_MISPREDICT", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict" + }, + { + "PublicDescription": "Predictable branch speculatively executed, unpredicted, that mispredict", + "EventCode": "0x11b", + "EventName": "BPU_NO_PREDICTION_MISPREDICT", + "BriefDescription": "Predictable branch speculatively executed, unpredicted, that mispredict" + }, + { + "PublicDescription": "Predictable branch speculatively executed, unpredicted, that mispredict", + "EventCode": "0x11c", + "EventName": "BPU_BTB_UPDATE", + "BriefDescription": "Predictable branch speculatively executed, unpredicted, that mispredict" + }, + { + "PublicDescription": "Count predict pipe stalls due to speculative return address predictor full", + "EventCode": "0x11d", + "EventName": "BPU_RSB_FULL_STALL", + "BriefDescription": "Count predict pipe stalls due to speculative return address predictor full" + }, + { + "PublicDescription": "Macro-ops speculatively decoded", + "EventCode": "0x11f", + "EventName": "ICF_INST_SPEC_DECODE", + "BriefDescription": "Macro-ops speculatively decoded" + }, + { + "PublicDescription": "Flushes", + "EventCode": "0x120", + "EventName": "GPC_FLUSH", + "BriefDescription": "Flushes" + }, + { + "PublicDescription": "Flushes due to memory hazards", + "EventCode": "0x121", + "EventName": "BPU_FLUSH_MEM_FAULT", + "BriefDescription": "Flushes due to memory hazards" + }, + { + "PublicDescription": "ETM extout bit 0", + "EventCode": "0x141", + "EventName": "MSC_ETM_EXTOUT0", + "BriefDescription": "ETM extout bit 0" + }, + { + "PublicDescription": "ETM extout bit 1", + "EventCode": "0x142", + "EventName": "MSC_ETM_EXTOUT1", + "BriefDescription": "ETM extout bit 1" + }, + { + "PublicDescription": "ETM extout bit 2", + "EventCode": "0x143", + "EventName": "MSC_ETM_EXTOUT2", + "BriefDescription": "ETM extout bit 2" + }, + { + "PublicDescription": "ETM extout bit 3", + "EventCode": "0x144", + "EventName": "MSC_ETM_EXTOUT3", + "BriefDescription": "ETM extout bit 3" + }, + { + "PublicDescription": "Bus request sn", + "EventCode": "0x156", + "EventName": "L2C_SNOOP", + "BriefDescription": "Bus request sn" + }, + { + "PublicDescription": "L2 TXDAT LCRD blocked", + "EventCode": "0x169", + "EventName": "L2C_DAT_CRD_STALL", + "BriefDescription": "L2 TXDAT LCRD blocked" + }, + { + "PublicDescription": "L2 TXRSP LCRD blocked", + "EventCode": "0x16a", + "EventName": "L2C_RSP_CRD_STALL", + "BriefDescription": "L2 TXRSP LCRD blocked" + }, + { + "PublicDescription": "L2 TXREQ LCRD blocked", + "EventCode": "0x16b", + "EventName": "L2C_REQ_CRD_STALL", + "BriefDescription": "L2 TXREQ LCRD blocked" + }, + { + "PublicDescription": "Early mispredict", + "EventCode": "0xD100", + "EventName": "ICF_EARLY_MIS_PRED", + "BriefDescription": "Early mispredict" + }, + { + "PublicDescription": "FEQ full cycles", + "EventCode": "0xD101", + "EventName": "ICF_FEQ_FULL", + "BriefDescription": "FEQ full cycles" + }, + { + "PublicDescription": "Instruction FIFO Full", + "EventCode": "0xD102", + "EventName": "ICF_INST_FIFO_FULL", + "BriefDescription": "Instruction FIFO Full" + }, + { + "PublicDescription": "L1I TLB miss", + "EventCode": "0xD103", + "EventName": "L1I_TLB_MISS", + "BriefDescription": "L1I TLB miss" + }, + { + "PublicDescription": "ICF sent 0 instructions to IDR this cycle", + "EventCode": "0xD104", + "EventName": "ICF_STALL", + "BriefDescription": "ICF sent 0 instructions to IDR this cycle" + }, + { + "PublicDescription": "PC FIFO Full", + "EventCode": "0xD105", + "EventName": "ICF_PC_FIFO_FULL", + "BriefDescription": "PC FIFO Full" + }, + { + "PublicDescription": "Stall due to BOB ID", + "EventCode": "0xD200", + "EventName": "IDR_STALL_BOB_ID", + "BriefDescription": "Stall due to BOB ID" + }, + { + "PublicDescription": "Dispatch stall due to LOB entries", + "EventCode": "0xD201", + "EventName": "IDR_STALL_LOB_ID", + "BriefDescription": "Dispatch stall due to LOB entries" + }, + { + "PublicDescription": "Dispatch stall due to SOB entries", + "EventCode": "0xD202", + "EventName": "IDR_STALL_SOB_ID", + "BriefDescription": "Dispatch stall due to SOB entries" + }, + { + "PublicDescription": "Dispatch stall due to IXU scheduler entries", + "EventCode": "0xD203", + "EventName": "IDR_STALL_IXU_SCHED", + "BriefDescription": "Dispatch stall due to IXU scheduler entries" + }, + { + "PublicDescription": "Dispatch stall due to FSU scheduler entries", + "EventCode": "0xD204", + "EventName": "IDR_STALL_FSU_SCHED", + "BriefDescription": "Dispatch stall due to FSU scheduler entries" + }, + { + "PublicDescription": "Dispatch stall due to ROB entries", + "EventCode": "0xD205", + "EventName": "IDR_STALL_ROB_ID", + "BriefDescription": "Dispatch stall due to ROB entries" + }, + { + "PublicDescription": "Dispatch stall due to flush (6 cycles)", + "EventCode": "0xD206", + "EventName": "IDR_STALL_FLUSH", + "BriefDescription": "Dispatch stall due to flush (6 cycles)" + }, + { + "PublicDescription": "Dispatch stall due to WFI", + "EventCode": "0xD207", + "EventName": "IDR_STALL_WFI", + "BriefDescription": "Dispatch stall due to WFI" + }, + { + "PublicDescription": "Number of SWOB drains triggered by timeout", + "EventCode": "0xD208", + "EventName": "IDR_STALL_SWOB_TIMEOUT", + "BriefDescription": "Number of SWOB drains triggered by timeout" + }, + { + "PublicDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain", + "EventCode": "0xD209", + "EventName": "IDR_STALL_SWOB_RAW", + "BriefDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain" + }, + { + "PublicDescription": "Number of SWOB drains triggered by system register write when SWOB full", + "EventCode": "0xD20A", + "EventName": "IDR_STALL_SWOB_FULL", + "BriefDescription": "Number of SWOB drains triggered by system register write when SWOB full" + }, + { + "PublicDescription": "Dispatch stall due to L1 instruction cache miss", + "EventCode": "0xD20B", + "EventName": "STALL_FRONTEND_CACHE", + "BriefDescription": "Dispatch stall due to L1 instruction cache miss" + }, + { + "PublicDescription": "Dispatch stall due to L1 instruction TLB miss", + "EventCode": "0xD20C", + "EventName": "STALL_FRONTEND_TLB", + "BriefDescription": "Dispatch stall due to L1 instruction TLB miss" + }, + { + "PublicDescription": "Dispatch stall due to L1 data cache miss", + "EventCode": "0xD20D", + "EventName": "STALL_BACKEND_CACHE", + "BriefDescription": "Dispatch stall due to L1 data cache miss" + }, + { + "PublicDescription": "Dispatch stall due to L1 data TLB miss", + "EventCode": "0xD20E", + "EventName": "STALL_BACKEND_TLB", + "BriefDescription": "Dispatch stall due to L1 data TLB miss" + }, + { + "PublicDescription": "Dispatch stall due to lack of any core resource", + "EventCode": "0xD20F", + "EventName": "STALL_BACKEND_RESOURCE", + "BriefDescription": "Dispatch stall due to lack of any core resource" + }, + { + "PublicDescription": "Instructions issued by the scheduler", + "EventCode": "0xD300", + "EventName": "IXU_NUM_UOPS_ISSUED", + "BriefDescription": "Instructions issued by the scheduler" + }, + { + "PublicDescription": "Any uop issued was canceled for any reason", + "EventCode": "0xD301", + "EventName": "IXU_ISSUE_CANCEL", + "BriefDescription": "Any uop issued was canceled for any reason" + }, + { + "PublicDescription": "A load wakeup to the scheduler has been cancelled", + "EventCode": "0xD302", + "EventName": "IXU_LOAD_CANCEL", + "BriefDescription": "A load wakeup to the scheduler has been cancelled" + }, + { + "PublicDescription": "The scheduler had to cancel one slow Uop due to resource conflict", + "EventCode": "0xD303", + "EventName": "IXU_SLOW_CANCEL", + "BriefDescription": "The scheduler had to cancel one slow Uop due to resource conflict" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXA", + "EventCode": "0xD304", + "EventName": "IXU_IXA_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXA" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXA Par 0", + "EventCode": "0xD305", + "EventName": "IXU_IXA_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXA Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXA Par 1", + "EventCode": "0xD306", + "EventName": "IXU_IXA_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXA Par 1" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXB", + "EventCode": "0xD307", + "EventName": "IXU_IXB_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXB" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXB Par 0", + "EventCode": "0xD308", + "EventName": "IXU_IXB_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXB Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXB Par 1", + "EventCode": "0xD309", + "EventName": "IXU_IXB_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXB Par 1" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXC", + "EventCode": "0xD30A", + "EventName": "IXU_IXC_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXC" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXC Par 0", + "EventCode": "0xD30B", + "EventName": "IXU_IXC_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXC Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXC Par 1", + "EventCode": "0xD30C", + "EventName": "IXU_IXC_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXC Par 1" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXD", + "EventCode": "0xD30D", + "EventName": "IXU_IXD_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXD" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXD Par 0", + "EventCode": "0xD30E", + "EventName": "IXU_IXD_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXD Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXD Par 1", + "EventCode": "0xD30F", + "EventName": "IXU_IXD_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXD Par 1" + }, + { + "PublicDescription": "Uops issued by the FSU scheduler", + "EventCode": "0xD400", + "EventName": "FSU_ISSUED", + "BriefDescription": "Uops issued by the FSU scheduler" + }, + { + "PublicDescription": "Uops issued by the scheduler on pipe X", + "EventCode": "0xD401", + "EventName": "FSU_FSX_ISSUED", + "BriefDescription": "Uops issued by the scheduler on pipe X" + }, + { + "PublicDescription": "Uops issued by the scheduler on pipe Y", + "EventCode": "0xD402", + "EventName": "FSU_FSY_ISSUED", + "BriefDescription": "Uops issued by the scheduler on pipe Y" + }, + { + "PublicDescription": "Uops issued by the scheduler on pipe Z", + "EventCode": "0xD403", + "EventName": "FSU_FSZ_ISSUED", + "BriefDescription": "Uops issued by the scheduler on pipe Z" + }, + { + "PublicDescription": "Uops canceled (load cancels)", + "EventCode": "0xD404", + "EventName": "FSU_CANCEL", + "BriefDescription": "Uops canceled (load cancels)" + }, + { + "PublicDescription": "Count scheduler stalls due to divide/sqrt", + "EventCode": "0xD405", + "EventName": "FSU_DIV_SQRT_STALL", + "BriefDescription": "Count scheduler stalls due to divide/sqrt" + }, + { + "PublicDescription": "Number of SWOB drains", + "EventCode": "0xD500", + "EventName": "GPC_SWOB_DRAIN", + "BriefDescription": "Number of SWOB drains" + }, + { + "PublicDescription": "GPC detected a Breakpoint instruction match", + "EventCode": "0xD501", + "EventName": "BREAKPOINT_MATCH", + "BriefDescription": "GPC detected a Breakpoint instruction match" + }, + { + "PublicDescription": "L1D TLB miss", + "EventCode": "0xD600", + "EventName": "L1D_TLB_MISS", + "BriefDescription": "L1D TLB miss" + }, + { + "PublicDescription": "OFB full cycles", + "EventCode": "0xD601", + "EventName": "OFB_FULL", + "BriefDescription": "OFB full cycles" + }, + { + "PublicDescription": "Load satisified from store forwarded data", + "EventCode": "0xD605", + "EventName": "LD_FROM_ST_FWD", + "BriefDescription": "Load satisified from store forwarded data" + }, + { + "PublicDescription": "L1 prefetcher, load prefetch requests generated", + "EventCode": "0xD606", + "EventName": "L1_PFETCH_LD_GEN", + "BriefDescription": "L1 prefetcher, load prefetch requests generated" + }, + { + "PublicDescription": "L1 prefetcher, load prefetch fills into the L1 cache", + "EventCode": "0xD607", + "EventName": "L1_PFETCH_LD_FILL", + "BriefDescription": "L1 prefetcher, load prefetch fills into the L1 cache" + }, + { + "PublicDescription": "L1 prefetcher, load prefetch to L2 generated", + "EventCode": "0xD608", + "EventName": "L1_PFETCH_L2_REQ", + "BriefDescription": "L1 prefetcher, load prefetch to L2 generated" + }, + { + "PublicDescription": "L1 prefetcher, distance was reset", + "EventCode": "0xD609", + "EventName": "L1_PFETCH_DIST_RST", + "BriefDescription": "L1 prefetcher, distance was reset" + }, + { + "PublicDescription": "L1 prefetcher, distance was increased", + "EventCode": "0xD60A", + "EventName": "L1_PFETCH_DIST_INC", + "BriefDescription": "L1 prefetcher, distance was increased" + }, + { + "PublicDescription": "L1 prefetcher, table entry is trained", + "EventCode": "0xD60B", + "EventName": "L1_PFETCH_ENTRY_TRAINED", + "BriefDescription": "L1 prefetcher, table entry is trained" + }, + { + "PublicDescription": "Store retirement pipe stall", + "EventCode": "0xD60C", + "EventName": "LSU_ST_RETIRE_STALL", + "BriefDescription": "Store retirement pipe stall" + }, + { + "PublicDescription": "LSU detected a Watchpoint data match", + "EventCode": "0xD60D", + "EventName": "WATCHPOINT_MATCH", + "BriefDescription": "LSU detected a Watchpoint data match" + }, + { + "PublicDescription": "L2 pipeline replay", + "EventCode": "0xD700", + "EventName": "L2C_PIPE_REPLAY", + "BriefDescription": "L2 pipeline replay" + }, + { + "PublicDescription": "L2 refill from I-side miss", + "EventCode": "0xD701", + "EventName": "L2C_INST_REFILL", + "BriefDescription": "L2 refill from I-side miss" + }, + { + "PublicDescription": "L2 refill from D-side miss", + "EventCode": "0xD702", + "EventName": "L2C_DATA_REFILL", + "BriefDescription": "L2 refill from D-side miss" + }, + { + "PublicDescription": "L2 prefetcher, load prefetch requests generated", + "EventCode": "0xD703", + "EventName": "L2_PREFETCH_REQ", + "BriefDescription": "L2 prefetcher, load prefetch requests generated" + }, + { + "PublicDescription": "L2D OTB allocate", + "EventCode": "0xD800", + "EventName": "MMU_D_OTB_ALLOC", + "BriefDescription": "L2D OTB allocate" + }, + { + "PublicDescription": "DTLB Translation cache hit on S1L2 walk cache entry", + "EventCode": "0xD801", + "EventName": "MMU_D_TRANS_CACHE_HIT_S1L2_WALK", + "BriefDescription": "DTLB Translation cache hit on S1L2 walk cache entry" + }, + { + "PublicDescription": "DTLB Translation cache hit on S1L1 walk cache entry", + "EventCode": "0xD802", + "EventName": "MMU_D_TRANS_CACHE_HIT_S1L1_WALK", + "BriefDescription": "DTLB Translation cache hit on S1L1 walk cache entry" + }, + { + "PublicDescription": "DTLB Translation cache hit on S1L0 walk cache entry", + "EventCode": "0xD803", + "EventName": "MMU_D_TRANS_CACHE_HIT_S1L0_WALK", + "BriefDescription": "DTLB Translation cache hit on S1L0 walk cache entry" + }, + { + "PublicDescription": "DTLB Translation cache hit on S2L2 walk cache entry", + "EventCode": "0xD804", + "EventName": "MMU_D_TRANS_CACHE_HIT_S2L2_WALK", + "BriefDescription": "DTLB Translation cache hit on S2L2 walk cache entry" + }, + { + "PublicDescription": "DTLB Translation cache hit on S2L1 walk cache entry", + "EventCode": "0xD805", + "EventName": "MMU_D_TRANS_CACHE_HIT_S2L1_WALK", + "BriefDescription": "DTLB Translation cache hit on S2L1 walk cache entry" + }, + { + "PublicDescription": "DTLB Translation cache hit on S2L0 walk cache entry", + "EventCode": "0xD806", + "EventName": "MMU_D_TRANS_CACHE_HIT_S2L0_WALK", + "BriefDescription": "DTLB Translation cache hit on S2L0 walk cache entry" + }, + { + "PublicDescription": "D-side S1 Page walk cache lookup", + "EventCode": "0xD807", + "EventName": "MMU_D_S1_WALK_CACHE_LOOKUP", + "BriefDescription": "D-side S1 Page walk cache lookup" + }, + { + "PublicDescription": "D-side S1 Page walk cache refill", + "EventCode": "0xD808", + "EventName": "MMU_D_S1_WALK_CACHE_REFILL", + "BriefDescription": "D-side S1 Page walk cache refill" + }, + { + "PublicDescription": "D-side S2 Page walk cache lookup", + "EventCode": "0xD809", + "EventName": "MMU_D_S2_WALK_CACHE_LOOKUP", + "BriefDescription": "D-side S2 Page walk cache lookup" + }, + { + "PublicDescription": "D-side S2 Page walk cache refill", + "EventCode": "0xD80A", + "EventName": "MMU_D_S2_WALK_CACHE_REFILL", + "BriefDescription": "D-side S2 Page walk cache refill" + }, + { + "PublicDescription": "D-side Stage1 tablewalk fault", + "EventCode": "0xD80B", + "EventName": "MMU_D_S1_WALK_FAULT", + "BriefDescription": "D-side Stage1 tablewalk fault" + }, + { + "PublicDescription": "D-side Stage2 tablewalk fault", + "EventCode": "0xD80C", + "EventName": "MMU_D_S2_WALK_FAULT", + "BriefDescription": "D-side Stage2 tablewalk fault" + }, + { + "PublicDescription": "D-side Tablewalk steps or descriptor fetches", + "EventCode": "0xD80D", + "EventName": "MMU_D_WALK_STEPS", + "BriefDescription": "D-side Tablewalk steps or descriptor fetches" + }, + { + "PublicDescription": "L2I OTB allocate", + "EventCode": "0xD900", + "EventName": "MMU_I_OTB_ALLOC", + "BriefDescription": "L2I OTB allocate" + }, + { + "PublicDescription": "ITLB Translation cache hit on S1L2 walk cache entry", + "EventCode": "0xD901", + "EventName": "MMU_I_TRANS_CACHE_HIT_S1L2_WALK", + "BriefDescription": "ITLB Translation cache hit on S1L2 walk cache entry" + }, + { + "PublicDescription": "ITLB Translation cache hit on S1L1 walk cache entry", + "EventCode": "0xD902", + "EventName": "MMU_I_TRANS_CACHE_HIT_S1L1_WALK", + "BriefDescription": "ITLB Translation cache hit on S1L1 walk cache entry" + }, + { + "PublicDescription": "ITLB Translation cache hit on S1L0 walk cache entry", + "EventCode": "0xD903", + "EventName": "MMU_I_TRANS_CACHE_HIT_S1L0_WALK", + "BriefDescription": "ITLB Translation cache hit on S1L0 walk cache entry" + }, + { + "PublicDescription": "ITLB Translation cache hit on S2L2 walk cache entry", + "EventCode": "0xD904", + "EventName": "MMU_I_TRANS_CACHE_HIT_S2L2_WALK", + "BriefDescription": "ITLB Translation cache hit on S2L2 walk cache entry" + }, + { + "PublicDescription": "ITLB Translation cache hit on S2L1 walk cache entry", + "EventCode": "0xD905", + "EventName": "MMU_I_TRANS_CACHE_HIT_S2L1_WALK", + "BriefDescription": "ITLB Translation cache hit on S2L1 walk cache entry" + }, + { + "PublicDescription": "ITLB Translation cache hit on S2L0 walk cache entry", + "EventCode": "0xD906", + "EventName": "MMU_I_TRANS_CACHE_HIT_S2L0_WALK", + "BriefDescription": "ITLB Translation cache hit on S2L0 walk cache entry" + }, + { + "PublicDescription": "I-side S1 Page walk cache lookup", + "EventCode": "0xD907", + "EventName": "MMU_I_S1_WALK_CACHE_LOOKUP", + "BriefDescription": "I-side S1 Page walk cache lookup" + }, + { + "PublicDescription": "I-side S1 Page walk cache refill", + "EventCode": "0xD908", + "EventName": "MMU_I_S1_WALK_CACHE_REFILL", + "BriefDescription": "I-side S1 Page walk cache refill" + }, + { + "PublicDescription": "I-side S2 Page walk cache lookup", + "EventCode": "0xD909", + "EventName": "MMU_I_S2_WALK_CACHE_LOOKUP", + "BriefDescription": "I-side S2 Page walk cache lookup" + }, + { + "PublicDescription": "I-side S2 Page walk cache refill", + "EventCode": "0xD90A", + "EventName": "MMU_I_S2_WALK_CACHE_REFILL", + "BriefDescription": "I-side S2 Page walk cache refill" + }, + { + "PublicDescription": "I-side Stage1 tablewalk fault", + "EventCode": "0xD90B", + "EventName": "MMU_I_S1_WALK_FAULT", + "BriefDescription": "I-side Stage1 tablewalk fault" + }, + { + "PublicDescription": "I-side Stage2 tablewalk fault", + "EventCode": "0xD90C", + "EventName": "MMU_I_S2_WALK_FAULT", + "BriefDescription": "I-side Stage2 tablewalk fault" + }, + { + "PublicDescription": "I-side Tablewalk steps or descriptor fetches", + "EventCode": "0xD90D", + "EventName": "MMU_I_WALK_STEPS", + "BriefDescription": "I-side Tablewalk steps or descriptor fetches" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/exception.json new file mode 100644 index 000000000000..ada052e19632 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/exception.json @@ -0,0 +1,44 @@ +[ + { + "ArchStdEvent": "EXC_UNDEF" + }, + { + "ArchStdEvent": "EXC_SVC" + }, + { + "ArchStdEvent": "EXC_PABORT" + }, + { + "ArchStdEvent": "EXC_DABORT" + }, + { + "ArchStdEvent": "EXC_IRQ" + }, + { + "ArchStdEvent": "EXC_FIQ" + }, + { + "ArchStdEvent": "EXC_HVC" + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER" + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ" + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ" + }, + { + "ArchStdEvent": "EXC_TAKEN" + }, + { + "ArchStdEvent": "EXC_RETURN" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json new file mode 100644 index 000000000000..18d1f2f76a23 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/instruction.json @@ -0,0 +1,89 @@ +[ + { + "ArchStdEvent": "SW_INCR" + }, + { + "ArchStdEvent": "ST_RETIRED" + }, + { + "ArchStdEvent": "OP_SPEC" + }, + { + "ArchStdEvent": "LD_SPEC" + }, + { + "ArchStdEvent": "ST_SPEC" + }, + { + "ArchStdEvent": "LDST_SPEC" + }, + { + "ArchStdEvent": "DP_SPEC" + }, + { + "ArchStdEvent": "ASE_SPEC" + }, + { + "ArchStdEvent": "VFP_SPEC" + }, + { + "ArchStdEvent": "PC_WRITE_SPEC" + }, + { + "ArchStdEvent": "BR_IMMED_RETIRED" + }, + { + "ArchStdEvent": "BR_RETURN_RETIRED" + }, + { + "ArchStdEvent": "CRYPTO_SPEC" + }, + { + "ArchStdEvent": "ISB_SPEC" + }, + { + "ArchStdEvent": "DSB_SPEC" + }, + { + "ArchStdEvent": "DMB_SPEC" + }, + { + "ArchStdEvent": "RC_LD_SPEC" + }, + { + "ArchStdEvent": "RC_ST_SPEC" + }, + { + "ArchStdEvent": "INST_RETIRED" + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED" + }, + { + "ArchStdEvent": "PC_WRITE_RETIRED" + }, + { + "ArchStdEvent": "INST_SPEC" + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED" + }, + { + "ArchStdEvent": "BR_RETIRED" + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED" + }, + { + "ArchStdEvent": "OP_RETIRED" + }, + { + "ArchStdEvent": "OP_SPEC" + }, + { + "PublicDescription": "Operation speculatively executed, NOP", + "EventCode": "0x100", + "EventName": "NOP_SPEC", + "BriefDescription": "Speculatively executed, NOP" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/intrinsic.json new file mode 100644 index 000000000000..7ecffb989ae0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/intrinsic.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "LDREX_SPEC" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC" + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC" + }, + { + "ArchStdEvent": "STREX_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json new file mode 100644 index 000000000000..0711782bfa6b --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/memory.json @@ -0,0 +1,44 @@ +[ + { + "ArchStdEvent": "LD_RETIRED" + }, + { + "ArchStdEvent": "MEM_ACCESS_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_WR" + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC" + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC" + }, + { + "ArchStdEvent": "LD_ALIGN_LAT" + }, + { + "ArchStdEvent": "ST_ALIGN_LAT" + }, + { + "ArchStdEvent": "MEM_ACCESS" + }, + { + "ArchStdEvent": "MEMORY_ERROR" + }, + { + "ArchStdEvent": "LDST_ALIGN_LAT" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json new file mode 100644 index 000000000000..f9fae15f7555 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/pipeline.json @@ -0,0 +1,23 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND" + }, + { + "ArchStdEvent": "STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND" + }, + { + "ArchStdEvent": "STALL_SLOT" + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/spe.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/spe.json new file mode 100644 index 000000000000..20f2165c85fe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/spe.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP" + }, + { + "ArchStdEvent": "SAMPLE_FEED" + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE" + }, + { + "ArchStdEvent": "SAMPLE_COLLISION" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 9d400785d195..32674ddd2b63 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -41,3 +41,4 @@ 0x00000000460f0010,v1,fujitsu/a64fx,core 0x00000000480fd010,v1,hisilicon/hip08,core 0x00000000500f0000,v1,ampere/emag,core +0x00000000c00fac30,v1,ampere/ampereone,core diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 1f9047553942..c9f7e3d4ab08 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -71,7 +71,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -120,7 +120,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", - "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_alloc_restriction", "MetricThreshold": "tma_alloc_restriction > 0.1", @@ -129,7 +129,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", @@ -151,7 +151,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", - "MetricExpr": "(tma_info_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_slots", + "MetricExpr": "(tma_info_core_slots - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -162,7 +162,7 @@ }, { "BriefDescription": "Counts the number of uops that are not from the microsequencer.", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_slots", + "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@) / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", @@ -172,7 +172,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_detect", "MetricThreshold": "tma_branch_detect > 0.05", @@ -182,7 +182,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", @@ -192,7 +192,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteer", "MetricThreshold": "tma_branch_resteer > 0.05", @@ -201,7 +201,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_cisc", "MetricThreshold": "tma_cisc > 0.05", @@ -220,7 +220,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_decode", "MetricThreshold": "tma_decode > 0.05", @@ -229,7 +229,7 @@ }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory disambiguation.", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.DISAMBIGUATION / MACHINE_CLEARS.SLOW)", + "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.DISAMBIGUATION@ / cpu_atom@MACHINE_CLEARS.SLOW@)", "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", "MetricName": "tma_disambiguation", "MetricThreshold": "tma_disambiguation > 0.02", @@ -239,7 +239,7 @@ { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", + "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1", @@ -248,7 +248,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", "MetricThreshold": "tma_fast_nuke > 0.05", @@ -257,7 +257,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", @@ -267,7 +267,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", @@ -277,7 +277,7 @@ }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists.", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", + "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.FP_ASSIST@ / cpu_atom@MACHINE_CLEARS.SLOW@)", "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", "MetricName": "tma_fp_assist", "MetricThreshold": "tma_fp_assist > 0.02", @@ -286,7 +286,7 @@ }, { "BriefDescription": "Counts the number of floating point divide operations per uop.", - "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", "MetricName": "tma_fpdiv_uops", "MetricThreshold": "tma_fpdiv_uops > 0.2", @@ -295,7 +295,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", @@ -305,7 +305,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05", @@ -313,246 +313,220 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", - "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_address_alias_blocks", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Ratio of all branches which mispredict", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": " ", - "MetricName": "tma_info_branch_mispredict_ratio", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Ratio between Mispredicted branches and unknown branches", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_branch_mispredict_to_unknown_branch_ratio", - "Unit": "cpu_atom" - }, - { "BriefDescription": "", - "MetricExpr": "CPU_CLK_UNHALTED.CORE", - "MetricGroup": " ", - "MetricName": "tma_info_clks", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@", + "MetricName": "tma_info_core_clks", "Unit": "cpu_atom" }, { "BriefDescription": "", - "MetricExpr": "CPU_CLK_UNHALTED.CORE_P", - "MetricGroup": " ", - "MetricName": "tma_info_clks_p", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@", + "MetricName": "tma_info_core_clks_p", "Unit": "cpu_atom" }, { "BriefDescription": "Cycles Per Instruction", - "MetricExpr": "tma_info_clks / INST_RETIRED.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_cpi", + "MetricExpr": "tma_info_core_clks / INST_RETIRED.ANY", + "MetricName": "tma_info_core_cpi", "Unit": "cpu_atom" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": " ", - "MetricName": "tma_info_cpu_utilization", + "BriefDescription": "Instructions Per Cycle", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricName": "tma_info_core_ipc", "Unit": "cpu_atom" }, { - "BriefDescription": "Cycle cost per DRAM hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", - "MetricGroup": " ", - "MetricName": "tma_info_cycles_per_demand_load_dram_hit", + "BriefDescription": "", + "MetricExpr": "5 * tma_info_core_clks", + "MetricName": "tma_info_core_slots", "Unit": "cpu_atom" }, { - "BriefDescription": "Cycle cost per L2 hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", - "MetricGroup": " ", - "MetricName": "tma_info_cycles_per_demand_load_l2_hit", + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", + "MetricName": "tma_info_core_upi", "Unit": "cpu_atom" }, { - "BriefDescription": "Cycle cost per LLC hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", - "MetricGroup": " ", - "MetricName": "tma_info_cycles_per_demand_load_l3_hit", + "BriefDescription": "Percent of instruction miss cost that hit in DRAM", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_DRAM_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@", + "MetricName": "tma_info_frontend_inst_miss_cost_dramhit_percent", "Unit": "cpu_atom" }, { - "BriefDescription": "Percentage of all uops which are FPDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_fpdiv_uop_ratio", + "BriefDescription": "Percent of instruction miss cost that hit in the L2", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@", + "MetricName": "tma_info_frontend_inst_miss_cost_l2hit_percent", "Unit": "cpu_atom" }, { - "BriefDescription": "Percentage of all uops which are IDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_idiv_uop_ratio", + "BriefDescription": "Percent of instruction miss cost that hit in the L3", + "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS.IFETCH_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.IFETCH@", + "MetricName": "tma_info_frontend_inst_miss_cost_l3hit_percent", "Unit": "cpu_atom" }, { - "BriefDescription": "Percent of instruction miss cost that hit in DRAM", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricGroup": " ", - "MetricName": "tma_info_inst_miss_cost_dramhit_percent", + "BriefDescription": "Ratio of all branches which mispredict", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", + "MetricName": "tma_info_inst_mix_branch_mispredict_ratio", "Unit": "cpu_atom" }, { - "BriefDescription": "Percent of instruction miss cost that hit in the L2", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricGroup": " ", - "MetricName": "tma_info_inst_miss_cost_l2hit_percent", + "BriefDescription": "Ratio between Mispredicted branches and unknown branches", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", + "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio", "Unit": "cpu_atom" }, { - "BriefDescription": "Percent of instruction miss cost that hit in the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricGroup": " ", - "MetricName": "tma_info_inst_miss_cost_l3hit_percent", + "BriefDescription": "Percentage of all uops which are FPDiv uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_fpdiv_uop_ratio", "Unit": "cpu_atom" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": " ", - "MetricName": "tma_info_ipbranch", + "BriefDescription": "Percentage of all uops which are IDiv uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_idiv_uop_ratio", "Unit": "cpu_atom" }, { - "BriefDescription": "Instructions Per Cycle", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": " ", - "MetricName": "tma_info_ipc", + "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricName": "tma_info_inst_mix_ipbranch", "Unit": "cpu_atom" }, { "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", - "MetricGroup": " ", - "MetricName": "tma_info_ipcall", + "MetricName": "tma_info_inst_mix_ipcall", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per Far Branch", - "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)", - "MetricGroup": " ", - "MetricName": "tma_info_ipfarbranch", + "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_INST_RETIRED.FAR_BRANCH@ / 2)", + "MetricName": "tma_info_inst_mix_ipfarbranch", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per Load", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": " ", - "MetricName": "tma_info_ipload", + "MetricName": "tma_info_inst_mix_ipload", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", - "MetricExpr": "INST_RETIRED.ANY / (BR_MISP_RETIRED.COND - BR_MISP_RETIRED.COND_TAKEN)", - "MetricName": "tma_info_ipmisp_cond_ntaken", + "MetricExpr": "INST_RETIRED.ANY / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)", + "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricName": "tma_info_ipmisp_cond_taken", + "MetricName": "tma_info_inst_mix_ipmisp_cond_taken", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", - "MetricName": "tma_info_ipmisp_indirect", + "MetricName": "tma_info_inst_mix_ipmisp_indirect", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired return Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN", - "MetricName": "tma_info_ipmisp_ret", + "MetricName": "tma_info_inst_mix_ipmisp_ret", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per retired Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": " ", - "MetricName": "tma_info_ipmispredict", + "MetricName": "tma_info_inst_mix_ipmispredict", "Unit": "cpu_atom" }, { "BriefDescription": "Instructions per Store", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": " ", - "MetricName": "tma_info_ipstore", + "MetricName": "tma_info_inst_mix_ipstore", "Unit": "cpu_atom" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", - "MetricGroup": " ", - "MetricName": "tma_info_kernel_utilization", + "BriefDescription": "Percentage of all uops which are ucode ops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_microcode_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of all uops which are x87 uops", + "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_x87_uop_ratio", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", + "MetricExpr": "100 * cpu_atom@LD_BLOCKS.4K_ALIAS@ / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_l1_bound_address_alias_blocks", "Unit": "cpu_atom" }, { "BriefDescription": "Percentage of total non-speculative loads that are splits", - "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_load_splits", + "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.SPLIT_LOADS@ / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_l1_bound_load_splits", "Unit": "cpu_atom" }, { - "BriefDescription": "load ops retired per 1000 instruction", - "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_memloadpki", + "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", + "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_l1_bound_store_fwd_blocks", "Unit": "cpu_atom" }, { - "BriefDescription": "Percentage of all uops which are ucode ops", - "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_microcode_uop_ratio", + "BriefDescription": "Cycle cost per DRAM hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit", "Unit": "cpu_atom" }, { - "BriefDescription": "", - "MetricExpr": "5 * tma_info_clks", - "MetricGroup": " ", - "MetricName": "tma_info_slots", + "BriefDescription": "Cycle cost per L2 hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit", "Unit": "cpu_atom" }, { - "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", - "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_store_fwd_blocks", + "BriefDescription": "Cycle cost per LLC hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit", "Unit": "cpu_atom" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": " ", - "MetricName": "tma_info_turbo_utilization", + "BriefDescription": "load ops retired per 1000 instruction", + "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / INST_RETIRED.ANY", + "MetricName": "tma_info_memory_memloadpki", "Unit": "cpu_atom" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_upi", + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_atom" }, { - "BriefDescription": "Percentage of all uops which are x87 uops", - "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_x87_uop_ratio", + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_kernel_utilization", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_core_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05", @@ -561,7 +535,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", - "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1", @@ -571,7 +545,7 @@ { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", + "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_L2_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.1", @@ -580,7 +554,7 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", + "MetricExpr": "cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / tma_info_core_clks - max((cpu_atom@MEM_BOUND_STALLS.LOAD@ - cpu_atom@LD_HEAD.L1_MISS_AT_RET@) / tma_info_core_clks, 0) * cpu_atom@MEM_BOUND_STALLS.LOAD_LLC_HIT@ / cpu_atom@MEM_BOUND_STALLS.LOAD@", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.1", @@ -589,7 +563,7 @@ }, { "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to load buffer full", - "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.LD_BUF / MEM_SCHEDULER_BLOCK.ALL", + "MetricExpr": "tma_mem_scheduler * cpu_atom@MEM_SCHEDULER_BLOCK.LD_BUF@ / MEM_SCHEDULER_BLOCK.ALL", "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", "MetricName": "tma_ld_buffer", "MetricThreshold": "tma_ld_buffer > 0.05", @@ -598,7 +572,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", @@ -608,7 +582,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", "MetricThreshold": "tma_mem_scheduler > 0.1", @@ -617,7 +591,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricExpr": "min(cpu_atom@TOPDOWN_BE_BOUND.ALL@ / tma_info_core_slots, cpu_atom@LD_HEAD.ANY_AT_RET@ / tma_info_core_clks + tma_store_bound)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", @@ -627,7 +601,7 @@ }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering.", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", + "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_atom@MACHINE_CLEARS.SLOW@)", "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", "MetricName": "tma_memory_ordering", "MetricThreshold": "tma_memory_ordering > 0.02", @@ -636,7 +610,7 @@ }, { "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", - "MetricExpr": "tma_microcode_sequencer", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", @@ -647,7 +621,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", "MetricThreshold": "tma_non_mem_scheduler > 0.1", @@ -656,7 +630,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", "MetricThreshold": "tma_nuke > 0.05", @@ -665,7 +639,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", - "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_other_fb", "MetricThreshold": "tma_other_fb > 0.05", @@ -674,7 +648,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", - "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_other_l1", "MetricThreshold": "tma_other_l1 > 0.05", @@ -692,7 +666,7 @@ }, { "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_slots", + "MetricExpr": "(cpu_atom@TOPDOWN_RETIRING.ALL@ - cpu_atom@UOPS_RETIRED.MS@ - cpu_atom@UOPS_RETIRED.FPDIV@) / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", "MetricName": "tma_other_ret", "MetricThreshold": "tma_other_ret > 0.3", @@ -701,7 +675,7 @@ }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to page faults.", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.PAGE_FAULT / MACHINE_CLEARS.SLOW)", + "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.PAGE_FAULT@ / cpu_atom@MACHINE_CLEARS.SLOW@)", "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", "MetricName": "tma_page_fault", "MetricThreshold": "tma_page_fault > 0.02", @@ -710,7 +684,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", - "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_predecode", "MetricThreshold": "tma_predecode > 0.05", @@ -719,7 +693,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", "MetricThreshold": "tma_register > 0.1", @@ -728,7 +702,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", "MetricThreshold": "tma_reorder_buffer > 0.1", @@ -748,7 +722,7 @@ }, { "BriefDescription": "Counts the numer of issue slots that result in retirement slots.", - "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_slots", + "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", @@ -758,7 +732,7 @@ }, { "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to RSV full relative", - "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.RSV / MEM_SCHEDULER_BLOCK.ALL", + "MetricExpr": "tma_mem_scheduler * cpu_atom@MEM_SCHEDULER_BLOCK.RSV@ / MEM_SCHEDULER_BLOCK.ALL", "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", "MetricName": "tma_rsv", "MetricThreshold": "tma_rsv > 0.05", @@ -767,7 +741,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", "MetricThreshold": "tma_serialization > 0.1", @@ -776,7 +750,7 @@ }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to SMC.", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.SMC / MACHINE_CLEARS.SLOW)", + "MetricExpr": "tma_nuke * (cpu_atom@MACHINE_CLEARS.SMC@ / cpu_atom@MACHINE_CLEARS.SLOW@)", "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", "MetricName": "tma_smc", "MetricThreshold": "tma_smc > 0.02", @@ -794,7 +768,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", - "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_stlb_hit", "MetricThreshold": "tma_stlb_hit > 0.05", @@ -803,7 +777,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", - "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_stlb_miss", "MetricThreshold": "tma_stlb_miss > 0.05", @@ -812,7 +786,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", - "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", + "MetricExpr": "tma_mem_scheduler * (cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@MEM_SCHEDULER_BLOCK.ALL@)", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.1", @@ -821,7 +795,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", - "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.05", @@ -830,7 +804,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_clks)", + "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -839,7 +813,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * [email protected]\\,umask\\=0x1B@ / tma_info_slots", + "MetricExpr": "100 * [email protected]\\,umask\\=0x1B@ / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -849,7 +823,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", - "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_slots", + "MetricExpr": "63 * [email protected]_AVX_MIX@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", "MetricThreshold": "tma_avx_assists > 0.1", @@ -858,7 +832,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -880,18 +854,18 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -911,7 +885,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -922,7 +896,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(25 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 24 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(25 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * ([email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ / ([email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ + [email protected]_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -944,7 +918,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "24 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "24 * tma_info_system_average_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - [email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ / ([email protected]_DATA_RD.L3_HIT.SNOOP_HITM@ + [email protected]_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -954,17 +928,17 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -975,7 +949,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks", + "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -985,47 +959,47 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "([email protected]_CYCLES_ANY@ - [email protected]_CYCLES_OK@) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "28 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "28 * tma_info_system_average_frequency * [email protected]_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1035,11 +1009,11 @@ }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -1048,15 +1022,15 @@ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -1077,6 +1051,7 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -1087,7 +1062,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", - "MetricExpr": "30 * ASSISTS.FP / tma_info_slots", + "MetricExpr": "30 * [email protected]@ / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", @@ -1097,7 +1072,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -1107,7 +1082,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -1117,7 +1092,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -1127,7 +1102,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -1137,7 +1112,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -1148,7 +1123,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", @@ -1158,7 +1133,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -1169,7 +1144,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / tma_info_clks", + "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1178,247 +1153,300 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch", + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200", "Unit": "cpu_core" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers", + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code", + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL\\,umask\\=0x80@ / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret", + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500", "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200", "Unit": "cpu_core" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki", + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt", + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk", + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", "Unit": "cpu_core" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5", + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead", "Unit": "cpu_core" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks", + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((cpu_core@BR_INST_RETIRED.COND@ + 3 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + (cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN@ - 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", - "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc", + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi", + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization", + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", "Unit": "cpu_core" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp", + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full", + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", - "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 6 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@BR_INST_RETIRED.NEAR_RETURN@) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_nt", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", - "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost", + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_branches_cond_tk", "Unit": "cpu_core" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute", + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(cpu_core@BR_INST_RETIRED.NEAR_TAKEN@ - cpu_core@BR_INST_RETIRED.COND_TAKEN@ - 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump", "Unit": "cpu_core" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches", "Unit": "cpu_core" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki", + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.DISTRIBUTED@", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_core_clks", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc", + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_core_coreipc", "Unit": "cpu_core" }, { "BriefDescription": "Floating Point Operations Per Cycle", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / tma_info_core_core_clks", "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc", + "MetricName": "tma_info_core_flopc", "Unit": "cpu_core" }, { "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_clks)", + "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)", "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", + "MetricName": "tma_info_core_fp_arith_utilization", "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", "Unit": "cpu_core" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine.", + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_frontend_dsb_switch_cost", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_frontend_fetch_upc", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L1 instruction cache misses", "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency", + "MetricName": "tma_info_frontend_icache_miss_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp", + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20", + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * cpu_core@FRONTEND_RETIRED.L2_MISS@ / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code", + "Unit": "cpu_core" + }, + { + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.CODE_RD_MISS@ / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / cpu_core@UOPS_ISSUED.ANY@", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_frontend_lsd_coverage", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch", "Unit": "cpu_core" }, { "BriefDescription": "Total number of retired Instructions", - "MetricExpr": "INST_RETIRED.ANY", + "MetricExpr": "cpu_core@INST_RETIRED.ANY@", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST", "Unit": "cpu_core" }, @@ -1426,26 +1454,26 @@ "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW.", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, @@ -1453,8 +1481,8 @@ "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, @@ -1462,490 +1490,445 @@ "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per a microcode Assist invocation", - "MetricExpr": "INST_RETIRED.ANY / [email protected]\\,umask\\=0x1B@", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_ipassist", - "MetricThreshold": "tma_info_ipassist < 100e3", - "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", - "Unit": "cpu_core" - }, - { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc", + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6", + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10", + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_ntaken", - "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_taken", - "MetricThreshold": "tma_info_ipmisp_cond_taken < 200", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL\\,umask\\=0x80@ / BR_MISP_RETIRED.INDIRECT", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_ret", - "MetricThreshold": "tma_info_ipmisp_ret < 500", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200", + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8", + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8", "Unit": "cpu_core" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100", + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100", "Unit": "cpu_core" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 13", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch", + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump", + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * [email protected]@ / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi", + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@L2_LINES_IN.ALL@ / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05", + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@OFFCORE_REQUESTS.ALL_REQUESTS@ / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * cpu_core@LONGEST_LAT_CACHE.MISS@ / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw", + "MetricName": "tma_info_memory_core_l3_cache_fill_bw", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t", + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki", "Unit": "cpu_core" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki", + "MetricName": "tma_info_memory_l1mpki", "Unit": "cpu_core" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.ALL_DEMAND_DATA_RD@ / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t", + "MetricName": "tma_info_memory_l1mpki_load", "Unit": "cpu_core" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricExpr": "1e3 * (cpu_core@L2_RQSTS.REFERENCES@ - cpu_core@L2_RQSTS.MISS@) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all", + "MetricName": "tma_info_memory_l2hpki_all", "Unit": "cpu_core" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_HIT@ / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load", + "MetricName": "tma_info_memory_l2hpki_load", "Unit": "cpu_core" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L2_MISS@ / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki", + "MetricName": "tma_info_memory_l2mpki", "Unit": "cpu_core" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.MISS@ / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all", - "Unit": "cpu_core" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code", - "Unit": "cpu_core" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all", + "MetricName": "tma_info_memory_l2mpki_all", "Unit": "cpu_core" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@L2_RQSTS.DEMAND_DATA_RD_MISS@ / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load", + "MetricName": "tma_info_memory_l2mpki_load", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * cpu_core@MEM_LOAD_RETIRED.L3_MISS@ / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", "Unit": "cpu_core" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki", + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency", + "MetricName": "tma_info_memory_oro_load_l2_miss_latency", "Unit": "cpu_core" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp", + "MetricName": "tma_info_memory_oro_load_l2_mlp", "Unit": "cpu_core" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l3_miss_latency", + "MetricName": "tma_info_memory_oro_load_l3_miss_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency", + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t", + "Unit": "cpu_core" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@ITLB_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki", "Unit": "cpu_core" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricExpr": "1e3 * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki", + "MetricName": "tma_info_memory_tlb_load_stlb_mpki", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", - "MetricGroup": "Fed;LSD", - "MetricName": "tma_info_lsd_coverage", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(cpu_core@ITLB_MISSES.WALK_PENDING@ + cpu_core@DTLB_LOAD_MISSES.WALK_PENDING@ + cpu_core@DTLB_STORE_MISSES.WALK_PENDING@) / (4 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", - "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED@ / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki", "Unit": "cpu_core" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", - "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)", + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute", "Unit": "cpu_core" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency", + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "INST_RETIRED.ANY / [email protected]\\,umask\\=0x1B@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_pipeline_ipassist", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full", + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_strings_cycles", + "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency", + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency", "Unit": "cpu_core" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization", "Unit": "cpu_core" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_other_branches", + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.SCALAR_DOUBLE@ + 2 * cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + 4 * (cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@) + 8 * cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine.", "Unit": "cpu_core" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5", + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire", + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@INST_RETIRED.ANY_P@k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi", "Unit": "cpu_core" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots", + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_slots_utilization", + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricExpr": "(1 - cpu_core@CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE@ / cpu_core@CPU_CLK_UNHALTED.REF_DISTRIBUTED@ if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization", + "MetricName": "tma_info_system_smt_2t_utilization", "Unit": "cpu_core" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "UNC_CLOCK.SOCKET", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks", + "MetricName": "tma_info_system_socket_clks", "Unit": "cpu_core" }, { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization", "Unit": "cpu_core" }, { - "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_strings_cycles", - "MetricThreshold": "tma_info_strings_cycles > 0.1", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks", "Unit": "cpu_core" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization", + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi", + "Unit": "cpu_core" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "[email protected]@", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / ([email protected]@ / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization", "Unit": "cpu_core" }, { "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05", "Unit": "cpu_core" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 9", + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 9", "Unit": "cpu_core" }, { @@ -1960,7 +1943,7 @@ }, { "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", - "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -1970,7 +1953,7 @@ }, { "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", - "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -1980,7 +1963,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_TAG.STALLS / tma_info_clks", + "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1990,7 +1973,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -2001,7 +1984,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -2011,7 +1994,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -2021,21 +2004,21 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "9 * tma_info_system_average_frequency * cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "DECODE.LCP / tma_info_clks", + "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%", "Unit": "cpu_core" }, @@ -2052,7 +2035,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_clks)", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -2071,7 +2054,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -2081,7 +2064,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2091,10 +2074,10 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "([email protected]_ACTIVE@ - [email protected]_OK@) / tma_info_core_core_clks / 2", "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", - "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,27 +2095,27 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -2143,7 +2126,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_clks", + "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -2152,7 +2135,8 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_slots)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", @@ -2161,7 +2145,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -2171,27 +2155,27 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "([email protected]_CYCLES_ANY@ - [email protected]_CYCLES_OK@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_clks", + "MetricExpr": "160 * [email protected]_AVX_MIX@ / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", @@ -2201,7 +2185,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_slots / UOPS_ISSUED.ANY) / tma_info_clks", + "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_thread_slots / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -2211,7 +2195,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ - cpu_core@INST_RETIRED.MACRO_FUSED@) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", @@ -2221,7 +2205,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_nop_instructions", "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", @@ -2231,6 +2215,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -2241,7 +2226,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", - "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_slots", + "MetricExpr": "99 * [email protected]_FAULT@ / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", @@ -2251,7 +2236,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -2261,7 +2246,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -2271,7 +2256,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -2281,7 +2266,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_clks)", + "MetricExpr": "((cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if [email protected]_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -2291,7 +2276,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_clks", + "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2301,7 +2286,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2311,7 +2296,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2321,7 +2306,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -2331,7 +2316,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -2342,7 +2327,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -2352,7 +2337,7 @@ }, { "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", - "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_slots)", + "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", "MetricName": "tma_shuffles", "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -2361,7 +2346,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_clks", + "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -2371,7 +2356,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu_core@LD_BLOCKS.NO_SR@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2381,7 +2366,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2391,17 +2376,17 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_clks", + "MetricExpr": "([email protected]_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%", "Unit": "cpu_core" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -2411,7 +2396,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2421,7 +2406,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2431,7 +2416,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_4_9@ + cpu_core@UOPS_DISPATCHED.PORT_7_8@) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -2450,7 +2435,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -2459,7 +2444,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricExpr": "9 * [email protected]_WR.ANY_RESPONSE@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -2469,7 +2454,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_clks", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -2479,7 +2464,7 @@ }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / UOPS_EXECUTED.THREAD", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json index 51770416bcc2..b3d7f8fb50df 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json @@ -1018,6 +1018,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0x2c", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10", + "Unit": "cpu_core" + }, + { "BriefDescription": "Number of PREFETCHNTA instructions executed.", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index 55827b276e6e..73d92d5c9f9d 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -93,19 +93,21 @@ "Unit": "cpu_core" }, { - "BriefDescription": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.", "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_core" }, { - "BriefDescription": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.", "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json new file mode 100644 index 000000000000..516eb0f93f02 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/alderlake/metricgroups.json @@ -0,0 +1,122 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_assists_group": "Metrics contributing to tma_assists category", + "tma_backend_bound_aux_group": "Metrics contributing to tma_backend_bound_aux category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_base_group": "Metrics contributing to tma_base category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_int_operations_group": "Metrics contributing to tma_int_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_mem_scheduler_group": "Metrics contributing to tma_mem_scheduler category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_nuke_group": "Metrics contributing to tma_nuke category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_resource_bound_group": "Metrics contributing to tma_resource_bound category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 0402adbf7d92..ed9ff25a03cf 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -86,7 +86,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", - "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_alloc_restriction", "MetricThreshold": "tma_alloc_restriction > 0.1", @@ -94,7 +94,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", @@ -114,7 +114,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", - "MetricExpr": "(tma_info_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_slots", + "MetricExpr": "(tma_info_core_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -124,7 +124,7 @@ }, { "BriefDescription": "Counts the number of uops that are not from the microsequencer.", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_slots", + "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", @@ -133,7 +133,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_detect", "MetricThreshold": "tma_branch_detect > 0.05", @@ -142,7 +142,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", @@ -151,7 +151,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteer", "MetricThreshold": "tma_branch_resteer > 0.05", @@ -159,7 +159,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_cisc", "MetricThreshold": "tma_cisc > 0.05", @@ -176,7 +176,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_decode", "MetricThreshold": "tma_decode > 0.05", @@ -193,7 +193,7 @@ { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1", @@ -201,7 +201,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_fast_nuke", "MetricThreshold": "tma_fast_nuke > 0.05", @@ -209,7 +209,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", @@ -218,7 +218,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", @@ -235,7 +235,7 @@ }, { "BriefDescription": "Counts the number of floating point divide operations per uop.", - "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", "MetricName": "tma_fpdiv_uops", "MetricThreshold": "tma_fpdiv_uops > 0.2", @@ -243,7 +243,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", @@ -252,218 +252,192 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", - "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_address_alias_blocks" - }, - { - "BriefDescription": "Ratio of all branches which mispredict", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": " ", - "MetricName": "tma_info_branch_mispredict_ratio" - }, - { - "BriefDescription": "Ratio between Mispredicted branches and unknown branches", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_branch_mispredict_to_unknown_branch_ratio" - }, - { "BriefDescription": "", "MetricExpr": "CPU_CLK_UNHALTED.CORE", - "MetricGroup": " ", - "MetricName": "tma_info_clks" + "MetricName": "tma_info_core_clks" }, { "BriefDescription": "", "MetricExpr": "CPU_CLK_UNHALTED.CORE_P", - "MetricGroup": " ", - "MetricName": "tma_info_clks_p" + "MetricName": "tma_info_core_clks_p" }, { "BriefDescription": "Cycles Per Instruction", - "MetricExpr": "tma_info_clks / INST_RETIRED.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": " ", - "MetricName": "tma_info_cpu_utilization" - }, - { - "BriefDescription": "Cycle cost per DRAM hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", - "MetricGroup": " ", - "MetricName": "tma_info_cycles_per_demand_load_dram_hit" - }, - { - "BriefDescription": "Cycle cost per L2 hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", - "MetricGroup": " ", - "MetricName": "tma_info_cycles_per_demand_load_l2_hit" + "MetricExpr": "tma_info_core_clks / INST_RETIRED.ANY", + "MetricName": "tma_info_core_cpi" }, { - "BriefDescription": "Cycle cost per LLC hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", - "MetricGroup": " ", - "MetricName": "tma_info_cycles_per_demand_load_l3_hit" + "BriefDescription": "Instructions Per Cycle", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricName": "tma_info_core_ipc" }, { - "BriefDescription": "Percentage of all uops which are FPDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_fpdiv_uop_ratio" + "BriefDescription": "", + "MetricExpr": "5 * tma_info_core_clks", + "MetricName": "tma_info_core_slots" }, { - "BriefDescription": "Percentage of all uops which are IDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_idiv_uop_ratio" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", + "MetricName": "tma_info_core_upi" }, { "BriefDescription": "Percent of instruction miss cost that hit in DRAM", "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricGroup": " ", - "MetricName": "tma_info_inst_miss_cost_dramhit_percent" + "MetricName": "tma_info_frontend_inst_miss_cost_dramhit_percent" }, { "BriefDescription": "Percent of instruction miss cost that hit in the L2", "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricGroup": " ", - "MetricName": "tma_info_inst_miss_cost_l2hit_percent" + "MetricName": "tma_info_frontend_inst_miss_cost_l2hit_percent" }, { "BriefDescription": "Percent of instruction miss cost that hit in the L3", "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricGroup": " ", - "MetricName": "tma_info_inst_miss_cost_l3hit_percent" + "MetricName": "tma_info_frontend_inst_miss_cost_l3hit_percent" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": " ", - "MetricName": "tma_info_ipbranch" + "BriefDescription": "Ratio of all branches which mispredict", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", + "MetricName": "tma_info_inst_mix_branch_mispredict_ratio" }, { - "BriefDescription": "Instructions Per Cycle", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": " ", - "MetricName": "tma_info_ipc" + "BriefDescription": "Ratio between Mispredicted branches and unknown branches", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", + "MetricName": "tma_info_inst_mix_branch_mispredict_to_unknown_branch_ratio" + }, + { + "BriefDescription": "Percentage of all uops which are FPDiv uops", + "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_fpdiv_uop_ratio" + }, + { + "BriefDescription": "Percentage of all uops which are IDiv uops", + "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_idiv_uop_ratio" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricName": "tma_info_inst_mix_ipbranch" }, { "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", - "MetricGroup": " ", - "MetricName": "tma_info_ipcall" + "MetricName": "tma_info_inst_mix_ipcall" }, { "BriefDescription": "Instructions per Far Branch", "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)", - "MetricGroup": " ", - "MetricName": "tma_info_ipfarbranch" + "MetricName": "tma_info_inst_mix_ipfarbranch" }, { "BriefDescription": "Instructions per Load", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": " ", - "MetricName": "tma_info_ipload" + "MetricName": "tma_info_inst_mix_ipload" }, { "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", "MetricExpr": "INST_RETIRED.ANY / (BR_MISP_RETIRED.COND - BR_MISP_RETIRED.COND_TAKEN)", - "MetricName": "tma_info_ipmisp_cond_ntaken" + "MetricName": "tma_info_inst_mix_ipmisp_cond_ntaken" }, { "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricName": "tma_info_ipmisp_cond_taken" + "MetricName": "tma_info_inst_mix_ipmisp_cond_taken" }, { "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", - "MetricName": "tma_info_ipmisp_indirect" + "MetricName": "tma_info_inst_mix_ipmisp_indirect" }, { "BriefDescription": "Instructions per retired return Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN", - "MetricName": "tma_info_ipmisp_ret" + "MetricName": "tma_info_inst_mix_ipmisp_ret" }, { "BriefDescription": "Instructions per retired Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": " ", - "MetricName": "tma_info_ipmispredict" + "MetricName": "tma_info_inst_mix_ipmispredict" }, { "BriefDescription": "Instructions per Store", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": " ", - "MetricName": "tma_info_ipstore" + "MetricName": "tma_info_inst_mix_ipstore" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", - "MetricGroup": " ", - "MetricName": "tma_info_kernel_utilization" + "BriefDescription": "Percentage of all uops which are ucode ops", + "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_microcode_uop_ratio" + }, + { + "BriefDescription": "Percentage of all uops which are x87 uops", + "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", + "MetricName": "tma_info_inst_mix_x87_uop_ratio" + }, + { + "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", + "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_l1_bound_address_alias_blocks" }, { "BriefDescription": "Percentage of total non-speculative loads that are splits", "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_load_splits" + "MetricName": "tma_info_l1_bound_load_splits" }, { - "BriefDescription": "load ops retired per 1000 instruction", - "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_memloadpki" + "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", + "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_l1_bound_store_fwd_blocks" }, { - "BriefDescription": "Percentage of all uops which are ucode ops", - "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_microcode_uop_ratio" + "BriefDescription": "Cycle cost per DRAM hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "MetricName": "tma_info_memory_cycles_per_demand_load_dram_hit" }, { - "BriefDescription": "", - "MetricExpr": "5 * tma_info_clks", - "MetricGroup": " ", - "MetricName": "tma_info_slots" + "BriefDescription": "Cycle cost per L2 hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricName": "tma_info_memory_cycles_per_demand_load_l2_hit" }, { - "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", - "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "tma_info_store_fwd_blocks" + "BriefDescription": "Cycle cost per LLC hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricName": "tma_info_memory_cycles_per_demand_load_l3_hit" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": " ", - "MetricName": "tma_info_turbo_utilization" + "BriefDescription": "load ops retired per 1000 instruction", + "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "tma_info_memory_memloadpki" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", - "MetricGroup": " ", - "MetricName": "tma_info_upi" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricName": "tma_info_system_cpu_utilization" }, { - "BriefDescription": "Percentage of all uops which are x87 uops", - "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", - "MetricGroup": " ", - "MetricName": "tma_info_x87_uop_ratio" + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", + "MetricGroup": "Summary", + "MetricName": "tma_info_system_kernel_utilization" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_core_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization" }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05", @@ -471,7 +445,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", - "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1", @@ -480,7 +454,7 @@ { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.1", @@ -488,7 +462,7 @@ }, { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_core_clks - max((MEM_BOUND_STALLS.LOAD - LD_HEAD.L1_MISS_AT_RET) / tma_info_core_clks, 0) * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.1", @@ -504,7 +478,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", @@ -513,7 +487,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_mem_scheduler", "MetricThreshold": "tma_mem_scheduler > 0.1", @@ -521,7 +495,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_core_clks + tma_store_bound)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", @@ -538,7 +512,7 @@ }, { "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", - "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_core_slots", "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", @@ -548,7 +522,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_non_mem_scheduler", "MetricThreshold": "tma_non_mem_scheduler > 0.1", @@ -556,7 +530,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_slots", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", "MetricName": "tma_nuke", "MetricThreshold": "tma_nuke > 0.05", @@ -564,7 +538,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", - "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_other_fb", "MetricThreshold": "tma_other_fb > 0.05", @@ -572,7 +546,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", - "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_other_l1", "MetricThreshold": "tma_other_l1 > 0.05", @@ -588,7 +562,7 @@ }, { "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_slots", + "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", "MetricName": "tma_other_ret", "MetricThreshold": "tma_other_ret > 0.3", @@ -604,7 +578,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", - "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots", + "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_predecode", "MetricThreshold": "tma_predecode > 0.05", @@ -612,7 +586,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_register", "MetricThreshold": "tma_register > 0.1", @@ -620,7 +594,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_reorder_buffer", "MetricThreshold": "tma_reorder_buffer > 0.1", @@ -638,7 +612,7 @@ }, { "BriefDescription": "Counts the numer of issue slots that result in retirement slots.", - "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_slots", + "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots", "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", @@ -655,7 +629,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_slots", + "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_core_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", "MetricName": "tma_serialization", "MetricThreshold": "tma_serialization > 0.1", @@ -679,7 +653,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", - "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_stlb_hit", "MetricThreshold": "tma_stlb_hit > 0.05", @@ -687,7 +661,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", - "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_stlb_miss", "MetricThreshold": "tma_stlb_miss > 0.05", @@ -703,7 +677,7 @@ }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", - "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks", + "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.05", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/metricgroups.json b/tools/perf/pmu-events/arch/x86/alderlaken/metricgroups.json new file mode 100644 index 000000000000..7b2049cd2694 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/alderlaken/metricgroups.json @@ -0,0 +1,26 @@ +{ + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_backend_bound_aux_group": "Metrics contributing to tma_backend_bound_aux category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_base_group": "Metrics contributing to tma_base category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category", + "tma_mem_scheduler_group": "Metrics contributing to tma_mem_scheduler category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_nuke_group": "Metrics contributing to tma_nuke category", + "tma_resource_bound_group": "Metrics contributing to tma_resource_bound category", + "tma_retiring_group": "Metrics contributing to tma_retiring category" +} diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index f9e2316601e1..55a10b0bf36f 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -71,7 +71,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -81,7 +81,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -89,7 +89,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -109,7 +109,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -125,12 +125,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -159,7 +159,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -180,7 +180,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -189,7 +189,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -199,7 +199,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -208,25 +208,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -235,7 +235,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -244,7 +244,7 @@ }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -254,11 +254,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -266,14 +266,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -328,7 +328,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -348,435 +348,435 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" - }, - { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." - }, - { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of parallel requests to external memory", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_parallel_requests", - "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_clks", + "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "UNC_CLOCK.SOCKET", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -785,7 +785,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -794,7 +794,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -804,7 +804,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -814,7 +814,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -823,11 +823,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -843,7 +843,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -853,7 +853,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -873,16 +873,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -892,7 +892,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -902,7 +902,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -915,21 +915,21 @@ "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -938,7 +938,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -947,7 +947,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -956,7 +956,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -965,7 +965,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -983,7 +983,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -992,7 +992,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1001,7 +1001,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -1011,7 +1011,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1020,7 +1020,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1029,7 +1029,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1038,7 +1038,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1047,7 +1047,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1055,7 +1055,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1066,7 +1066,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1075,7 +1075,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1084,16 +1084,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1102,7 +1102,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1112,7 +1112,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1121,7 +1121,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1138,7 +1138,7 @@ }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json index e4826dc7f797..986869252e71 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json @@ -32,6 +32,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", @@ -77,6 +85,13 @@ "UMask": "0x2a" }, { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "2000003", + "UMask": "0xfc" + }, + { "BriefDescription": "Cycles with any input/output SSE or FP assist", "CounterMask": "1", "EventCode": "0xCA", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwell/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index e9c46d336a8e..8fc62b8f667d 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -65,7 +65,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -75,7 +75,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -83,7 +83,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -103,7 +103,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -119,12 +119,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -153,7 +153,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -174,7 +174,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -183,7 +183,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -193,7 +193,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -202,25 +202,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -229,7 +229,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -239,11 +239,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -251,14 +251,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -313,7 +313,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -333,7 +333,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -341,409 +341,409 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" - }, - { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." - }, - { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_clks", + "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -752,7 +752,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -761,7 +761,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -771,7 +771,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -781,7 +781,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -790,11 +790,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -810,7 +810,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -820,7 +820,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -840,16 +840,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -859,7 +859,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -869,7 +869,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -882,21 +882,21 @@ "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -905,7 +905,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -914,7 +914,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -923,7 +923,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -931,7 +931,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -948,7 +948,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -957,7 +957,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -966,7 +966,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -975,7 +975,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -984,7 +984,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -993,7 +993,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1002,7 +1002,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1011,7 +1011,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1020,7 +1020,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1031,7 +1031,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1040,7 +1040,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1049,16 +1049,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1067,7 +1067,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1077,7 +1077,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1086,7 +1086,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1104,7 +1104,7 @@ }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json index e4826dc7f797..986869252e71 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json @@ -32,6 +32,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", @@ -77,6 +85,13 @@ "UMask": "0x2a" }, { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "2000003", + "UMask": "0xfc" + }, + { "BriefDescription": "Cycles with any input/output SSE or FP assist", "CounterMask": "1", "EventCode": "0xCA", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 437b9867acb9..b319e4edc238 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -50,11 +50,207 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ + cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x180\\,filter_tid\\=0x3e@) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x181@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x191@) / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x192@) / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from loop stream detector(LSD) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_loop_stream_detector", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Intel(R) Quick Path Interconnect (QPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_Q_TxL_FLITS_G0.DATA * 8 / 1e6 / duration_time", + "MetricName": "qpi_data_transmit_bw", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -70,8 +266,14 @@ "ScaleUnit": "1SMI#" }, { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_UOPS_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -81,7 +283,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -89,7 +291,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -109,7 +311,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -125,12 +327,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -159,7 +361,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -180,7 +382,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -189,7 +391,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -199,7 +401,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -208,25 +410,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -235,7 +437,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -244,7 +446,7 @@ }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_clks", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -254,11 +456,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -266,14 +468,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -328,7 +530,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -348,436 +550,436 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" - }, - { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." - }, - { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", - "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", - "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / (2 * tma_info_core_clks)", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / (2 * tma_info_core_core_clks)", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cbox_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -786,7 +988,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -795,7 +997,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -805,7 +1007,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -815,7 +1017,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -824,11 +1026,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -844,7 +1046,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -854,7 +1056,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -864,7 +1066,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -884,16 +1086,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -903,7 +1105,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -913,7 +1115,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -926,21 +1128,21 @@ "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -949,7 +1151,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -958,7 +1160,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -967,7 +1169,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -976,7 +1178,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -994,7 +1196,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1003,7 +1205,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1012,7 +1214,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -1022,7 +1224,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1031,7 +1233,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1040,7 +1242,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1049,7 +1251,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1058,7 +1260,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1067,7 +1269,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1077,7 +1279,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1086,7 +1288,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1097,7 +1299,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1106,7 +1308,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1115,16 +1317,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1133,7 +1335,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1143,7 +1345,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1152,7 +1354,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1169,11 +1371,17 @@ }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json index e4826dc7f797..986869252e71 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json @@ -32,6 +32,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", @@ -77,6 +85,13 @@ "UMask": "0x2a" }, { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "2000003", + "UMask": "0xfc" + }, + { "BriefDescription": "Cycles with any input/output SSE or FP assist", "CounterMask": "1", "EventCode": "0xCA", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json b/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 875c766222e3..0e2e446ced7a 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -50,11 +50,238 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "dtlb_2mb_large_page_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x12CC0233@ / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS\\,config1\\=0x40433@ / cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40433@) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS\\,config1\\=0x40432@ / cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS\\,config1\\=0x40431@ / cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x12D40433@ / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -70,8 +297,14 @@ "ScaleUnit": "1SMI#" }, { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -80,7 +313,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -88,7 +321,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_slots", + "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -97,7 +330,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -107,7 +340,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -123,12 +356,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -146,7 +379,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -156,7 +389,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -177,7 +410,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -186,16 +419,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -205,7 +438,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound)", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -214,45 +447,45 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(110 * tma_info_average_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_average_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_clks", + "MetricExpr": "(110 * tma_info_system_average_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_average_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -262,11 +495,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -274,14 +507,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -356,7 +589,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -375,7 +608,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_slots", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -385,7 +618,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -393,705 +626,711 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_core_ipmispredict", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts;TopdownL1;tma_L1_group", + "MetricName": "tma_info_core_ipmispredict", + "MetricgroupNoGroup": "TopdownL1" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_read_bw" - }, - { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_write_bw" - }, - { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx512", - "MetricThreshold": "tma_info_iparith_avx512 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_silent_pki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" - }, - { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_nonsilent_pki" - }, - { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_silent_pki" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" - }, - { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_read_bw" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_write_bw" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_dram_read_latency", + "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average number of parallel data read requests to external memory", "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", + "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", "MetricExpr": "(1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@ if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_pmm_read_latency", + "MetricName": "tma_info_system_mem_pmm_read_latency", "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", + "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" - }, - { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" - }, - { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" - }, - { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "tma_info_pmm_read_bw" + "MetricName": "tma_info_system_pmm_read_bw" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "tma_info_pmm_write_bw" + "MetricName": "tma_info_system_pmm_write_bw" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks)", + "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", - "MetricName": "tma_info_power_license0_utilization", + "MetricName": "tma_info_system_power_license0_utilization", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks)", + "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", - "MetricName": "tma_info_power_license1_utilization", - "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "MetricName": "tma_info_system_power_license1_utilization", + "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks)", + "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", - "MetricName": "tma_info_power_license2_utilization", - "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "MetricName": "tma_info_system_power_license2_utilization", + "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cha_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1100,7 +1339,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1110,7 +1349,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1119,7 +1358,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1128,20 +1367,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "17 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1156,7 +1395,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1174,7 +1413,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1182,7 +1421,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "59.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "59.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1191,7 +1430,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1211,20 +1450,20 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1248,7 +1487,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1257,19 +1496,19 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, @@ -1284,7 +1523,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1321,7 +1560,7 @@ { "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_pmm_bound", "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1330,7 +1569,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1339,7 +1578,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1348,7 +1587,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -1357,7 +1596,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -1375,7 +1614,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1384,7 +1623,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1393,7 +1632,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -1402,7 +1641,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1411,7 +1650,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_clks", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1420,7 +1659,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_clks", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1429,7 +1668,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_clks", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1438,7 +1677,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_clks", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1447,7 +1686,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(89.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1456,7 +1695,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "127 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "127 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1465,7 +1704,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1475,7 +1714,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1484,7 +1723,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_clks", + "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -1494,7 +1733,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1503,7 +1742,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1512,16 +1751,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1530,7 +1769,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1540,7 +1779,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1549,7 +1788,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1565,7 +1804,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1573,7 +1812,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "9 * BACLEARS.ANY / tma_info_clks", + "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -1616,5 +1855,17 @@ "MetricGroup": "transaction", "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_transmit_bw", + "ScaleUnit": "1MB/s" } ] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/floating-point.json b/tools/perf/pmu-events/arch/x86/cascadelakex/floating-point.json index 1f46e6b33856..bb4d5101f962 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/floating-point.json @@ -32,6 +32,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x18" + }, + { "BriefDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", @@ -48,6 +56,22 @@ "UMask": "0x80" }, { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Counts once for most SIMD scalar computational floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Counts once for most SIMD scalar computational single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SIMD scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { "BriefDescription": "Counts once for most SIMD scalar computational double precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", @@ -64,6 +88,13 @@ "UMask": "0x2" }, { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "2000003", + "UMask": "0xfc" + }, + { "BriefDescription": "Intel AVX-512 computational 512-bit packed BFloat16 instructions retired.", "EventCode": "0xCF", "EventName": "FP_ARITH_INST_RETIRED2.128BIT_PACKED_BF16", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json new file mode 100644 index 000000000000..bc6a9a4d27a9 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/metricgroups.json @@ -0,0 +1,114 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json index 0f06e314fe36..31a1663d57f8 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json @@ -26,12 +26,21 @@ "UMask": "0x4" }, { - "BriefDescription": "Conditional branch instructions retired.", + "BriefDescription": "Conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.CONDITIONAL]", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "This event counts conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.CONDITIONAL]", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.COND]", "Errata": "SKL091", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.CONDITIONAL", "PEBS": "1", - "PublicDescription": "This event counts conditional branch instructions retired.", + "PublicDescription": "This event counts conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.COND]", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -414,6 +423,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "EventCode": "0x0D", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json index 0ab90e3bf76b..c6be60584522 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json @@ -72,6 +72,7 @@ "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2, LLC, DRAM or MMIO (Non-DRAM).", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS.IFETCH", + "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or translation lookaside buffer (TLB) miss which hit in the L2, LLC, DRAM or MMIO (Non-DRAM).", "SampleAfterValue": "200003", "UMask": "0x38" }, @@ -437,6 +438,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", @@ -446,6 +448,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -455,6 +458,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -464,6 +468,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -473,6 +478,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -482,6 +488,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json index 18621909d1a9..c02eb0e836ad 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json @@ -96,6 +96,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -105,6 +106,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json index 00ae180ded25..fefbc383b840 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.SELF_LOCKS", + "Deprecated": "1", "EdgeDetect": "1", "EventCode": "0x63", "EventName": "BUS_LOCK.ALL", @@ -16,6 +17,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.BLOCK_CYCLES", + "Deprecated": "1", "EventCode": "0x63", "EventName": "BUS_LOCK.CYCLES_OTHER_BLOCK", "SampleAfterValue": "200003", @@ -23,6 +25,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.LOCK_CYCLES", + "Deprecated": "1", "EventCode": "0x63", "EventName": "BUS_LOCK.CYCLES_SELF_BLOCK", "SampleAfterValue": "200003", @@ -46,6 +49,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_BOUND_STALLS.LOAD_DRAM_HIT", + "Deprecated": "1", "EventCode": "0x34", "EventName": "C0_STALLS.LOAD_DRAM_HIT", "SampleAfterValue": "200003", @@ -53,6 +57,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_BOUND_STALLS.LOAD_L2_HIT", + "Deprecated": "1", "EventCode": "0x34", "EventName": "C0_STALLS.LOAD_L2_HIT", "SampleAfterValue": "200003", @@ -60,6 +65,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_BOUND_STALLS.LOAD_LLC_HIT", + "Deprecated": "1", "EventCode": "0x34", "EventName": "C0_STALLS.LOAD_LLC_HIT", "SampleAfterValue": "200003", @@ -207,6 +213,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -216,6 +223,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -225,6 +233,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -234,6 +243,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json index 9dd8c909facc..c483c0838e08 100644 --- a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json @@ -165,6 +165,7 @@ }, { "BriefDescription": "This event is deprecated.", + "Deprecated": "1", "EventCode": "0xcd", "EventName": "CYCLES_DIV_BUSY.ANY", "SampleAfterValue": "2000003" @@ -283,6 +284,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event TOPDOWN_BAD_SPECULATION.FASTNUKE", + "Deprecated": "1", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.MONUKE", "SampleAfterValue": "1000003", @@ -338,6 +340,7 @@ }, { "BriefDescription": "This event is deprecated.", + "Deprecated": "1", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.STORE_BUFFER", "SampleAfterValue": "1000003", diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 9570a88d6d1c..79d89c263677 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -71,7 +71,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -81,7 +81,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -89,7 +89,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -109,7 +109,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -125,12 +125,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -150,7 +150,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -171,7 +171,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -180,7 +180,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_clks", + "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -190,7 +190,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -199,25 +199,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -226,7 +226,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -235,7 +235,7 @@ }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_clks", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -245,11 +245,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -257,14 +257,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -274,7 +274,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -294,324 +294,324 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" - }, - { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" - }, - { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" + }, + { + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of parallel requests to external memory", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_parallel_requests", - "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "UNC_CLOCK.SOCKET", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -620,7 +620,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -629,7 +629,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -639,7 +639,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -649,7 +649,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -658,11 +658,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -678,7 +678,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -688,7 +688,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -708,16 +708,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -727,7 +727,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -737,7 +737,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -746,16 +746,16 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -764,7 +764,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -773,7 +773,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -782,7 +782,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -791,7 +791,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -809,7 +809,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -818,7 +818,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -827,7 +827,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -837,7 +837,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -846,7 +846,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -855,7 +855,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -864,7 +864,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -873,7 +873,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -881,7 +881,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -892,7 +892,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -901,7 +901,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -910,16 +910,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -928,7 +928,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -938,7 +938,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -947,7 +947,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -955,7 +955,7 @@ }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", "MetricThreshold": "tma_x87_use > 0.1", diff --git a/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json b/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index a522202cf684..5f451948c893 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -50,11 +50,207 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x181@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x191@) / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x192@) / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from loop stream detector(LSD) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "(UOPS_ISSUED.ANY - IDQ.MITE_UOPS - IDQ.MS_UOPS - IDQ.DSB_UOPS) / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_loop_stream_detector", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Intel(R) Quick Path Interconnect (QPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_Q_TxL_FLITS_G0.DATA * 8 / 1e6 / duration_time", + "MetricName": "qpi_data_transmit_bw", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -70,8 +266,14 @@ "ScaleUnit": "1SMI#" }, { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_UOPS_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -81,7 +283,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -89,7 +291,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -109,7 +311,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -125,12 +327,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -150,7 +352,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -171,7 +373,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -180,7 +382,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_clks", + "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -190,7 +392,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -199,25 +401,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -226,7 +428,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -235,7 +437,7 @@ }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_clks", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -245,11 +447,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -257,14 +459,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -274,7 +476,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -294,325 +496,325 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" - }, - { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" - }, - { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" + }, + { + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", - "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", - "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cbox_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -621,7 +823,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -630,7 +832,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -640,7 +842,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -650,7 +852,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -659,11 +861,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -679,7 +881,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -689,7 +891,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -699,7 +901,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -719,16 +921,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -738,7 +940,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -748,7 +950,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -757,16 +959,16 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -775,7 +977,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -784,7 +986,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -793,7 +995,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -802,7 +1004,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -820,7 +1022,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -829,7 +1031,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -838,7 +1040,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -848,7 +1050,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -857,7 +1059,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -866,7 +1068,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -875,7 +1077,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -884,7 +1086,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -893,7 +1095,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -903,7 +1105,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -912,7 +1114,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -923,7 +1125,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -932,7 +1134,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -941,16 +1143,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -959,7 +1161,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -969,7 +1171,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -978,7 +1180,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -986,11 +1188,17 @@ }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", "MetricThreshold": "tma_x87_use > 0.1", "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json b/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json index a9174a0837f0..79b9f02a4b63 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json @@ -339,6 +339,16 @@ "UMask": "0x8" }, { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or Bus Lock.", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", "Data_LA": "1", "EventCode": "0xd1", @@ -834,6 +844,14 @@ "UMask": "0x4" }, { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0xF4", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { "BriefDescription": "Cycles the queue waiting for offcore responses is full.", "EventCode": "0xf4", "EventName": "SQ_MISC.SQ_FULL", diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index 1a2154f28b7b..20210742171d 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -64,7 +64,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -85,7 +85,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -94,7 +94,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -102,7 +102,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -111,7 +111,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -131,7 +131,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", - "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", @@ -144,12 +144,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -167,7 +167,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -177,7 +177,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(29 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(29 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -197,7 +197,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "23.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "23.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -206,16 +206,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -225,7 +225,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -234,43 +234,43 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "32.5 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "32.5 * tma_info_system_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -279,11 +279,11 @@ }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -291,14 +291,14 @@ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -317,6 +317,7 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -326,7 +327,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -335,7 +336,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -344,7 +345,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -353,7 +354,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -362,7 +363,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -371,7 +372,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -391,7 +392,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -399,668 +400,676 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 5 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_frontend_lsd_coverage" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx512", - "MetricThreshold": "tma_info_iparith_avx512 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_ntaken", - "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_taken", - "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_ret", - "MetricThreshold": "tma_info_ipmisp_ret < 500" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 11", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / tma_info_instructions", + "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / tma_info_inst_mix_instructions", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" - }, - { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l3_miss_latency" + "MetricName": "tma_info_memory_oro_load_l3_miss_latency" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" }, { - "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", - "MetricGroup": "Fed;LSD", - "MetricName": "tma_info_lsd_coverage" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" }, { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_other_branches" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license0_utilization", + "MetricName": "tma_info_system_power_license0_utilization", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license1_utilization", - "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "MetricName": "tma_info_system_power_license1_utilization", + "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license2_utilization", - "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "MetricName": "tma_info_system_power_license2_utilization", + "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_slots_utilization" - }, - { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "UNC_CLOCK.SOCKET", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization" }, { "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 7.5" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1069,7 +1078,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1079,7 +1088,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1088,7 +1097,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1097,20 +1106,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "9 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1125,7 +1134,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_clks)", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1142,7 +1151,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1151,7 +1160,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1160,10 +1169,10 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", - "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%" }, @@ -1179,20 +1188,20 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1207,6 +1216,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1215,7 +1225,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_retiring * tma_info_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "tma_retiring * tma_info_thread_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1224,28 +1234,28 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "([email protected]_UOPS\\,cmask\\=4@ - [email protected]_UOPS\\,cmask\\=5@) / tma_info_clks", + "MetricExpr": "([email protected]_UOPS\\,cmask\\=4@ - [email protected]_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", "ScaleUnit": "100%" }, { @@ -1259,7 +1269,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1268,7 +1278,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_nop_instructions", "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", @@ -1277,6 +1287,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1286,7 +1297,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1295,7 +1306,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1304,7 +1315,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1313,7 +1324,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1322,7 +1333,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1331,7 +1342,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1340,7 +1351,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1349,7 +1360,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1358,7 +1369,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1367,7 +1378,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1377,7 +1388,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1386,7 +1397,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_clks", + "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -1395,7 +1406,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1404,7 +1415,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1413,16 +1424,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1431,7 +1442,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1440,7 +1451,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1449,7 +1460,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1466,7 +1477,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1474,7 +1485,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1483,7 +1494,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "10 * BACLEARS.ANY / tma_info_clks", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", diff --git a/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json b/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json new file mode 100644 index 000000000000..a151ba9cccb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/metricgroups.json @@ -0,0 +1,113 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 1ef772b40e04..ef25cda019be 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -29,11 +29,244 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_CRD + UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF) / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_to_pmem_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM).", + "MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time", + "MetricName": "memory_extra_write_bw_due_to_directory_updates", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -49,8 +282,14 @@ "ScaleUnit": "1SMI#" }, { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -59,7 +298,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -67,7 +306,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -76,7 +315,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -96,7 +335,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", - "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", @@ -109,12 +348,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -132,7 +371,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -142,7 +381,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 43.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 43.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -162,7 +401,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43.5 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "43.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -171,16 +410,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -190,7 +429,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound)", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -199,43 +438,43 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "48 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "48 * tma_info_system_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -244,11 +483,11 @@ }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -256,14 +495,14 @@ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -282,6 +521,7 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -291,7 +531,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -300,7 +540,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -309,7 +549,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -318,7 +558,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -327,7 +567,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -336,7 +576,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -356,7 +596,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -364,726 +604,741 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_core_ipmispredict", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts;TopdownL1;tma_L1_group", + "MetricName": "tma_info_core_ipmispredict", + "MetricgroupNoGroup": "TopdownL1" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 5 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_read_bw" - }, - { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_write_bw" - }, - { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx512", - "MetricThreshold": "tma_info_iparith_avx512 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_ntaken", - "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_taken", - "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_ret", - "MetricThreshold": "tma_info_ipmisp_ret < 500" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 11", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_silent_pki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" - }, - { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_nonsilent_pki" - }, - { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_silent_pki" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / tma_info_instructions", + "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / tma_info_inst_mix_instructions", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" - }, - { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l3_miss_latency" + "MetricName": "tma_info_memory_oro_load_l3_miss_latency" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_read_bw" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_write_bw" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_dram_read_latency", + "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average number of parallel data read requests to external memory", "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", + "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@ if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_pmm_read_latency", + "MetricName": "tma_info_system_mem_pmm_read_latency", "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", + "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" - }, - { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" - }, - { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_other_branches" - }, - { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" - }, - { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "tma_info_pmm_read_bw" + "MetricName": "tma_info_system_pmm_read_bw" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "tma_info_pmm_write_bw" + "MetricName": "tma_info_system_pmm_write_bw" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license0_utilization", + "MetricName": "tma_info_system_power_license0_utilization", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license1_utilization", - "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "MetricName": "tma_info_system_power_license1_utilization", + "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license2_utilization", - "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "MetricName": "tma_info_system_power_license2_utilization", + "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_slots_utilization" - }, - { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cha_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization" }, { "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 7.5" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1092,7 +1347,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1102,7 +1357,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1111,7 +1366,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1120,20 +1375,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "19 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "19 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1148,7 +1403,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_clks)", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1165,7 +1420,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1173,7 +1428,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "43.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "43.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1183,7 +1438,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1202,20 +1457,20 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1230,6 +1485,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1238,7 +1494,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_retiring * tma_info_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "tma_retiring * tma_info_thread_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1247,28 +1503,28 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "([email protected]_UOPS\\,cmask\\=4@ - [email protected]_UOPS\\,cmask\\=5@) / tma_info_clks", + "MetricExpr": "([email protected]_UOPS\\,cmask\\=4@ - [email protected]_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", "ScaleUnit": "100%" }, { @@ -1282,7 +1538,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1291,7 +1547,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_nop_instructions", "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", @@ -1300,6 +1556,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1309,7 +1566,7 @@ }, { "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_pmm_bound", "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1318,7 +1575,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1327,7 +1584,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1336,7 +1593,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1345,7 +1602,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1354,7 +1611,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1363,7 +1620,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1372,7 +1629,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1381,7 +1638,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1390,7 +1647,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1399,7 +1656,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(97 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 97 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(97 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 97 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1408,7 +1665,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "108 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "108 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1417,7 +1674,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1427,7 +1684,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1436,7 +1693,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / tma_info_clks", + "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -1445,7 +1702,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1454,7 +1711,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1463,16 +1720,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1481,7 +1738,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1490,7 +1747,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1499,7 +1756,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1516,7 +1773,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1524,7 +1781,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1533,7 +1790,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "10 * BACLEARS.ANY / tma_info_clks", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -1576,5 +1833,17 @@ "MetricGroup": "transaction", "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_transmit_bw", + "ScaleUnit": "1MB/s" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json new file mode 100644 index 000000000000..bc6a9a4d27a9 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelakex/metricgroups.json @@ -0,0 +1,114 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 11080ccffd51..33fe555252b2 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -71,7 +71,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -81,7 +81,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -89,7 +89,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -109,7 +109,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -125,12 +125,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -150,7 +150,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -171,7 +171,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -180,7 +180,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -190,7 +190,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -199,25 +199,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -226,7 +226,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -235,7 +235,7 @@ }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / tma_info_clks", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -245,11 +245,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -257,14 +257,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -301,7 +301,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -321,358 +321,358 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFETCH_STALL / tma_info_clks - tma_itlb_misses", + "MetricExpr": "ICACHE.IFETCH_STALL / tma_info_thread_clks - tma_itlb_misses", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" - }, - { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of parallel requests to external memory", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_parallel_requests", - "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "UNC_CLOCK.SOCKET", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -681,7 +681,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -690,7 +690,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -700,7 +700,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -710,7 +710,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / tma_info_clks", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -719,11 +719,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -739,7 +739,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -749,7 +749,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -769,16 +769,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -788,7 +788,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -798,7 +798,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -807,16 +807,16 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -825,7 +825,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -834,7 +834,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -843,7 +843,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -852,7 +852,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -870,7 +870,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -880,7 +880,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -889,7 +889,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -898,7 +898,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -907,7 +907,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -916,7 +916,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -924,7 +924,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -935,7 +935,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -944,7 +944,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -953,16 +953,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -971,7 +971,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -981,7 +981,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -990,7 +990,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json b/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivybridge/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 65a46d659c0a..f5e46a768fdd 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -71,7 +71,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -81,7 +81,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -89,7 +89,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -109,7 +109,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -125,12 +125,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -150,7 +150,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -171,7 +171,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -180,7 +180,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -190,7 +190,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -199,25 +199,25 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -226,7 +226,7 @@ }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -235,7 +235,7 @@ }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_clks", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -245,11 +245,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -257,14 +257,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -301,7 +301,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -321,359 +321,359 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFETCH_STALL / tma_info_clks - tma_itlb_misses", + "MetricExpr": "ICACHE.IFETCH_STALL / tma_info_thread_clks - tma_itlb_misses", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" - }, - { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" }, { "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", - "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", - "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_core_clks", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cbox_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -682,7 +682,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -691,7 +691,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -701,7 +701,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -711,7 +711,7 @@ { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -720,11 +720,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -740,7 +740,7 @@ { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -750,7 +750,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -760,7 +760,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -780,16 +780,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -799,7 +799,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -809,7 +809,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -818,16 +818,16 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -836,7 +836,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -845,7 +845,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -854,7 +854,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -863,7 +863,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -881,7 +881,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -891,7 +891,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -900,7 +900,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -909,7 +909,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -918,7 +918,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -927,7 +927,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -936,7 +936,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -946,7 +946,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "310 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricExpr": "310 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -955,7 +955,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -966,7 +966,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -975,7 +975,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -984,16 +984,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1002,7 +1002,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1012,7 +1012,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1021,7 +1021,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json b/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json new file mode 100644 index 000000000000..f6a0258e3241 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index 66a6f657bd6f..35b1a3aa728d 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -82,7 +82,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -98,12 +98,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -123,7 +123,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -133,7 +133,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -142,16 +142,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1", @@ -163,14 +163,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -207,7 +207,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -226,169 +226,169 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" - }, - { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_DISPATCHED.THREAD / (cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_DISPATCHED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_DISPATCHED.THREAD / (cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" }, { - "BriefDescription": "Total number of retired Instructions", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", - "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Average number of parallel data read requests to external memory", "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", + "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / duration_time)", "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", + "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cbox_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_DISPATCHED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -398,7 +398,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -407,11 +407,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage", "ScaleUnit": "100%" }, { @@ -437,16 +437,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_dram_bw_use", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -456,7 +456,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -466,7 +466,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -475,7 +475,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -485,7 +485,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / tma_info_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -494,7 +494,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -504,7 +504,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json b/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json new file mode 100644 index 000000000000..bebb85945d62 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/metricgroups.json @@ -0,0 +1,100 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 66c37a3cbf43..6543a68d4a17 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,19 +1,19 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.20,alderlake,core -GenuineIntel-6-BE,v1.20,alderlaken,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.21,alderlake,core +GenuineIntel-6-BE,v1.21,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core -GenuineIntel-6-(3D|47),v27,broadwell,core -GenuineIntel-6-56,v9,broadwellde,core -GenuineIntel-6-4F,v20,broadwellx,core -GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core -GenuineIntel-6-9[6C],v1.03,elkhartlake,core +GenuineIntel-6-(3D|47),v28,broadwell,core +GenuineIntel-6-56,v10,broadwellde,core +GenuineIntel-6-4F,v21,broadwellx,core +GenuineIntel-6-55-[56789ABCDEF],v1.18,cascadelakex,core +GenuineIntel-6-9[6C],v1.04,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-B6,v1.00,grandridge,core GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v33,haswell,core GenuineIntel-6-3F,v27,haswellx,core -GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core +GenuineIntel-6-(7D|7E|A7),v1.18,icelake,core GenuineIntel-6-6[AC],v1.20,icelakex,core GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v23,ivytown,core @@ -23,13 +23,13 @@ GenuineIntel-6-A[AC],v1.01,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-(8F|CF),v1.12,sapphirerapids,core +GenuineIntel-6-(8F|CF),v1.13,sapphirerapids,core GenuineIntel-6-AF,v1.00,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core -GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v55,skylake,core -GenuineIntel-6-55-[01234],v1.29,skylakex,core -GenuineIntel-6-86,v1.20,snowridgex,core -GenuineIntel-6-8[CD],v1.10,tigerlake,core +GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v56,skylake,core +GenuineIntel-6-55-[01234],v1.30,skylakex,core +GenuineIntel-6-86,v1.21,snowridgex,core +GenuineIntel-6-8[CD],v1.12,tigerlake,core GenuineIntel-6-2C,v4,westmereep-dp,core GenuineIntel-6-25,v3,westmereep-sp,core GenuineIntel-6-2F,v3,westmereex,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json b/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json new file mode 100644 index 000000000000..bebb85945d62 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sandybridge/metricgroups.json @@ -0,0 +1,100 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4b8bc19392a4..8898b6fd0dea 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -82,7 +82,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -98,12 +98,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -123,7 +123,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -133,7 +133,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -142,16 +142,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1", @@ -163,14 +163,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -207,7 +207,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -226,168 +226,168 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" - }, - { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" - }, - { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_DISPATCHED.THREAD / (cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_DISPATCHED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_DISPATCHED.THREAD / (cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" }, { - "BriefDescription": "Total number of retired Instructions", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", - "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "MetricName": "tma_info_system_kernel_cpi" }, { "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Average number of parallel requests to external memory", "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_parallel_requests", + "MetricName": "tma_info_system_mem_parallel_requests", "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" }, { "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency" - }, - { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "MetricName": "tma_info_system_mem_request_latency" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "UNC_CLOCK.SOCKET", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_DISPATCHED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -397,7 +397,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", "MetricConstraint": "NO_GROUP_EVENTS_SMT", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -406,11 +406,11 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage", "ScaleUnit": "100%" }, { @@ -436,16 +436,16 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_dram_bw_use", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_system_dram_bw_use", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -455,7 +455,7 @@ { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -465,7 +465,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -474,7 +474,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -484,7 +484,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / tma_info_clks", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -493,7 +493,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -503,7 +503,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json index b72a36999930..e8bf7c9c44e1 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json @@ -32,18 +32,20 @@ "UMask": "0x3" }, { - "BriefDescription": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.", "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x5" }, { - "BriefDescription": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.", "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", "SampleAfterValue": "1000003", "UMask": "0x9" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json new file mode 100644 index 000000000000..e6f7934320bf --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/metricgroups.json @@ -0,0 +1,118 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_assists_group": "Metrics contributing to tma_assists category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_int_operations_group": "Metrics contributing to tma_int_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_bandwidth_group": "Metrics contributing to tma_mem_bandwidth category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 620fc5bd2217..4f3dd85540b6 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -29,11 +29,262 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF) / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_to_dram_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_to_pmem_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory write bandwidth (MB/sec) caused by directory updates; includes DDR and Intel(R) Optane(TM) Persistent Memory(PMEM).", + "MetricExpr": "(UNC_CHA_DIR_UPDATE.HA + UNC_CHA_DIR_UPDATE.TOR + UNC_M2M_DIRECTORY_UPDATE.ANY) * 64 / 1e6 / duration_time", + "MetricName": "memory_extra_write_bw_due_to_directory_updates", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", + "MetricName": "pmem_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -49,8 +300,14 @@ "ScaleUnit": "1SMI#" }, { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -58,7 +315,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the Advanced Matrix Extensions (AMX) execution engine was busy with tile (arithmetic) operations", - "MetricExpr": "EXE.AMX_BUSY / tma_info_core_clks", + "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks", "MetricGroup": "Compute;HPC;Server;TopdownL5;tma_L5_group;tma_ports_utilized_0_group", "MetricName": "tma_amx_busy", "MetricThreshold": "tma_amx_busy > 0.5 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -66,7 +323,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * [email protected]\\,umask\\=0x1B@ / tma_info_slots", + "MetricExpr": "100 * [email protected]\\,umask\\=0x1B@ / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -75,7 +332,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", - "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_slots", + "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_avx_assists", "MetricThreshold": "tma_avx_assists > 0.1", @@ -83,7 +340,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -103,17 +360,17 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -131,7 +388,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -141,7 +398,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(76 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(76 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -161,7 +418,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "75.5 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "75.5 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -170,16 +427,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -189,7 +446,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks)", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -198,43 +455,43 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "80 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "80 * tma_info_system_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -243,11 +500,11 @@ }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -255,14 +512,14 @@ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -281,7 +538,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine)", - "MetricExpr": "cpu@AMX_OPS_RETIRED.BF16\\,cmask\\=1@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@AMX_OPS_RETIRED.BF16\\,cmask\\=1@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;HPC;Pipeline;Server;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_fp_amx", "MetricThreshold": "tma_fp_amx > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -290,6 +547,7 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector + tma_fp_amx", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -299,7 +557,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", - "MetricExpr": "30 * ASSISTS.FP / tma_info_slots", + "MetricExpr": "30 * ASSISTS.FP / tma_info_thread_slots", "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_fp_assists", "MetricThreshold": "tma_fp_assists > 0.1", @@ -308,7 +566,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -317,7 +575,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -326,7 +584,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -335,7 +593,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -344,7 +602,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -353,7 +611,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -363,7 +621,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fused_instructions", "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", @@ -372,7 +630,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -382,7 +640,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / tma_info_clks", + "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -390,746 +648,754 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 6 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 6 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "tma_info_flopc / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_write_bw" - }, - { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR + (cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ + FP_ARITH_INST_RETIRED2.VECTOR))", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.BF16", "MetricGroup": "Flops;FpVector;InsType;Server", - "MetricName": "tma_info_iparith_amx_f16", - "MetricThreshold": "tma_info_iparith_amx_f16 < 10", + "MetricName": "tma_info_inst_mix_iparith_amx_f16", + "MetricThreshold": "tma_info_inst_mix_iparith_amx_f16 < 10", "PublicDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." }, { "BriefDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.INT8", "MetricGroup": "InsType;IntVector;Server", - "MetricName": "tma_info_iparith_amx_int8", - "MetricThreshold": "tma_info_iparith_amx_int8 < 10", + "MetricName": "tma_info_inst_mix_iparith_amx_int8", + "MetricThreshold": "tma_info_inst_mix_iparith_amx_int8 < 10", "PublicDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx512", - "MetricThreshold": "tma_info_iparith_avx512 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Instructions per a microcode Assist invocation", - "MetricExpr": "INST_RETIRED.ANY / [email protected]\\,umask\\=0x1B@", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_ipassist", - "MetricThreshold": "tma_info_ipassist < 100e3", - "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" - }, - { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_flopc", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_flopc", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_ntaken", - "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_taken", - "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_ret", - "MetricThreshold": "tma_info_ipmisp_ret < 500" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 13", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 13", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_silent_pki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" - }, - { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_nonsilent_pki" - }, - { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_silent_pki" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" - }, - { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l3_miss_latency" + "MetricName": "tma_info_memory_oro_load_l3_miss_latency" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" + }, + { + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "INST_RETIRED.ANY / [email protected]\\,umask\\=0x1B@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_pipeline_ipassist", + "MetricThreshold": "tma_info_pipeline_ipassist < 100e3", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_strings_cycles", + "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "tma_info_core_flopc / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_write_bw" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_dram_read_latency", + "MetricName": "tma_info_system_mem_dram_read_latency", "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average number of parallel data read requests to external memory", "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", + "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@ if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_pmm_read_latency", + "MetricName": "tma_info_system_mem_pmm_read_latency", "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", + "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" - }, - { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" - }, - { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" - }, - { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" - }, - { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_other_branches" - }, - { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" - }, - { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "tma_info_pmm_read_bw" + "MetricName": "tma_info_system_pmm_read_bw" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "tma_info_pmm_write_bw" - }, - { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_slots_utilization" + "MetricName": "tma_info_system_pmm_write_bw" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "uncore_cha_0@event\\=0x1@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" - }, - { - "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_strings_cycles", - "MetricThreshold": "tma_info_strings_cycles > 0.1" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Tera Integer (matrix) Operations Per Second", "MetricExpr": "8 * AMX_OPS_RETIRED.INT8 / 1e12 / duration_time", "MetricGroup": "Cor;HPC;IntVector;Server", - "MetricName": "tma_info_tiops" + "MetricName": "tma_info_system_tiops" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" - }, - { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_system_turbo_utilization" }, { "BriefDescription": "Cross-socket Ultra Path Interconnect (UPI) data transmit bandwidth for data only [MB / sec]", "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 64 / 9 / 1e6", "MetricGroup": "Server;SoC", - "MetricName": "tma_info_upi_data_transmit_bw" + "MetricName": "tma_info_system_upi_data_transmit_bw" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 9" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 9" }, { "BriefDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine)", - "MetricExpr": "cpu@AMX_OPS_RETIRED.INT8\\,cmask\\=1@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@AMX_OPS_RETIRED.INT8\\,cmask\\=1@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;HPC;IntVector;Pipeline;Server;TopdownL4;tma_L4_group;tma_int_operations_group", "MetricName": "tma_int_amx", "MetricThreshold": "tma_int_amx > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -1147,7 +1413,7 @@ }, { "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", - "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_128b", "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -1156,7 +1422,7 @@ }, { "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", - "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", "MetricName": "tma_int_vector_256b", "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -1165,7 +1431,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_TAG.STALLS / tma_info_clks", + "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1174,7 +1440,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1184,7 +1450,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1193,7 +1459,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1202,20 +1468,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "33 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "33 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "DECODE.LCP / tma_info_clks", + "MetricExpr": "DECODE.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1230,7 +1496,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_clks)", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1247,7 +1513,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1255,7 +1521,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "71 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "71 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1265,7 +1531,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1284,7 +1550,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", - "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_clks", + "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", "MetricName": "tma_mba_stalls", "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1292,25 +1558,25 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", @@ -1320,7 +1586,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_clks", + "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_memory_fence", "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -1328,7 +1594,8 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_slots)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", @@ -1336,7 +1603,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1345,25 +1612,25 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 6 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_clks", + "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", "MetricThreshold": "tma_mixing_vectors > 0.05", @@ -1372,7 +1639,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_slots / UOPS_ISSUED.ANY) / tma_info_clks", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_thread_slots / UOPS_ISSUED.ANY) / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1381,7 +1648,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_non_fused_branches", "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", @@ -1390,7 +1657,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_nop_instructions", "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", @@ -1399,6 +1666,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1408,7 +1676,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", - "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_slots", + "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", "MetricName": "tma_page_faults", "MetricThreshold": "tma_page_faults > 0.05", @@ -1417,7 +1685,7 @@ }, { "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_pmm_bound", "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1426,7 +1694,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1435,7 +1703,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1444,7 +1712,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1453,7 +1721,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_clks)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1462,7 +1730,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_clks", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1471,7 +1739,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1480,7 +1748,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1489,7 +1757,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1498,7 +1766,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(135.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 135.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(135.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 135.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1507,7 +1775,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "149 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "149 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1516,7 +1784,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1526,7 +1794,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1535,7 +1803,7 @@ }, { "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", - "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_slots)", + "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", "MetricName": "tma_shuffles", "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", @@ -1543,7 +1811,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_clks", + "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -1552,7 +1820,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1561,7 +1829,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1570,16 +1838,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_clks", + "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1588,7 +1856,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1597,7 +1865,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1606,7 +1874,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1623,7 +1891,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1631,7 +1899,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1640,7 +1908,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_clks", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -1683,5 +1951,17 @@ "MetricGroup": "transaction", "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_transmit_bw", + "ScaleUnit": "1MB/s" } ] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json index 08faf38115d9..6800de05c836 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json @@ -464,7 +464,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Counts the time when FM didn? do d2c for fill reads (cross tile case)", + "BriefDescription": "Counts the time when FM didn't do d2c for fill reads (cross tile case)", "EventCode": "0x4a", "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json index 225333561295..3ff9e9b722c8 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json @@ -2480,11 +2480,11 @@ "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands. : Precharge due to (?)", + "BriefDescription": "DRAM Precharge commands", "EventCode": "0x03", "EventName": "UNC_M_PRE_COUNT.PGT", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Precharge due to (?) : Counts the number of DRAM Precharge commands sent on this channel.", + "PublicDescription": "DRAM Precharge commands. Counts the number of DRAM Precharge commands sent on this channel.", "UMask": "0x88", "Unit": "iMC" }, @@ -3236,7 +3236,7 @@ "Unit": "iMC" }, { - "BriefDescription": "2LM Tag check hit due to memory read (bug?)", + "BriefDescription": "2LM Tag check hit due to memory read", "EventCode": "0xd3", "EventName": "UNC_M_TAGCHK.NM_RD_HIT", "PerPkg": "1", @@ -3244,7 +3244,7 @@ "Unit": "iMC" }, { - "BriefDescription": "2LM Tag check hit due to memory write (bug?)", + "BriefDescription": "2LM Tag check hit due to memory write", "EventCode": "0xd3", "EventName": "UNC_M_TAGCHK.NM_WR_HIT", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json index 4d494a5cabbf..5891bd74af60 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json @@ -32,6 +32,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x18" + }, + { "BriefDescription": "Counts once for most SIMD scalar computational floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", diff --git a/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json b/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json new file mode 100644 index 000000000000..a151ba9cccb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylake/metricgroups.json @@ -0,0 +1,113 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index 2dfc3af08eff..cc800fb8180a 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -26,12 +26,21 @@ "UMask": "0x4" }, { - "BriefDescription": "Conditional branch instructions retired.", + "BriefDescription": "Conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.CONDITIONAL]", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "This event counts conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.CONDITIONAL]", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.COND]", "Errata": "SKL091", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.CONDITIONAL", "PEBS": "1", - "PublicDescription": "This event counts conditional branch instructions retired.", + "PublicDescription": "This event counts conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.COND]", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -405,9 +414,9 @@ "UMask": "0x1" }, { - "AnyThread": "1", "BriefDescription": "Clears speculative count", "CounterMask": "1", + "EdgeDetect": "1", "EventCode": "0x0D", "EventName": "INT_MISC.CLEARS_COUNT", "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 21ef6c9be816..2ed88842b880 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -50,7 +50,7 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, @@ -71,7 +71,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -80,7 +80,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -88,7 +88,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_slots", + "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -97,7 +97,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -107,7 +107,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -123,12 +123,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -146,7 +146,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -156,7 +156,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(18.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(18.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -177,7 +177,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "16.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "16.5 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -186,16 +186,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -205,7 +205,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -214,45 +214,45 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "22 * tma_info_average_frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "22 * tma_info_system_average_frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -262,11 +262,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -274,14 +274,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -347,7 +347,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -366,7 +366,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_slots", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -376,7 +376,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -384,220 +384,231 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { @@ -605,416 +616,404 @@ "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" - }, - { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" - }, - { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" }, { "BriefDescription": "Average number of parallel data read requests to external memory", "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@thresh\\=1@", "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", + "MetricName": "tma_info_system_mem_parallel_reads", "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { "BriefDescription": "Average number of parallel requests to external memory", "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_parallel_requests", + "MetricName": "tma_info_system_mem_parallel_requests", "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" }, { "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_REQUESTS.DATA_READ) / (tma_info_socket_clks / duration_time)", + "MetricExpr": "1e9 * (UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_REQUESTS.DATA_READ) / (tma_info_system_socket_clks / duration_time)", "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", + "MetricName": "tma_info_system_mem_read_latency", "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency" + "MetricName": "tma_info_system_mem_request_latency" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_system_smt_2t_utilization" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" }, { "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", + "MetricExpr": "4 * tma_info_core_core_clks", "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" - }, - { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" - }, - { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1023,7 +1022,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1033,7 +1032,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1042,7 +1041,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1051,20 +1050,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "6.5 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "6.5 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1079,7 +1078,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1097,7 +1096,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1105,7 +1104,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1125,20 +1124,20 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1162,7 +1161,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1171,19 +1170,19 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, @@ -1198,7 +1197,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1234,7 +1233,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1243,7 +1242,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1252,7 +1251,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -1261,7 +1260,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -1279,7 +1278,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1288,7 +1287,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1297,7 +1296,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -1306,7 +1305,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1315,7 +1314,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_clks", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1324,7 +1323,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_clks", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1333,7 +1332,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_clks", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1342,7 +1341,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_clks", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1350,7 +1349,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1360,7 +1359,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1370,7 +1369,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1379,7 +1378,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1388,16 +1387,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1406,7 +1405,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1416,7 +1415,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1425,7 +1424,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1441,7 +1440,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1449,7 +1448,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "9 * BACLEARS.ANY / tma_info_clks", + "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json index 64dd36387209..384b3c551a1f 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -32,6 +32,14 @@ "UMask": "0x20" }, { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x18" + }, + { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", @@ -48,6 +56,22 @@ "UMask": "0x80" }, { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Counts once for most SIMD scalar computational floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Counts once for most SIMD scalar computational single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SIMD scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { "BriefDescription": "Counts once for most SIMD scalar computational double precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", @@ -64,6 +88,13 @@ "UMask": "0x2" }, { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "2000003", + "UMask": "0xfc" + }, + { "BriefDescription": "Cycles with any input/output SSE or FP assist", "CounterMask": "1", "EventCode": "0xCA", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json b/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json new file mode 100644 index 000000000000..bc6a9a4d27a9 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/metricgroups.json @@ -0,0 +1,114 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IoBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json index 0f06e314fe36..31a1663d57f8 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -26,12 +26,21 @@ "UMask": "0x4" }, { - "BriefDescription": "Conditional branch instructions retired.", + "BriefDescription": "Conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.CONDITIONAL]", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.COND", + "PublicDescription": "This event counts conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.CONDITIONAL]", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.COND]", "Errata": "SKL091", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.CONDITIONAL", "PEBS": "1", - "PublicDescription": "This event counts conditional branch instructions retired.", + "PublicDescription": "This event counts conditional branch instructions retired. [This event is alias to BR_INST_RETIRED.COND]", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -414,6 +423,16 @@ "UMask": "0x1" }, { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "EventCode": "0x0D", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index eb6f12c0343d..507d39efacc8 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -50,11 +50,220 @@ }, { "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", "MetricGroup": "SoC", "MetricName": "UNCORE_FREQ" }, { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "dtlb_2mb_large_page_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x12CC0233@ / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS\\,config1\\=0x40433@ / cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40433@) / (UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "1e9 * (cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS\\,config1\\=0x40432@ / cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@) / (UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "1e9 * (cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS\\,config1\\=0x40431@ / cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@) / (UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", + "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x12D40433@ / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_local_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", + "MetricName": "llc_miss_remote_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@ / (cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40432@ + cha@UNC_CHA_TOR_INSERTS.IA_MISS\\,config1\\=0x40431@)", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MITE_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "100%" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -70,8 +279,14 @@ "ScaleUnit": "1SMI#" }, { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -80,7 +295,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -88,7 +303,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_slots", + "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -97,7 +312,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -107,7 +322,7 @@ }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", @@ -123,12 +338,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -146,7 +361,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -156,7 +371,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -177,7 +392,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "44 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -186,16 +401,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -205,7 +420,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -214,45 +429,45 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(110 * tma_info_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_clks", + "MetricExpr": "(110 * tma_info_system_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -262,11 +477,11 @@ { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -274,14 +489,14 @@ "MetricExpr": "tma_frontend_bound - tma_fetch_latency", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -356,7 +571,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -375,7 +590,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_slots", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots", "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", @@ -385,7 +600,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_clks", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -393,686 +608,692 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_core_ipmispredict", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts;TopdownL1;tma_L1_group", + "MetricName": "tma_info_core_ipmispredict", + "MetricgroupNoGroup": "TopdownL1" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_read_bw" - }, - { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "tma_info_io_write_bw" - }, - { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx512", - "MetricThreshold": "tma_info_iparith_avx512 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 9", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_inst_mix_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_memory_core_l2_evictions_silent_pki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" - }, - { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_nonsilent_pki" - }, - { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "tma_info_l2_evictions_silent_pki" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" - }, - { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" }, { - "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "tma_info_mem_dram_read_latency", - "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", - "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", - "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_read_bw" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_system_io_write_bw" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_system_mem_dram_read_latency", + "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_system_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks)", + "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", - "MetricName": "tma_info_power_license0_utilization", + "MetricName": "tma_info_system_power_license0_utilization", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks)", + "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", - "MetricName": "tma_info_power_license1_utilization", - "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "MetricName": "tma_info_system_power_license1_utilization", + "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks)", + "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_core_clks)", "MetricGroup": "Power", - "MetricName": "tma_info_power_license2_utilization", - "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "MetricName": "tma_info_system_power_license2_utilization", + "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * tma_info_core_clks", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" - }, - { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "MetricName": "tma_info_system_smt_2t_utilization" }, { "BriefDescription": "Socket actual clocks when any core is active on that socket", "MetricExpr": "cha_0@event\\=0x0@", "MetricGroup": "SoC", - "MetricName": "tma_info_socket_clks" - }, - { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" + "MetricName": "tma_info_system_socket_clks" }, { "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" }, { "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 6" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1081,7 +1302,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1091,7 +1312,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1100,7 +1321,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1109,20 +1330,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "17 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1137,7 +1358,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1155,7 +1376,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1163,7 +1384,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "59.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "59.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1172,7 +1393,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1192,20 +1413,20 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1229,7 +1450,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1238,19 +1459,19 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, @@ -1265,7 +1486,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1301,7 +1522,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1310,7 +1531,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1319,7 +1540,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", "MetricThreshold": "tma_port_2 > 0.6", @@ -1328,7 +1549,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", "MetricThreshold": "tma_port_3 > 0.6", @@ -1346,7 +1567,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1355,7 +1576,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1364,7 +1585,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", "MetricName": "tma_port_7", "MetricThreshold": "tma_port_7 > 0.6", @@ -1373,7 +1594,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1382,7 +1603,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_clks", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1391,7 +1612,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_clks", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1400,7 +1621,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_clks", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1409,7 +1630,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_clks", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1418,7 +1639,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(89.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", "MetricName": "tma_remote_cache", "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1427,7 +1648,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "127 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "127 * tma_info_system_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_remote_dram", "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1436,7 +1657,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1446,7 +1667,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1456,7 +1677,7 @@ { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1465,7 +1686,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1474,16 +1695,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1492,7 +1713,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1502,7 +1723,7 @@ { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", "MetricConstraint": "NO_GROUP_EVENTS_NMI", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1511,7 +1732,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1527,7 +1748,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1535,7 +1756,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "9 * BACLEARS.ANY / tma_info_clks", + "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -1578,5 +1799,17 @@ "MetricGroup": "transaction", "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_transmit_bw", + "ScaleUnit": "1MB/s" } ] diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/cache.json b/tools/perf/pmu-events/arch/x86/snowridgex/cache.json index 0ab90e3bf76b..c6be60584522 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/cache.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/cache.json @@ -72,6 +72,7 @@ "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2, LLC, DRAM or MMIO (Non-DRAM).", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS.IFETCH", + "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or translation lookaside buffer (TLB) miss which hit in the L2, LLC, DRAM or MMIO (Non-DRAM).", "SampleAfterValue": "200003", "UMask": "0x38" }, @@ -437,6 +438,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", @@ -446,6 +448,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -455,6 +458,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -464,6 +468,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -473,6 +478,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -482,6 +488,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/memory.json index 18621909d1a9..c02eb0e836ad 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/memory.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/memory.json @@ -96,6 +96,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -105,6 +106,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/other.json b/tools/perf/pmu-events/arch/x86/snowridgex/other.json index 00ae180ded25..fefbc383b840 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/other.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/other.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.SELF_LOCKS", + "Deprecated": "1", "EdgeDetect": "1", "EventCode": "0x63", "EventName": "BUS_LOCK.ALL", @@ -16,6 +17,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.BLOCK_CYCLES", + "Deprecated": "1", "EventCode": "0x63", "EventName": "BUS_LOCK.CYCLES_OTHER_BLOCK", "SampleAfterValue": "200003", @@ -23,6 +25,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event BUS_LOCK.LOCK_CYCLES", + "Deprecated": "1", "EventCode": "0x63", "EventName": "BUS_LOCK.CYCLES_SELF_BLOCK", "SampleAfterValue": "200003", @@ -46,6 +49,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_BOUND_STALLS.LOAD_DRAM_HIT", + "Deprecated": "1", "EventCode": "0x34", "EventName": "C0_STALLS.LOAD_DRAM_HIT", "SampleAfterValue": "200003", @@ -53,6 +57,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_BOUND_STALLS.LOAD_L2_HIT", + "Deprecated": "1", "EventCode": "0x34", "EventName": "C0_STALLS.LOAD_L2_HIT", "SampleAfterValue": "200003", @@ -60,6 +65,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event MEM_BOUND_STALLS.LOAD_LLC_HIT", + "Deprecated": "1", "EventCode": "0x34", "EventName": "C0_STALLS.LOAD_LLC_HIT", "SampleAfterValue": "200003", @@ -207,6 +213,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -216,6 +223,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -225,6 +233,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -234,6 +243,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING", + "Deprecated": "1", "EventCode": "0XB7", "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json b/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json index 9dd8c909facc..c483c0838e08 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/pipeline.json @@ -165,6 +165,7 @@ }, { "BriefDescription": "This event is deprecated.", + "Deprecated": "1", "EventCode": "0xcd", "EventName": "CYCLES_DIV_BUSY.ANY", "SampleAfterValue": "2000003" @@ -283,6 +284,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event TOPDOWN_BAD_SPECULATION.FASTNUKE", + "Deprecated": "1", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.MONUKE", "SampleAfterValue": "1000003", @@ -338,6 +340,7 @@ }, { "BriefDescription": "This event is deprecated.", + "Deprecated": "1", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.STORE_BUFFER", "SampleAfterValue": "1000003", diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json index de3840078e21..7e2895f7fe3d 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json @@ -590,7 +590,7 @@ "EventCode": "0x0C", "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Outbound Request Queue Occupancy : Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Outbound Request Queue Occupancy : Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -5570,7 +5570,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", "EventCode": "0x4D", "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", "PerPkg": "1", @@ -5578,7 +5578,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", "EventCode": "0x4D", "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", "PerPkg": "1", @@ -5586,7 +5586,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 2", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 2", "EventCode": "0x4D", "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN2", "PerPkg": "1", @@ -5594,7 +5594,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", "EventCode": "0x4E", "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", "PerPkg": "1", @@ -5602,7 +5602,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", "EventCode": "0x4E", "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", "PerPkg": "1", @@ -5610,7 +5610,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 2", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 2", "EventCode": "0x4E", "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN2", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json index 996028071ee4..ecdd6f0f8e8f 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json @@ -34,7 +34,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", "UMask": "0x20", "Unit": "iio_free_running" }, @@ -43,7 +42,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", "UMask": "0x21", "Unit": "iio_free_running" }, @@ -52,7 +50,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", "UMask": "0x22", "Unit": "iio_free_running" }, @@ -61,7 +58,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", "UMask": "0x23", "Unit": "iio_free_running" }, @@ -70,7 +66,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", "UMask": "0x24", "Unit": "iio_free_running" }, @@ -79,7 +74,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", "UMask": "0x25", "Unit": "iio_free_running" }, @@ -88,7 +82,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", "UMask": "0x26", "Unit": "iio_free_running" }, @@ -97,7 +90,6 @@ "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", "UMask": "0x27", "Unit": "iio_free_running" }, diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json index 530e9b71b92a..b80911d498dd 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json @@ -130,7 +130,6 @@ "EventCode": "0xff", "EventName": "UNC_M_CLOCKTICKS_FREERUN", "PerPkg": "1", - "PublicDescription": "UNC_M_CLOCKTICKS_FREERUN", "UMask": "0x10", "Unit": "imc_free_running" }, @@ -322,7 +321,7 @@ "EventCode": "0x02", "EventName": "UNC_M_PRE_COUNT.PGT", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Precharge due to page table : Counts the number of DRAM Precharge commands sent on this channel. : Prechages from Page Table", + "PublicDescription": "DRAM Precharge commands. : Precharge due to page table : Counts the number of DRAM Precharge commands sent on this channel. : Precharges from Page Table", "UMask": "0x10", "Unit": "iMC" }, @@ -497,7 +496,7 @@ "EventCode": "0x82", "EventName": "UNC_M_WPQ_OCCUPANCY_PCH0", "PerPkg": "1", - "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", "Unit": "iMC" }, { @@ -505,7 +504,7 @@ "EventCode": "0x83", "EventName": "UNC_M_WPQ_OCCUPANCY_PCH1", "PerPkg": "1", - "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-power.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-power.json index 27fc155f1223..a61ffca2dfea 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-power.json @@ -149,7 +149,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", "PerPkg": "1", - "PublicDescription": "Number of cores in C-State : C0 and C1 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "Number of cores in C-State : C0 and C1 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -157,7 +157,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", "PerPkg": "1", - "PublicDescription": "Number of cores in C-State : C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "Number of cores in C-State : C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -165,7 +165,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", "PerPkg": "1", - "PublicDescription": "Number of cores in C-State : C6 and C7 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "Number of cores in C-State : C6 and C7 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json index 738249a6f488..c54fb65d3259 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json @@ -323,6 +323,16 @@ "UMask": "0x2" }, { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", "Data_LA": "1", "EventCode": "0xd1", @@ -511,6 +521,14 @@ "UMask": "0x4" }, { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0xf4", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { "BriefDescription": "Cycles the superQ cannot take any more entries.", "EventCode": "0xf4", "EventName": "SQ_MISC.SQ_FULL", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json new file mode 100644 index 000000000000..a151ba9cccb0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json @@ -0,0 +1,113 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json index a0aeeb801fd7..020801cbd7e3 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json @@ -395,6 +395,7 @@ { "BriefDescription": "Clears speculative count", "CounterMask": "1", + "EdgeDetect": "1", "EventCode": "0x0d", "EventName": "INT_MISC.CLEARS_COUNT", "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index b442ed4acfbb..d0538a754288 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -79,7 +79,7 @@ }, { "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_4k_aliasing", "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -88,7 +88,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_alu_op_utilization", "MetricThreshold": "tma_alu_op_utilization > 0.6", @@ -96,7 +96,7 @@ }, { "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_thread_slots", "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", "MetricName": "tma_assists", "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", @@ -105,7 +105,7 @@ }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", @@ -125,7 +125,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", - "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_branch_instructions", "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", @@ -138,12 +138,12 @@ "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteers", "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -161,7 +161,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", "MetricName": "tma_clears_resteers", "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", @@ -171,7 +171,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(49 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "(49 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -191,7 +191,7 @@ { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "48 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "48 * tma_info_system_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_data_sharing", "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -200,16 +200,16 @@ }, { "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", "MetricName": "tma_decoder0_alone", - "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -219,7 +219,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -228,43 +228,43 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_dsb", - "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_dsb_switches", "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", "MetricName": "tma_dtlb_load", "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", "MetricName": "tma_dtlb_store", "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "54 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricExpr": "54 * tma_info_system_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -273,11 +273,11 @@ }, { "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", "MetricName": "tma_fb_full", "MetricThreshold": "tma_fb_full > 0.3", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { @@ -285,14 +285,14 @@ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", - "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35", "MetricgroupNoGroup": "TopdownL2", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_thread_slots", "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", @@ -311,6 +311,7 @@ }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", @@ -320,7 +321,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -329,7 +330,7 @@ }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", @@ -338,7 +339,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_128b", "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -347,7 +348,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_256b", "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -356,7 +357,7 @@ }, { "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", "MetricName": "tma_fp_vector_512b", "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", @@ -365,7 +366,7 @@ }, { "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", @@ -385,7 +386,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_icache_misses", "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -393,688 +394,696 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "tma_info_average_frequency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", - "MetricName": "tma_info_big_code", - "MetricThreshold": "tma_info_big_code > 20", - "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" }, { - "BriefDescription": "Branch instructions per taken branch.", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_bptkbranch" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_branch_misprediction_cost", - "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", - "MetricGroup": "Ret;tma_issueBC", - "MetricName": "tma_info_branching_overhead", - "MetricThreshold": "tma_info_branching_overhead > 10", - "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_callret" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "tma_info_clks" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Fed;MemoryTLB", - "MetricName": "tma_info_code_stlb_mpki" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_callret" }, { "BriefDescription": "Fraction of branches that are non-taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_nt" + "MetricName": "tma_info_branches_cond_nt" }, { "BriefDescription": "Fraction of branches that are taken conditionals", "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "tma_info_cond_tk" + "MetricName": "tma_info_branches_cond_tk" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "tma_info_core_bound_likely", - "MetricThreshold": "tma_info_core_bound_likely > 0.5" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches" }, { "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", "MetricGroup": "SMT", - "MetricName": "tma_info_core_clks" + "MetricName": "tma_info_core_core_clks" }, { "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_coreipc" + "MetricName": "tma_info_core_coreipc" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / tma_info_ipc", - "MetricGroup": "Mem;Pipeline", - "MetricName": "tma_info_cpi" - }, - { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "tma_info_cpu_utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" }, { - "BriefDescription": "Average Parallel L2 cache miss data reads", - "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_data_l2_mlp" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", - "MetricName": "tma_info_dram_bw_use", - "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" }, { "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", - "MetricName": "tma_info_dsb_coverage", - "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 5 > 0.35", - "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" - }, - { - "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", - "MetricGroup": "DSBmiss;Fed;tma_issueFB", - "MetricName": "tma_info_dsb_misses", - "MetricThreshold": "tma_info_dsb_misses > 10", - "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" }, { "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", "MetricGroup": "DSBmiss", - "MetricName": "tma_info_dsb_switch_cost" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "tma_info_execute" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "tma_info_execute_per_issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_fb_hpki" + "MetricName": "tma_info_frontend_dsb_switch_cost" }, { "BriefDescription": "Average number of Uops issued by front-end when it issued something", "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", "MetricGroup": "Fed;FetchBW", - "MetricName": "tma_info_fetch_upc" + "MetricName": "tma_info_frontend_fetch_upc" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", - "MetricGroup": "Flops;Ret", - "MetricName": "tma_info_flopc" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_fp_arith_utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "tma_info_gflops", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" }, { - "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", - "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", - "MetricName": "tma_info_ic_misses", - "MetricThreshold": "tma_info_ic_misses > 5", - "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" }, { - "BriefDescription": "Average Latency for L1 instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", - "MetricGroup": "Fed;FetchLat;IcMiss", - "MetricName": "tma_info_icache_miss_latency" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "tma_info_ilp" + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_frontend_lsd_coverage" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "tma_info_instruction_fetch_bw", - "MetricThreshold": "tma_info_instruction_fetch_bw > 20" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" }, { "BriefDescription": "Total number of retired Instructions", "MetricExpr": "INST_RETIRED.ANY", "MetricGroup": "Summary;TmaL1;tma_L1_group", - "MetricName": "tma_info_instructions", + "MetricName": "tma_info_inst_mix_instructions", "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_iparith", - "MetricThreshold": "tma_info_iparith < 10", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx128", - "MetricThreshold": "tma_info_iparith_avx128 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx256", - "MetricThreshold": "tma_info_iparith_avx256 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "tma_info_iparith_avx512", - "MetricThreshold": "tma_info_iparith_avx512 < 10", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_dp", - "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "tma_info_iparith_scalar_sp", - "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "MetricName": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Branches;Fed;InsType", - "MetricName": "tma_info_ipbranch", - "MetricThreshold": "tma_info_ipbranch < 8" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", - "MetricGroup": "Ret;Summary", - "MetricName": "tma_info_ipc" + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" }, { "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", "MetricGroup": "Branches;Fed;PGO", - "MetricName": "tma_info_ipcall", - "MetricThreshold": "tma_info_ipcall < 200" - }, - { - "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "tma_info_ipdsb_miss_ret", - "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" - }, - { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "tma_info_ipfarbranch", - "MetricThreshold": "tma_info_ipfarbranch < 1e6" + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" }, { "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", "MetricGroup": "Flops;InsType", - "MetricName": "tma_info_ipflop", - "MetricThreshold": "tma_info_ipflop < 10" + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" }, { "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", "MetricGroup": "InsType", - "MetricName": "tma_info_ipload", - "MetricThreshold": "tma_info_ipload < 3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_ntaken", - "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_cond_taken", - "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" - }, - { - "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_indirect", - "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" - }, - { - "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "tma_info_ipmisp_ret", - "MetricThreshold": "tma_info_ipmisp_ret < 500" - }, - { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "tma_info_ipmispredict", - "MetricThreshold": "tma_info_ipmispredict < 200" + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" }, { "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", "MetricGroup": "InsType", - "MetricName": "tma_info_ipstore", - "MetricThreshold": "tma_info_ipstore < 8" + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" }, { "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", "MetricGroup": "Prefetches", - "MetricName": "tma_info_ipswpf", - "MetricThreshold": "tma_info_ipswpf < 100" + "MetricName": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", - "MetricName": "tma_info_iptb", - "MetricThreshold": "tma_info_iptb < 11", - "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", - "MetricExpr": "tma_info_instructions / BACLEARS.ANY", - "MetricGroup": "Fed", - "MetricName": "tma_info_ipunknown_branch" - }, - { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_jump" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_cpi" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "tma_info_kernel_utilization", - "MetricThreshold": "tma_info_kernel_utilization > 0.05" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw" + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "tma_info_l1d_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l1d_cache_fill_bw_1t" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki" + "MetricName": "tma_info_memory_l1mpki" }, { "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l1mpki_load" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw" - }, - { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "tma_info_l2_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l2_cache_fill_bw_1t" + "MetricName": "tma_info_memory_l1mpki_load" }, { "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_all" + "MetricName": "tma_info_memory_l2hpki_all" }, { "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2hpki_load" + "MetricName": "tma_info_memory_l2hpki_load" }, { "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "tma_info_l2mpki" + "MetricName": "tma_info_memory_l2mpki" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "tma_info_l2mpki_all" - }, - { - "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code" - }, - { - "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", - "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "IcMiss", - "MetricName": "tma_info_l2mpki_code_all" + "MetricName": "tma_info_memory_l2mpki_all" }, { "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l2mpki_load" - }, - { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw" + "MetricName": "tma_info_memory_l2mpki_load" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_access_bw", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "tma_info_l3_cache_access_bw_1t" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "tma_info_l3_cache_fill_bw", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "tma_info_l3_cache_fill_bw_1t" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "tma_info_l3mpki" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" }, { "BriefDescription": "Average Latency for L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l2_miss_latency" + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" }, { "BriefDescription": "Average Parallel L2 cache miss demand Loads", "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", "MetricGroup": "Memory_BW;Offcore", - "MetricName": "tma_info_load_l2_mlp" + "MetricName": "tma_info_memory_oro_load_l2_mlp" }, { "BriefDescription": "Average Latency for L3 cache miss demand Loads", "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "MetricGroup": "Memory_Lat;Offcore", - "MetricName": "tma_info_load_l3_miss_latency" + "MetricName": "tma_info_memory_oro_load_l3_miss_latency" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "tma_info_load_miss_real_latency" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" }, { "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_load_stlb_mpki" + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" }, { - "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", - "MetricGroup": "Fed;LSD", - "MetricName": "tma_info_lsd_coverage" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" }, { - "BriefDescription": "Average number of parallel data read requests to external memory", - "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "tma_info_mem_parallel_reads", - "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", - "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "tma_info_mem_read_latency", - "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / arb@event\\=0x81\\,umask\\=0x1@", - "MetricGroup": "Mem;SoC", - "MetricName": "tma_info_mem_request_latency" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", - "MetricName": "tma_info_memory_bandwidth", - "MetricThreshold": "tma_info_memory_bandwidth > 20", - "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", - "MetricName": "tma_info_memory_data_tlbs", - "MetricThreshold": "tma_info_memory_data_tlbs > 20", - "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", - "MetricName": "tma_info_memory_latency", - "MetricThreshold": "tma_info_memory_latency > 20", - "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", - "MetricName": "tma_info_mispredictions", - "MetricThreshold": "tma_info_mispredictions > 20", - "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "tma_info_mlp", - "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" }, { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "tma_info_other_branches" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_clks)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_page_walks_utilization", - "MetricThreshold": "tma_info_page_walks_utilization > 0.5" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / arb@event\\=0x81\\,umask\\=0x1@", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency" }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license0_utilization", + "MetricName": "tma_info_system_power_license0_utilization", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license1_utilization", - "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "MetricName": "tma_info_system_power_license1_utilization", + "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_core_clks", "MetricGroup": "Power", - "MetricName": "tma_info_power_license2_utilization", - "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "MetricName": "tma_info_system_power_license2_utilization", + "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "tma_info_retire" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_system_smt_2t_utilization" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "TmaL1;tma_L1_group", - "MetricName": "tma_info_slots" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization" }, { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;TmaL1;tma_L1_group", - "MetricName": "tma_info_slots_utilization" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "tma_info_smt_2t_utilization" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" }, { - "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", - "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "tma_info_store_stlb_mpki" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "tma_info_turbo_utilization" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization" }, { "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "tma_info_uoppi", - "MetricThreshold": "tma_info_uoppi > 1.05" + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "tma_info_uptb", - "MetricThreshold": "tma_info_uptb < 7.5" + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 7.5" }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_itlb_misses", "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1083,7 +1092,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1093,7 +1102,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1102,7 +1111,7 @@ }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1111,20 +1120,20 @@ }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17.5 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricExpr": "17.5 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", "MetricName": "tma_lcp", "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", "ScaleUnit": "100%" }, { @@ -1139,7 +1148,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_clks)", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_load_op_utilization", "MetricThreshold": "tma_load_op_utilization > 0.6", @@ -1156,7 +1165,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", "MetricName": "tma_load_stlb_miss", "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1165,7 +1174,7 @@ { "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks", "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", "MetricName": "tma_lock_latency", "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1174,10 +1183,10 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_lsd", - "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", "ScaleUnit": "100%" }, @@ -1193,20 +1202,20 @@ }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { @@ -1221,6 +1230,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_memory_operations", @@ -1229,7 +1239,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_retiring * tma_info_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricExpr": "tma_retiring * tma_info_thread_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", "MetricName": "tma_microcode_sequencer", "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", @@ -1238,28 +1248,28 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", "MetricName": "tma_mispredicts_resteers", "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_core_clks / 2", "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_mite", - "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "([email protected]_UOPS\\,cmask\\=4@ - [email protected]_UOPS\\,cmask\\=5@) / tma_info_clks", + "MetricExpr": "([email protected]_UOPS\\,cmask\\=4@ - [email protected]_UOPS\\,cmask\\=5@) / tma_info_thread_clks", "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", "MetricName": "tma_mite_4wide", - "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", "ScaleUnit": "100%" }, { @@ -1273,7 +1283,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks", "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", "MetricName": "tma_ms_switches", "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", @@ -1282,7 +1292,7 @@ }, { "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_nop_instructions", "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", @@ -1291,6 +1301,7 @@ }, { "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_other_light_ops", @@ -1300,7 +1311,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", "MetricThreshold": "tma_port_0 > 0.6", @@ -1309,7 +1320,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", "MetricThreshold": "tma_port_1 > 0.6", @@ -1318,7 +1329,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", "MetricThreshold": "tma_port_5 > 0.6", @@ -1327,7 +1338,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", "MetricThreshold": "tma_port_6 > 0.6", @@ -1336,7 +1347,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", @@ -1345,7 +1356,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1354,7 +1365,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1363,7 +1374,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1372,7 +1383,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", @@ -1381,7 +1392,7 @@ }, { "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", @@ -1391,7 +1402,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", "MetricName": "tma_serializing_operation", "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", @@ -1400,7 +1411,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_clks", + "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", "MetricName": "tma_slow_pause", "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", @@ -1409,7 +1420,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_split_loads", "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1418,7 +1429,7 @@ }, { "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", "MetricName": "tma_split_stores", "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1427,16 +1438,16 @@ }, { "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_clks", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", "MetricName": "tma_sq_full", "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -1445,7 +1456,7 @@ }, { "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", "MetricName": "tma_store_fwd_blk", "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1454,7 +1465,7 @@ }, { "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", "MetricName": "tma_store_latency", "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1463,7 +1474,7 @@ }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_core_clks)", "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", "MetricName": "tma_store_op_utilization", "MetricThreshold": "tma_store_op_utilization > 0.6", @@ -1480,7 +1491,7 @@ }, { "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks", "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", "MetricName": "tma_store_stlb_miss", "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", @@ -1488,7 +1499,7 @@ }, { "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks", "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", "MetricName": "tma_streaming_stores", "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", @@ -1497,7 +1508,7 @@ }, { "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "10 * BACLEARS.ANY / tma_info_clks", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", "MetricName": "tma_unknown_branches", "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index e74defb5284f..a630c617e879 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -420,3 +420,8 @@ int pmu_for_each_sys_metric(pmu_metric_iter_fn fn __maybe_unused, void *data __m { return 0; } + +const char *describe_metricgroup(const char *group __maybe_unused) +{ + return NULL; +} diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index f57a8f274025..7ed258be1829 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -37,6 +37,8 @@ _pending_metrics = [] _pending_metrics_tblname = None # Global BigCString shared by all structures. _bcs = None +# Map from the name of a metric group to a description of the group. +_metricgroups = {} # Order specific JsonEvent attributes will be visited. _json_event_attributes = [ # cmp_sevent related attributes. @@ -51,8 +53,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ - 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'pmu', 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', + 'desc', 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... @@ -391,11 +393,11 @@ def read_json_events(path: str, topic: str) -> Sequence[JsonEvent]: except BaseException as err: print(f"Exception processing {path}") raise - metrics: list[Tuple[str, metric.Expression]] = [] + metrics: list[Tuple[str, str, metric.Expression]] = [] for event in events: event.topic = topic if event.metric_name and '-' not in event.metric_name: - metrics.append((event.metric_name, event.metric_expr)) + metrics.append((event.pmu, event.metric_name, event.metric_expr)) updates = metric.RewriteMetricsInTermsOfOthers(metrics) if updates: for event in events: @@ -512,6 +514,17 @@ def preprocess_one_file(parents: Sequence[str], item: os.DirEntry) -> None: if not item.is_file() or not item.name.endswith('.json'): return + if item.name == 'metricgroups.json': + metricgroup_descriptions = json.load(open(item.path)) + for mgroup in metricgroup_descriptions: + assert len(mgroup) > 1, parents + description = f"{metricgroup_descriptions[mgroup]}\\000" + mgroup = f"{mgroup}\\000" + _bcs.add(mgroup) + _bcs.add(description) + _metricgroups[mgroup] = description + return + topic = get_topic(item.name) for event in read_json_events(item.path, topic): if event.name: @@ -548,7 +561,7 @@ def process_one_file(parents: Sequence[str], item: os.DirEntry) -> None: # Ignore other directories. If the file name does not have a .json # extension, ignore it. It could be a readme.txt for instance. - if not item.is_file() or not item.name.endswith('.json'): + if not item.is_file() or not item.name.endswith('.json') or item.name == 'metricgroups.json': return add_events_table_entries(item, get_topic(item.name)) @@ -911,6 +924,38 @@ int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data) } """) +def print_metricgroups() -> None: + _args.output_file.write(""" +static const int metricgroups[][2] = { +""") + for mgroup in sorted(_metricgroups): + description = _metricgroups[mgroup] + _args.output_file.write( + f'\t{{ {_bcs.offsets[mgroup]}, {_bcs.offsets[description]} }}, /* {mgroup} => {description} */\n' + ) + _args.output_file.write(""" +}; + +const char *describe_metricgroup(const char *group) +{ + int low = 0, high = (int)ARRAY_SIZE(metricgroups) - 1; + + while (low <= high) { + int mid = (low + high) / 2; + const char *mgroup = &big_c_string[metricgroups[mid][0]]; + int cmp = strcmp(mgroup, group); + + if (cmp == 0) { + return &big_c_string[metricgroups[mid][1]]; + } else if (cmp < 0) { + low = mid + 1; + } else { + high = mid - 1; + } + } + return NULL; +} +""") def main() -> None: global _args @@ -993,7 +1038,7 @@ struct compact_pmu_event { print_mapping_table(archs) print_system_mapping_table() - + print_metricgroups() if __name__ == '__main__': main() diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 8ec0ba884673..af58b74d1644 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -552,28 +552,34 @@ def ParsePerfJson(orig: str) -> Expression: return _Constify(eval(compile(parsed, orig, 'eval'))) -def RewriteMetricsInTermsOfOthers(metrics: List[Tuple[str, Expression]] - )-> Dict[str, Expression]: +def RewriteMetricsInTermsOfOthers(metrics: List[Tuple[str, str, Expression]] + )-> Dict[Tuple[str, str], Expression]: """Shorten metrics by rewriting in terms of others. Args: - metrics (list): pairs of metric names and their expressions. + metrics (list): pmus, metric names and their expressions. Returns: - Dict: mapping from a metric name to a shortened expression. + Dict: mapping from a pmu, metric name pair to a shortened expression. """ - updates: Dict[str, Expression] = dict() - for outer_name, outer_expression in metrics: + updates: Dict[Tuple[str, str], Expression] = dict() + for outer_pmu, outer_name, outer_expression in metrics: + if outer_pmu is None: + outer_pmu = 'cpu' updated = outer_expression while True: - for inner_name, inner_expression in metrics: + for inner_pmu, inner_name, inner_expression in metrics: + if inner_pmu is None: + inner_pmu = 'cpu' + if inner_pmu.lower() != outer_pmu.lower(): + continue if inner_name.lower() == outer_name.lower(): continue - if inner_name in updates: - inner_expression = updates[inner_name] + if (inner_pmu, inner_name) in updates: + inner_expression = updates[(inner_pmu, inner_name)] updated = updated.Substitute(inner_name, inner_expression) if updated.Equals(outer_expression): break - if outer_name in updates and updated.Equals(updates[outer_name]): + if (outer_pmu, outer_name) in updates and updated.Equals(updates[(outer_pmu, outer_name)]): break - updates[outer_name] = updated + updates[(outer_pmu, outer_name)] = updated return updates diff --git a/tools/perf/pmu-events/metric_test.py b/tools/perf/pmu-events/metric_test.py index 40a3c7d8b2bc..ee22ff43ddd7 100755 --- a/tools/perf/pmu-events/metric_test.py +++ b/tools/perf/pmu-events/metric_test.py @@ -158,9 +158,9 @@ class TestMetricExpressions(unittest.TestCase): def test_RewriteMetricsInTermsOfOthers(self): Expression.__eq__ = lambda e1, e2: e1.Equals(e2) - before = [('m1', ParsePerfJson('a + b + c + d')), - ('m2', ParsePerfJson('a + b + c'))] - after = {'m1': ParsePerfJson('m2 + d')} + before = [('cpu', 'm1', ParsePerfJson('a + b + c + d')), + ('cpu', 'm2', ParsePerfJson('a + b + c'))] + after = {('cpu', 'm1'): ParsePerfJson('m2 + d')} self.assertEqual(RewriteMetricsInTermsOfOthers(before), after) Expression.__eq__ = None diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 80349685cf4d..8cd23d656a5d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -51,6 +51,7 @@ struct pmu_event { }; struct pmu_metric { + const char *pmu; const char *metric_name; const char *metric_group; const char *metric_expr; @@ -92,4 +93,6 @@ const struct pmu_metrics_table *find_sys_metrics_table(const char *name); int pmu_for_each_sys_event(pmu_event_iter_fn fn, void *data); int pmu_for_each_sys_metric(pmu_metric_iter_fn fn, void *data); +const char *describe_metricgroup(const char *group); + #endif diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 56fba08a3037..61186d0d1cfa 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -34,7 +34,7 @@ #include "event.h" #include "util.h" #include "tests.h" -#include "pmu.h" +#include "pmus.h" #define ENV "PERF_TEST_ATTR" @@ -185,8 +185,15 @@ static int test__attr(struct test_suite *test __maybe_unused, int subtest __mayb char path_dir[PATH_MAX]; char *exec_path; - if (perf_pmu__has_hybrid()) + if (perf_pmus__num_core_pmus() > 1) { + /* + * TODO: Attribute tests hard code the PMU type. If there are >1 + * core PMU then each PMU will have a different type whic + * requires additional support. + */ + pr_debug("Skip test on hybrid systems"); return TEST_SKIP; + } /* First try development tree tests. */ if (!lstat("./tests", &st)) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index b89d69afcef0..aa44fdc84763 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -88,15 +88,13 @@ static struct test_suite *generic_tests[] = { &suite__bpf, &suite__thread_map_synthesize, &suite__thread_map_remove, - &suite__cpu_map_synthesize, + &suite__cpu_map, &suite__synthesize_stat_config, &suite__synthesize_stat, &suite__synthesize_stat_round, &suite__event_update, &suite__event_times, &suite__backward_ring_buffer, - &suite__cpu_map_print, - &suite__cpu_map_merge, &suite__sdt_event, &suite__is_printable_array, &suite__bitmap_print, diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index b1a924314e09..7730fc2ab40b 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -171,6 +171,92 @@ static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subte return 0; } -DEFINE_SUITE("Synthesize cpu map", cpu_map_synthesize); -DEFINE_SUITE("Print cpu map", cpu_map_print); -DEFINE_SUITE("Merge cpu map", cpu_map_merge); +static int __test__cpu_map_intersect(const char *lhs, const char *rhs, int nr, const char *expected) +{ + struct perf_cpu_map *a = perf_cpu_map__new(lhs); + struct perf_cpu_map *b = perf_cpu_map__new(rhs); + struct perf_cpu_map *c = perf_cpu_map__intersect(a, b); + char buf[100]; + + TEST_ASSERT_EQUAL("failed to intersect map: bad nr", perf_cpu_map__nr(c), nr); + cpu_map__snprint(c, buf, sizeof(buf)); + TEST_ASSERT_VAL("failed to intersect map: bad result", !strcmp(buf, expected)); + perf_cpu_map__put(a); + perf_cpu_map__put(b); + perf_cpu_map__put(c); + return 0; +} + +static int test__cpu_map_intersect(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + int ret; + + ret = __test__cpu_map_intersect("4,2,1", "4,5,7", 1, "4"); + if (ret) + return ret; + ret = __test__cpu_map_intersect("1-8", "6-9", 3, "6-8"); + if (ret) + return ret; + ret = __test__cpu_map_intersect("1-8,12-20", "6-9,15", 4, "6-8,15"); + if (ret) + return ret; + ret = __test__cpu_map_intersect("4,2,1", "1", 1, "1"); + if (ret) + return ret; + ret = __test__cpu_map_intersect("1", "4,2,1", 1, "1"); + if (ret) + return ret; + ret = __test__cpu_map_intersect("1", "1", 1, "1"); + return ret; +} + +static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subtest __maybe_unused) +{ + struct perf_cpu_map *any = perf_cpu_map__dummy_new(); + struct perf_cpu_map *one = perf_cpu_map__new("1"); + struct perf_cpu_map *two = perf_cpu_map__new("2"); + struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two); + struct perf_cpu_map *pair = perf_cpu_map__new("1-2"); + struct perf_cpu_map *tmp; + struct perf_cpu_map *maps[] = {empty, any, one, two, pair}; + + for (size_t i = 0; i < ARRAY_SIZE(maps); i++) { + /* Maps equal themself. */ + TEST_ASSERT_VAL("equal", perf_cpu_map__equal(maps[i], maps[i])); + for (size_t j = 0; j < ARRAY_SIZE(maps); j++) { + /* Maps dont't equal each other. */ + if (i == j) + continue; + TEST_ASSERT_VAL("not equal", !perf_cpu_map__equal(maps[i], maps[j])); + } + } + + /* Maps equal made maps. */ + tmp = perf_cpu_map__merge(perf_cpu_map__get(one), two); + TEST_ASSERT_VAL("pair", perf_cpu_map__equal(pair, tmp)); + perf_cpu_map__put(tmp); + + tmp = perf_cpu_map__intersect(pair, one); + TEST_ASSERT_VAL("one", perf_cpu_map__equal(one, tmp)); + perf_cpu_map__put(tmp); + + for (size_t i = 0; i < ARRAY_SIZE(maps); i++) + perf_cpu_map__put(maps[i]); + + return TEST_OK; +} + +static struct test_case tests__cpu_map[] = { + TEST_CASE("Synthesize cpu map", cpu_map_synthesize), + TEST_CASE("Print cpu map", cpu_map_print), + TEST_CASE("Merge cpu map", cpu_map_merge), + TEST_CASE("Intersect cpu map", cpu_map_intersect), + TEST_CASE("Equal cpu map", cpu_map_equal), + { .name = NULL, } +}; + +struct test_suite suite__cpu_map = { + .desc = "CPU map", + .test_cases = tests__cpu_map, +}; diff --git a/tools/perf/tests/event_groups.c b/tools/perf/tests/event_groups.c index 029442b4e9c6..ccd9d8b2903f 100644 --- a/tools/perf/tests/event_groups.c +++ b/tools/perf/tests/event_groups.c @@ -50,13 +50,10 @@ static int event_open(int type, unsigned long config, int group_fd) static int setup_uncore_event(void) { - struct perf_pmu *pmu; + struct perf_pmu *pmu = NULL; int i, fd; - if (list_empty(&pmus)) - perf_pmu__scan(NULL); - - perf_pmus__for_each_pmu(pmu) { + while ((pmu = perf_pmus__scan(pmu)) != NULL) { for (i = 0; i < NR_UNCORE_PMUS; i++) { if (!strcmp(uncore_pmus[i].name, pmu->name)) { pr_debug("Using %s for uncore pmu event\n", pmu->name); diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index e94fed901992..15ff86f9da0b 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -4,114 +4,93 @@ #include "parse-events.h" #include "tests.h" #include "debug.h" -#include "pmu.h" -#include "pmu-hybrid.h" -#include <errno.h> #include <linux/kernel.h> static int perf_evsel__roundtrip_cache_name_test(void) { - char name[128]; - int type, op, err = 0, ret = 0, i, idx; - struct evsel *evsel; - struct evlist *evlist = evlist__new(); + int ret = TEST_OK; - if (evlist == NULL) - return -ENOMEM; - - for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + for (int type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (int op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { /* skip invalid cache type */ if (!evsel__is_cache_op_valid(type, op)) continue; - for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); - err = parse_event(evlist, name); - if (err) - ret = err; - } - } - } - - idx = 0; - evsel = evlist__first(evlist); + for (int res = 0; res < PERF_COUNT_HW_CACHE_RESULT_MAX; res++) { + char name[128]; + struct evlist *evlist = evlist__new(); + struct evsel *evsel; + int err; - for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { - /* skip invalid cache type */ - if (!evsel__is_cache_op_valid(type, op)) - continue; + if (evlist == NULL) { + pr_debug("Failed to alloc evlist"); + return TEST_FAIL; + } + __evsel__hw_cache_type_op_res_name(type, op, res, + name, sizeof(name)); - for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); - if (evsel->core.idx != idx) + err = parse_event(evlist, name); + if (err) { + pr_debug("Failure to parse cache event '%s' possibly as PMUs don't support it", + name); + evlist__delete(evlist); continue; - - ++idx; - - if (strcmp(evsel__name(evsel), name)) { - pr_debug("%s != %s\n", evsel__name(evsel), name); - ret = -1; } - - evsel = evsel__next(evsel); + evlist__for_each_entry(evlist, evsel) { + if (strcmp(evsel__name(evsel), name)) { + pr_debug("%s != %s\n", evsel__name(evsel), name); + ret = TEST_FAIL; + } + } + evlist__delete(evlist); } } } - - evlist__delete(evlist); return ret; } -static int __perf_evsel__name_array_test(const char *const names[], int nr_names, - int distance) +static int perf_evsel__name_array_test(const char *const names[], int nr_names) { - int i, err; - struct evsel *evsel; - struct evlist *evlist = evlist__new(); + int ret = TEST_OK; - if (evlist == NULL) - return -ENOMEM; + for (int i = 0; i < nr_names; ++i) { + struct evlist *evlist = evlist__new(); + struct evsel *evsel; + int err; - for (i = 0; i < nr_names; ++i) { + if (evlist == NULL) { + pr_debug("Failed to alloc evlist"); + return TEST_FAIL; + } err = parse_event(evlist, names[i]); if (err) { pr_debug("failed to parse event '%s', err %d\n", names[i], err); - goto out_delete_evlist; + evlist__delete(evlist); + ret = TEST_FAIL; + continue; } - } - - err = 0; - evlist__for_each_entry(evlist, evsel) { - if (strcmp(evsel__name(evsel), names[evsel->core.idx / distance])) { - --err; - pr_debug("%s != %s\n", evsel__name(evsel), names[evsel->core.idx / distance]); + evlist__for_each_entry(evlist, evsel) { + if (strcmp(evsel__name(evsel), names[i])) { + pr_debug("%s != %s\n", evsel__name(evsel), names[i]); + ret = TEST_FAIL; + } } + evlist__delete(evlist); } - -out_delete_evlist: - evlist__delete(evlist); - return err; + return ret; } -#define perf_evsel__name_array_test(names, distance) \ - __perf_evsel__name_array_test(names, ARRAY_SIZE(names), distance) - static int test__perf_evsel__roundtrip_name_test(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - int err = 0, ret = 0; - - if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) - return perf_evsel__name_array_test(evsel__hw_names, 2); + int err = 0, ret = TEST_OK; - err = perf_evsel__name_array_test(evsel__hw_names, 1); + err = perf_evsel__name_array_test(evsel__hw_names, PERF_COUNT_HW_MAX); if (err) ret = err; - err = __perf_evsel__name_array_test(evsel__sw_names, PERF_COUNT_SW_DUMMY + 1, 1); + err = perf_evsel__name_array_test(evsel__sw_names, PERF_COUNT_SW_DUMMY + 1); if (err) ret = err; diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 8068cfd89b84..9d05bc551791 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -6,7 +6,7 @@ #include "tests.h" #include "debug.h" #include "pmu.h" -#include "pmu-hybrid.h" +#include "pmus.h" #include <dirent.h> #include <errno.h> #include "fncache.h" @@ -20,6 +20,26 @@ #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) +static bool test_config(const struct evsel *evsel, __u64 expected_config) +{ + __u32 type = evsel->core.attr.type; + __u64 config = evsel->core.attr.config; + + if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE) { + /* + * HARDWARE and HW_CACHE events encode the PMU's extended type + * in the top 32-bits. Mask in order to ignore. + */ + config &= PERF_HW_EVENT_MASK; + } + return config == expected_config; +} + +static bool test_perf_config(const struct perf_evsel *evsel, __u64 expected_config) +{ + return (evsel->attr.config & PERF_HW_EVENT_MASK) == expected_config; +} + #ifdef HAVE_LIBTRACEEVENT #if defined(__s390x__) @@ -82,11 +102,27 @@ static int test__checkevent_tracepoint_multi(struct evlist *evlist) static int test__checkevent_raw(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); + struct perf_evsel *evsel; + bool raw_type_match = false; - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries); + + perf_evlist__for_each_evsel(&evlist->core, evsel) { + struct perf_pmu *pmu = NULL; + bool type_matched = false; + + TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, 0x1a)); + while ((pmu = perf_pmus__scan(pmu)) != NULL) { + if (pmu->type == evsel->attr.type) { + TEST_ASSERT_VAL("PMU type expected once", !type_matched); + type_matched = true; + if (pmu->type == PERF_TYPE_RAW) + raw_type_match = true; + } + } + TEST_ASSERT_VAL("No PMU found for type", type_matched); + } + TEST_ASSERT_VAL("Raw PMU not matched", raw_type_match); return TEST_OK; } @@ -96,39 +132,41 @@ static int test__checkevent_numeric(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 1)); return TEST_OK; } static int test__checkevent_symbolic_name(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); + struct perf_evsel *evsel; - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries); + + perf_evlist__for_each_evsel(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + test_perf_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + } return TEST_OK; } static int test__checkevent_symbolic_name_config(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); + struct perf_evsel *evsel; - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); - /* - * The period value gets configured within evlist__config, - * while this test executes only parse events method. - */ - TEST_ASSERT_VAL("wrong period", - 0 == evsel->core.attr.sample_period); - TEST_ASSERT_VAL("wrong config1", - 0 == evsel->core.attr.config1); - TEST_ASSERT_VAL("wrong config2", - 1 == evsel->core.attr.config2); + TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries); + + perf_evlist__for_each_evsel(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + /* + * The period value gets configured within evlist__config, + * while this test executes only parse events method. + */ + TEST_ASSERT_VAL("wrong period", 0 == evsel->attr.sample_period); + TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1); + TEST_ASSERT_VAL("wrong config2", 1 == evsel->attr.config2); + } return TEST_OK; } @@ -138,18 +176,20 @@ static int test__checkevent_symbolic_alias(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_SW_PAGE_FAULTS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_SW_PAGE_FAULTS)); return TEST_OK; } static int test__checkevent_genhw(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); + struct perf_evsel *evsel; - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", (1 << 16) == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries); + + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, 1 << 16)); + } return TEST_OK; } @@ -159,7 +199,7 @@ static int test__checkevent_breakpoint(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_4 == @@ -173,7 +213,7 @@ static int test__checkevent_breakpoint_x(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_X == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", sizeof(long) == evsel->core.attr.bp_len); @@ -187,7 +227,7 @@ static int test__checkevent_breakpoint_r(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_R == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", @@ -202,7 +242,7 @@ static int test__checkevent_breakpoint_w(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", @@ -217,7 +257,7 @@ static int test__checkevent_breakpoint_rw(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", @@ -241,17 +281,15 @@ static int test__checkevent_tracepoint_modifier(struct evlist *evlist) static int test__checkevent_tracepoint_multi_modifier(struct evlist *evlist) { - struct evsel *evsel; + struct perf_evsel *evsel; TEST_ASSERT_VAL("wrong number of entries", evlist->core.nr_entries > 1); - evlist__for_each_entry(evlist, evsel) { - TEST_ASSERT_VAL("wrong exclude_user", - !evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", - evsel->core.attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); } return test__checkevent_tracepoint_multi(evlist); @@ -260,25 +298,27 @@ test__checkevent_tracepoint_multi_modifier(struct evlist *evlist) static int test__checkevent_raw_modifier(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); + struct perf_evsel *evsel; + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + } return test__checkevent_raw(evlist); } static int test__checkevent_numeric_modifier(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); + struct perf_evsel *evsel; + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + } return test__checkevent_numeric(evlist); } @@ -296,21 +336,23 @@ static int test__checkevent_symbolic_name_modifier(struct evlist *evlist) static int test__checkevent_exclude_host_modifier(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", evsel->core.attr.exclude_host); + struct perf_evsel *evsel; + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + } return test__checkevent_symbolic_name(evlist); } static int test__checkevent_exclude_guest_modifier(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); - TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); + struct perf_evsel *evsel; + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + } return test__checkevent_symbolic_name(evlist); } @@ -328,13 +370,14 @@ static int test__checkevent_symbolic_alias_modifier(struct evlist *evlist) static int test__checkevent_genhw_modifier(struct evlist *evlist) { - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip); + struct perf_evsel *evsel; + perf_evlist__for_each_entry(&evlist->core, evsel) { + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + } return test__checkevent_genhw(evlist); } @@ -446,7 +489,7 @@ static int test__checkevent_pmu(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 10 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 10)); TEST_ASSERT_VAL("wrong config1", 1 == evsel->core.attr.config1); TEST_ASSERT_VAL("wrong config2", 3 == evsel->core.attr.config2); TEST_ASSERT_VAL("wrong config3", 0 == evsel->core.attr.config3); @@ -464,21 +507,23 @@ static int test__checkevent_list(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); + TEST_ASSERT_VAL("wrong number of entries", 3 <= evlist->core.nr_entries); /* r1 */ - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong config1", 0 == evsel->core.attr.config1); - TEST_ASSERT_VAL("wrong config2", 0 == evsel->core.attr.config2); - TEST_ASSERT_VAL("wrong config3", 0 == evsel->core.attr.config3); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); - TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT != evsel->core.attr.type); + while (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) { + TEST_ASSERT_VAL("wrong config", test_config(evsel, 1)); + TEST_ASSERT_VAL("wrong config1", 0 == evsel->core.attr.config1); + TEST_ASSERT_VAL("wrong config2", 0 == evsel->core.attr.config2); + TEST_ASSERT_VAL("wrong config3", 0 == evsel->core.attr.config3); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); + evsel = evsel__next(evsel); + } /* syscalls:sys_enter_openat:k */ - evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); @@ -491,7 +536,7 @@ static int test__checkevent_list(struct evlist *evlist) /* 1:1:hp */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 1)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -508,14 +553,14 @@ static int test__checkevent_pmu_name(struct evlist *evlist) /* cpu/config=1,name=krava/u */ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 1)); TEST_ASSERT_VAL("wrong name", !strcmp(evsel__name(evsel), "krava")); /* cpu/config=2/u" */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 2 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 2)); TEST_ASSERT_VAL("wrong name", !strcmp(evsel__name(evsel), "cpu/config=2/u")); @@ -529,7 +574,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) /* cpu/config=1,call-graph=fp,time,period=100000/ */ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 1)); /* * The period, time and callgraph value gets configured within evlist__config, * while this test executes only parse events method. @@ -541,7 +586,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) /* cpu/config=2,call-graph=no,time=0,period=2000/ */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 2 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 2)); /* * The period, time and callgraph value gets configured within evlist__config, * while this test executes only parse events method. @@ -558,7 +603,8 @@ static int test__checkevent_pmu_events(struct evlist *evlist) struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type || + strcmp(evsel->pmu_name, "cpu")); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", @@ -590,7 +636,8 @@ static int test__checkevent_pmu_events_mix(struct evlist *evlist) /* cpu/pmu-event/u*/ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type || + strcmp(evsel->pmu_name, "cpu")); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", @@ -661,11 +708,11 @@ static int test__checkterms_simple(struct list_head *terms) */ term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", - term->type_term == PARSE_EVENTS__TERM_TYPE_USER); + term->type_term == PARSE_EVENTS__TERM_TYPE_RAW); TEST_ASSERT_VAL("wrong type val", - term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); - TEST_ASSERT_VAL("wrong val", term->val.num == 1); - TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "read")); + term->type_val == PARSE_EVENTS__TERM_TYPE_STR); + TEST_ASSERT_VAL("wrong val", !strcmp(term->val.str, "read")); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "raw")); /* * r0xead @@ -675,11 +722,11 @@ static int test__checkterms_simple(struct list_head *terms) */ term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", - term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG); + term->type_term == PARSE_EVENTS__TERM_TYPE_RAW); TEST_ASSERT_VAL("wrong type val", - term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); - TEST_ASSERT_VAL("wrong val", term->val.num == 0xead); - TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config")); + term->type_val == PARSE_EVENTS__TERM_TYPE_STR); + TEST_ASSERT_VAL("wrong val", !strcmp(term->val.str, "r0xead")); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "raw")); return TEST_OK; } @@ -693,8 +740,7 @@ static int test__group1(struct evlist *evlist) /* instructions:k */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -709,8 +755,7 @@ static int test__group1(struct evlist *evlist) /* cycles:upp */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -735,8 +780,7 @@ static int test__group2(struct evlist *evlist) /* faults + :ku modifier */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_SW_PAGE_FAULTS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_SW_PAGE_FAULTS)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -751,8 +795,7 @@ static int test__group2(struct evlist *evlist) /* cache-references + :u modifier */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_REFERENCES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_REFERENCES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -766,8 +809,7 @@ static int test__group2(struct evlist *evlist) /* cycles:k */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -810,8 +852,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) /* group1 cycles:kppp */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -827,8 +868,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) /* group2 cycles + G modifier */ evsel = leader = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -845,7 +885,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) /* group2 1:3 + G modifier */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", 1 == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 3 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 3)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -859,8 +899,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) /* instructions:u */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -884,8 +923,7 @@ static int test__group4(struct evlist *evlist __maybe_unused) /* cycles:u + p */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -902,8 +940,7 @@ static int test__group4(struct evlist *evlist __maybe_unused) /* instructions:kp + p */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -928,8 +965,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* cycles + G */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -945,8 +981,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* instructions + G */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -960,8 +995,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* cycles:G */ evsel = leader = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -977,8 +1011,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* instructions:G */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -991,8 +1024,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* cycles */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1014,8 +1046,7 @@ static int test__group_gh1(struct evlist *evlist) /* cycles + :H group modifier */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1030,8 +1061,7 @@ static int test__group_gh1(struct evlist *evlist) /* cache-misses:G + :H group modifier */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1054,8 +1084,7 @@ static int test__group_gh2(struct evlist *evlist) /* cycles + :G group modifier */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1070,8 +1099,7 @@ static int test__group_gh2(struct evlist *evlist) /* cache-misses:H + :G group modifier */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1094,8 +1122,7 @@ static int test__group_gh3(struct evlist *evlist) /* cycles:G + :u group modifier */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1110,8 +1137,7 @@ static int test__group_gh3(struct evlist *evlist) /* cache-misses:H + :u group modifier */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1134,8 +1160,7 @@ static int test__group_gh4(struct evlist *evlist) /* cycles:G + :uG group modifier */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1150,8 +1175,7 @@ static int test__group_gh4(struct evlist *evlist) /* cache-misses:H + :uG group modifier */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1173,8 +1197,7 @@ static int test__leader_sample1(struct evlist *evlist) /* cycles - sampling group leader */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1188,8 +1211,7 @@ static int test__leader_sample1(struct evlist *evlist) /* cache-misses - not sampling */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1202,8 +1224,7 @@ static int test__leader_sample1(struct evlist *evlist) /* branch-misses - not sampling */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1226,8 +1247,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused) /* instructions - sampling group leader */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_INSTRUCTIONS == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1241,8 +1261,7 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused) /* branch-misses - not sampling */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1278,8 +1297,7 @@ static int test__pinned_group(struct evlist *evlist) /* cycles - group leader */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); TEST_ASSERT_VAL("wrong pinned", evsel->core.attr.pinned); @@ -1287,14 +1305,12 @@ static int test__pinned_group(struct evlist *evlist) /* cache-misses - can not be pinned, but will go on with the leader */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); /* branch-misses - ditto */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); return TEST_OK; @@ -1322,8 +1338,7 @@ static int test__exclusive_group(struct evlist *evlist) /* cycles - group leader */ evsel = leader = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); TEST_ASSERT_VAL("wrong exclusive", evsel->core.attr.exclusive); @@ -1331,14 +1346,12 @@ static int test__exclusive_group(struct evlist *evlist) /* cache-misses - can not be pinned, but will go on with the leader */ evsel = evsel__next(evsel); TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_CACHE_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); /* branch-misses - ditto */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_HW_BRANCH_MISSES == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); return TEST_OK; @@ -1349,7 +1362,7 @@ static int test__checkevent_breakpoint_len(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", (HW_BREAKPOINT_R | HW_BREAKPOINT_W) == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_1 == @@ -1364,7 +1377,7 @@ static int test__checkevent_breakpoint_len_w(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0 == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0)); TEST_ASSERT_VAL("wrong bp_type", HW_BREAKPOINT_W == evsel->core.attr.bp_type); TEST_ASSERT_VAL("wrong bp_len", HW_BREAKPOINT_LEN_2 == @@ -1392,8 +1405,7 @@ static int test__checkevent_precise_max_modifier(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", - PERF_COUNT_SW_TASK_CLOCK == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_SW_TASK_CLOCK)); return TEST_OK; } @@ -1426,12 +1438,17 @@ static int test__checkevent_config_cache(struct evlist *evlist) struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "cachepmu")); - return TEST_OK; + return test__checkevent_genhw(evlist); +} + +static bool test__pmu_cpu_valid(void) +{ + return !!perf_pmus__find("cpu"); } static bool test__intel_pt_valid(void) { - return !!perf_pmu__find("intel_pt"); + return !!perf_pmus__find("intel_pt"); } static int test__intel_pt(struct evlist *evlist) @@ -1446,7 +1463,9 @@ static int test__checkevent_complex_name(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong complex name parsing", evsel__name_is(evsel, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks")); + TEST_ASSERT_VAL("wrong complex name parsing", + evsel__name_is(evsel, + "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks")); return TEST_OK; } @@ -1456,7 +1475,7 @@ static int test__checkevent_raw_pmu(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); + TEST_ASSERT_VAL("wrong config", test_config(evsel, 0x1a)); return TEST_OK; } @@ -1465,7 +1484,7 @@ static int test__sym_event_slash(struct evlist *evlist) struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); return TEST_OK; } @@ -1475,11 +1494,31 @@ static int test__sym_event_dc(struct evlist *evlist) struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); return TEST_OK; } +static int test__term_equal_term(struct evlist *evlist) +{ + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "name") == 0); + return TEST_OK; +} + +static int test__term_equal_legacy(struct evlist *evlist) +{ + struct evsel *evsel = evlist__first(evlist); + + TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); + TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "l1d") == 0); + return TEST_OK; +} + #ifdef HAVE_LIBTRACEEVENT static int count_tracepoints(void) { @@ -1536,127 +1575,6 @@ static int test__all_tracepoints(struct evlist *evlist) } #endif /* HAVE_LIBTRACEVENT */ -static int test__hybrid_hw_event_with_pmu(struct evlist *evlist) -{ - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x3c == evsel->core.attr.config); - return TEST_OK; -} - -static int test__hybrid_hw_group_event(struct evlist *evlist) -{ - struct evsel *evsel, *leader; - - evsel = leader = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x3c == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0xc0 == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - return TEST_OK; -} - -static int test__hybrid_sw_hw_group_event(struct evlist *evlist) -{ - struct evsel *evsel, *leader; - - evsel = leader = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x3c == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - return TEST_OK; -} - -static int test__hybrid_hw_sw_group_event(struct evlist *evlist) -{ - struct evsel *evsel, *leader; - - evsel = leader = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x3c == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - return TEST_OK; -} - -static int test__hybrid_group_modifier1(struct evlist *evlist) -{ - struct evsel *evsel, *leader; - - evsel = leader = evlist__first(evlist); - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x3c == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); - - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0xc0 == evsel->core.attr.config); - TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); - TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); - TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); - return TEST_OK; -} - -static int test__hybrid_raw1(struct evlist *evlist) -{ - struct evsel *evsel = evlist__first(evlist); - - if (!perf_pmu__hybrid_mounted("cpu_atom")) { - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); - return TEST_OK; - } - - TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); - - /* The type of second event is randome value */ - evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); - return TEST_OK; -} - -static int test__hybrid_raw2(struct evlist *evlist) -{ - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config); - return TEST_OK; -} - -static int test__hybrid_cache_event(struct evlist *evlist) -{ - struct evsel *evsel = evlist__first(evlist); - - TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff)); - return TEST_OK; -} - struct evlist_test { const char *name; bool (*valid)(void); @@ -1973,26 +1891,40 @@ static const struct evlist_test test__events[] = { .check = test__exclusive_group, /* 7 */ }, + { + .name = "cycles/name=name/", + .check = test__term_equal_term, + /* 8 */ + }, + { + .name = "cycles/name=l1d/", + .check = test__term_equal_legacy, + /* 9 */ + }, }; static const struct evlist_test test__events_pmu[] = { { .name = "cpu/config=10,config1,config2=3,period=1000/u", + .valid = test__pmu_cpu_valid, .check = test__checkevent_pmu, /* 0 */ }, { .name = "cpu/config=1,name=krava/u,cpu/config=2/u", + .valid = test__pmu_cpu_valid, .check = test__checkevent_pmu_name, /* 1 */ }, { .name = "cpu/config=1,call-graph=fp,time,period=100000/,cpu/config=2,call-graph=no,time=0,period=2000/", + .valid = test__pmu_cpu_valid, .check = test__checkevent_pmu_partial_time_callgraph, /* 2 */ }, { .name = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp", + .valid = test__pmu_cpu_valid, .check = test__checkevent_complex_name, /* 3 */ }, @@ -2006,66 +1938,174 @@ static const struct evlist_test test__events_pmu[] = { .check = test__checkevent_raw_pmu, /* 5 */ }, -}; - -struct terms_test { - const char *str; - int (*check)(struct list_head *terms); -}; - -static const struct terms_test test__terms[] = { - [0] = { - .str = "config=10,config1,config2=3,config3=4,umask=1,read,r0xead", - .check = test__checkterms_simple, + { + .name = "cpu/L1-dcache-load-miss/", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_genhw, + /* 6 */ + }, + { + .name = "cpu/L1-dcache-load-miss/kp", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_genhw_modifier, + /* 7 */ + }, + { + .name = "cpu/L1-dcache-misses,name=cachepmu/", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_config_cache, + /* 8 */ + }, + { + .name = "cpu/instructions/", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_symbolic_name, + /* 9 */ }, -}; - -static const struct evlist_test test__hybrid_events[] = { { - .name = "cpu_core/cpu-cycles/", - .check = test__hybrid_hw_event_with_pmu, + .name = "cpu/cycles,period=100000,config2/", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_symbolic_name_config, /* 0 */ }, { - .name = "{cpu_core/cpu-cycles/,cpu_core/instructions/}", - .check = test__hybrid_hw_group_event, + .name = "cpu/instructions/h", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_symbolic_name_modifier, /* 1 */ }, { - .name = "{cpu-clock,cpu_core/cpu-cycles/}", - .check = test__hybrid_sw_hw_group_event, + .name = "cpu/instructions/G", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_exclude_host_modifier, /* 2 */ }, { - .name = "{cpu_core/cpu-cycles/,cpu-clock}", - .check = test__hybrid_hw_sw_group_event, + .name = "cpu/instructions/H", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_exclude_guest_modifier, /* 3 */ }, { - .name = "{cpu_core/cpu-cycles/k,cpu_core/instructions/u}", - .check = test__hybrid_group_modifier1, + .name = "{cpu/instructions/k,cpu/cycles/upp}", + .valid = test__pmu_cpu_valid, + .check = test__group1, /* 4 */ }, { - .name = "r1a", - .check = test__hybrid_raw1, + .name = "{cpu/cycles/u,cpu/instructions/kp}:p", + .valid = test__pmu_cpu_valid, + .check = test__group4, /* 5 */ }, { - .name = "cpu_core/r1a/", - .check = test__hybrid_raw2, + .name = "{cpu/cycles/,cpu/cache-misses/G}:H", + .valid = test__pmu_cpu_valid, + .check = test__group_gh1, /* 6 */ }, { - .name = "cpu_core/config=10,config1,config2=3,period=1000/u", - .check = test__checkevent_pmu, + .name = "{cpu/cycles/,cpu/cache-misses/H}:G", + .valid = test__pmu_cpu_valid, + .check = test__group_gh2, + /* 7 */ + }, + { + .name = "{cpu/cycles/G,cpu/cache-misses/H}:u", + .valid = test__pmu_cpu_valid, + .check = test__group_gh3, + /* 8 */ + }, + { + .name = "{cpu/cycles/G,cpu/cache-misses/H}:uG", + .valid = test__pmu_cpu_valid, + .check = test__group_gh4, + /* 9 */ + }, + { + .name = "{cpu/cycles/,cpu/cache-misses/,cpu/branch-misses/}:S", + .valid = test__pmu_cpu_valid, + .check = test__leader_sample1, + /* 0 */ + }, + { + .name = "{cpu/instructions/,cpu/branch-misses/}:Su", + .valid = test__pmu_cpu_valid, + .check = test__leader_sample2, + /* 1 */ + }, + { + .name = "cpu/instructions/uDp", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_pinned_modifier, + /* 2 */ + }, + { + .name = "{cpu/cycles/,cpu/cache-misses/,cpu/branch-misses/}:D", + .valid = test__pmu_cpu_valid, + .check = test__pinned_group, + /* 3 */ + }, + { + .name = "cpu/instructions/I", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_exclude_idle_modifier, + /* 4 */ + }, + { + .name = "cpu/instructions/kIG", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_exclude_idle_modifier_1, + /* 5 */ + }, + { + .name = "cpu/cycles/u", + .valid = test__pmu_cpu_valid, + .check = test__sym_event_slash, + /* 6 */ + }, + { + .name = "cpu/cycles/k", + .valid = test__pmu_cpu_valid, + .check = test__sym_event_dc, /* 7 */ }, { - .name = "cpu_core/LLC-loads/", - .check = test__hybrid_cache_event, + .name = "cpu/instructions/uep", + .valid = test__pmu_cpu_valid, + .check = test__checkevent_exclusive_modifier, /* 8 */ }, + { + .name = "{cpu/cycles/,cpu/cache-misses/,cpu/branch-misses/}:e", + .valid = test__pmu_cpu_valid, + .check = test__exclusive_group, + /* 9 */ + }, + { + .name = "cpu/cycles,name=name/", + .valid = test__pmu_cpu_valid, + .check = test__term_equal_term, + /* 0 */ + }, + { + .name = "cpu/cycles,name=l1d/", + .valid = test__pmu_cpu_valid, + .check = test__term_equal_legacy, + /* 1 */ + }, +}; + +struct terms_test { + const char *str; + int (*check)(struct list_head *terms); +}; + +static const struct terms_test test__terms[] = { + [0] = { + .str = "config=10,config1,config2=3,config3=4,umask=1,read,r0xead", + .check = test__checkterms_simple, + }, }; static int test_event(const struct evlist_test *e) @@ -2091,7 +2131,7 @@ static int test_event(const struct evlist_test *e) e->name, ret, err.str); parse_events_error__print(&err, e->name); ret = TEST_FAIL; - if (strstr(err.str, "can't access trace events")) + if (err.str && strstr(err.str, "can't access trace events")) ret = TEST_SKIP; } else { ret = e->check(evlist); @@ -2113,8 +2153,8 @@ static int test_event_fake_pmu(const char *str) return -ENOMEM; parse_events_error__init(&err); - perf_pmu__test_parse_init(); - ret = __parse_events(evlist, str, &err, &perf_pmu__fake, /*warn_if_reordered=*/true); + ret = __parse_events(evlist, str, /*pmu_filter=*/NULL, &err, + &perf_pmu__fake, /*warn_if_reordered=*/true); if (ret) { pr_debug("failed to parse event '%s', err %d, str '%s'\n", str, ret, err.str); @@ -2167,13 +2207,6 @@ static int test_term(const struct terms_test *t) INIT_LIST_HEAD(&terms); - /* - * The perf_pmu__test_parse_init prepares perf_pmu_events_list - * which gets freed in parse_events_terms. - */ - if (perf_pmu__test_parse_init()) - return -1; - ret = parse_events_terms(&terms, t->str); if (ret) { pr_debug("failed to parse terms '%s', err %d\n", @@ -2208,99 +2241,88 @@ static int test__terms2(struct test_suite *test __maybe_unused, int subtest __ma return test_terms(test__terms, ARRAY_SIZE(test__terms)); } -static int test_pmu(void) +static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - struct stat st; - char path[PATH_MAX]; - int ret; + struct perf_pmu *pmu = NULL; + int ret = TEST_OK; - snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/format/", - sysfs__mountpoint()); + while ((pmu = perf_pmus__scan(pmu)) != NULL) { + struct stat st; + char path[PATH_MAX]; + struct dirent *ent; + DIR *dir; + int err; - ret = stat(path, &st); - if (ret) - pr_debug("omitting PMU cpu tests\n"); - return !ret; -} + snprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/", + sysfs__mountpoint(), pmu->name); -static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused) -{ - struct stat st; - char path[PATH_MAX]; - struct dirent *ent; - DIR *dir; - int ret; + err = stat(path, &st); + if (err) { + pr_debug("skipping PMU %s events tests: %s\n", pmu->name, path); + continue; + } - if (!test_pmu()) - return TEST_SKIP; + dir = opendir(path); + if (!dir) { + pr_debug("can't open pmu event dir: %s\n", path); + ret = combine_test_results(ret, TEST_SKIP); + continue; + } - snprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu/events/", - sysfs__mountpoint()); + while ((ent = readdir(dir))) { + struct evlist_test e = { .name = NULL, }; + char name[2 * NAME_MAX + 1 + 12 + 3]; + int test_ret; - ret = stat(path, &st); - if (ret) { - pr_debug("omitting PMU cpu events tests: %s\n", path); - return TEST_OK; - } + /* Names containing . are special and cannot be used directly */ + if (strchr(ent->d_name, '.')) + continue; - dir = opendir(path); - if (!dir) { - pr_debug("can't open pmu event dir: %s\n", path); - return TEST_FAIL; - } + snprintf(name, sizeof(name), "%s/event=%s/u", pmu->name, ent->d_name); - ret = TEST_OK; - while ((ent = readdir(dir))) { - struct evlist_test e = { .name = NULL, }; - char name[2 * NAME_MAX + 1 + 12 + 3]; - int test_ret; + e.name = name; + e.check = test__checkevent_pmu_events; - /* Names containing . are special and cannot be used directly */ - if (strchr(ent->d_name, '.')) - continue; + test_ret = test_event(&e); + if (test_ret != TEST_OK) { + pr_debug("Test PMU event failed for '%s'", name); + ret = combine_test_results(ret, test_ret); + } - snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name); + if (!is_pmu_core(pmu->name)) + continue; - e.name = name; - e.check = test__checkevent_pmu_events; + /* + * Names containing '-' are recognized as prefixes and suffixes + * due to '-' being a legacy PMU separator. This fails when the + * prefix or suffix collides with an existing legacy token. For + * example, branch-brs has a prefix (branch) that collides with + * a PE_NAME_CACHE_TYPE token causing a parse error as a suffix + * isn't expected after this. As event names in the config + * slashes are allowed a '-' in the name we check this works + * above. + */ + if (strchr(ent->d_name, '-')) + continue; - test_ret = test_event(&e); - if (test_ret != TEST_OK) { - pr_debug("Test PMU event failed for '%s'", name); - ret = combine_test_results(ret, test_ret); + snprintf(name, sizeof(name), "%s:u,%s/event=%s/u", + ent->d_name, pmu->name, ent->d_name); + e.name = name; + e.check = test__checkevent_pmu_events_mix; + test_ret = test_event(&e); + if (test_ret != TEST_OK) { + pr_debug("Test PMU event failed for '%s'", name); + ret = combine_test_results(ret, test_ret); + } } - /* - * Names containing '-' are recognized as prefixes and suffixes - * due to '-' being a legacy PMU separator. This fails when the - * prefix or suffix collides with an existing legacy token. For - * example, branch-brs has a prefix (branch) that collides with - * a PE_NAME_CACHE_TYPE token causing a parse error as a suffix - * isn't expected after this. As event names in the config - * slashes are allowed a '-' in the name we check this works - * above. - */ - if (strchr(ent->d_name, '-')) - continue; - snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); - e.name = name; - e.check = test__checkevent_pmu_events_mix; - test_ret = test_event(&e); - if (test_ret != TEST_OK) { - pr_debug("Test PMU event failed for '%s'", name); - ret = combine_test_results(ret, test_ret); - } + closedir(dir); } - - closedir(dir); return ret; } static int test__pmu_events2(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - if (!test_pmu()) - return TEST_SKIP; - return test_events(test__events_pmu, ARRAY_SIZE(test__events_pmu)); } @@ -2362,14 +2384,6 @@ static bool test_alias(char **event, char **alias) return false; } -static int test__hybrid(struct test_suite *test __maybe_unused, int subtest __maybe_unused) -{ - if (!perf_pmu__has_hybrid()) - return TEST_SKIP; - - return test_events(test__hybrid_events, ARRAY_SIZE(test__hybrid_events)); -} - static int test__checkevent_pmu_events_alias(struct evlist *evlist) { struct evsel *evsel1 = evlist__first(evlist); @@ -2433,9 +2447,6 @@ static struct test_case tests__parse_events[] = { TEST_CASE_REASON("Test event parsing", events2, "permissions"), - TEST_CASE_REASON("Test parsing of \"hybrid\" CPU events", - hybrid, - "not hybrid"), TEST_CASE_REASON("Parsing of all PMU events from sysfs", pmu_events, "permissions"), diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index c05148ea400c..2c28fb50dc24 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -11,7 +11,7 @@ #include "debug.h" #include "expr.h" #include "stat.h" -#include "pmu.h" +#include "pmus.h" struct value { const char *event; @@ -302,11 +302,8 @@ static int test__parse_metric(struct test_suite *test __maybe_unused, int subtes TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0); TEST_ASSERT_VAL("recursion fail failed", test_recursion_fail() == 0); TEST_ASSERT_VAL("Memory bandwidth", test_memory_bandwidth() == 0); - - if (!perf_pmu__has_hybrid()) { - TEST_ASSERT_VAL("cache_miss_cycles failed", test_cache_miss_cycles() == 0); - TEST_ASSERT_VAL("test metric group", test_metric_group() == 0); - } + TEST_ASSERT_VAL("cache_miss_cycles failed", test_cache_miss_cycles() == 0); + TEST_ASSERT_VAL("test metric group", test_metric_group() == 0); return 0; } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 1dff863b9711..64383fc34ef1 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -2,6 +2,7 @@ #include "math.h" #include "parse-events.h" #include "pmu.h" +#include "pmus.h" #include "tests.h" #include <errno.h> #include <stdio.h> @@ -708,12 +709,9 @@ static int test__aliases(struct test_suite *test __maybe_unused, struct perf_pmu *pmu = NULL; unsigned long i; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { int count = 0; - if (!is_pmu_core(pmu->name)) - continue; - if (list_empty(&pmu->format)) { pr_debug2("skipping testing core PMU %s\n", pmu->name); continue; @@ -776,16 +774,8 @@ static int check_parse_id(const char *id, struct parse_events_error *error, for (cur = strchr(dup, '@') ; cur; cur = strchr(++cur, '@')) *cur = '/'; - if (fake_pmu) { - /* - * Every call to __parse_events will try to initialize the PMU - * state from sysfs and then clean it up at the end. Reset the - * PMU events to the test state so that we don't pick up - * erroneous prefixes and suffixes. - */ - perf_pmu__test_parse_init(); - } - ret = __parse_events(evlist, dup, error, fake_pmu, /*warn_if_reordered=*/true); + ret = __parse_events(evlist, dup, /*pmu_filter=*/NULL, error, fake_pmu, + /*warn_if_reordered=*/true); free(dup); evlist__delete(evlist); diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 3cf25f883df7..a4452639a3d4 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -86,17 +86,16 @@ static struct parse_events_term test_terms[] = { * Prepare format directory data, exported by kernel * at /sys/bus/event_source/devices/<dev>/format. */ -static char *test_format_dir_get(void) +static char *test_format_dir_get(char *dir, size_t sz) { - static char dir[PATH_MAX]; unsigned int i; - snprintf(dir, PATH_MAX, "/tmp/perf-pmu-test-format-XXXXXX"); + snprintf(dir, sz, "/tmp/perf-pmu-test-format-XXXXXX"); if (!mkdtemp(dir)) return NULL; for (i = 0; i < ARRAY_SIZE(test_formats); i++) { - static char name[PATH_MAX]; + char name[PATH_MAX]; struct test_format *format = &test_formats[i]; FILE *file; @@ -118,12 +117,13 @@ static char *test_format_dir_get(void) /* Cleanup format directory. */ static int test_format_dir_put(char *dir) { - char buf[PATH_MAX]; - snprintf(buf, PATH_MAX, "rm -f %s/*\n", dir); + char buf[PATH_MAX + 20]; + + snprintf(buf, sizeof(buf), "rm -f %s/*\n", dir); if (system(buf)) return -1; - snprintf(buf, PATH_MAX, "rmdir %s\n", dir); + snprintf(buf, sizeof(buf), "rmdir %s\n", dir); return system(buf); } @@ -140,7 +140,8 @@ static struct list_head *test_terms_list(void) static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - char *format = test_format_dir_get(); + char dir[PATH_MAX]; + char *format = test_format_dir_get(dir, sizeof(dir)); LIST_HEAD(formats); struct list_head *terms = test_terms_list(); int ret; diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 6b990ee38575..0ebc22ac8d5b 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -14,7 +14,7 @@ static int test__python_use(struct test_suite *test __maybe_unused, int subtest char *cmd; int ret; - if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s", + if (asprintf(&cmd, "echo \"import sys ; sys.path.insert(0, '%s'); import perf\" | %s %s", PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0) return -1; diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index 61f3059ca54b..b81582a89d36 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -14,6 +14,7 @@ ap.add_argument('--system-wide', action='store_true') ap.add_argument('--event', action='store_true') ap.add_argument('--per-core', action='store_true') ap.add_argument('--per-thread', action='store_true') +ap.add_argument('--per-cache', action='store_true') ap.add_argument('--per-die', action='store_true') ap.add_argument('--per-node', action='store_true') ap.add_argument('--per-socket', action='store_true') @@ -47,6 +48,7 @@ def check_json_output(expected_items): 'counter-value': lambda x: is_counter_value(x), 'cgroup': lambda x: True, 'cpu': lambda x: isint(x), + 'cache': lambda x: True, 'die': lambda x: True, 'event': lambda x: True, 'event-runtime': lambda x: isfloat(x), @@ -83,7 +85,7 @@ try: expected_items = 7 elif args.interval or args.per_thread or args.system_wide_no_aggr: expected_items = 8 - elif args.per_core or args.per_socket or args.per_node or args.per_die: + elif args.per_core or args.per_socket or args.per_node or args.per_die or args.per_cache: expected_items = 9 else: # If no option is specified, don't check the number of items. diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index fb78b6251a4e..a1969f236a0a 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -40,6 +40,7 @@ function commachecker() ;; "--per-socket") exp=8 ;; "--per-node") exp=8 ;; "--per-die") exp=8 + ;; "--per-cache") exp=8 esac while read line @@ -145,6 +146,18 @@ check_per_thread() echo "[Success]" } +check_per_cache_instance() +{ + echo -n "Checking CSV output: per cache instance " + if ParanoidAndNotRoot 0 + then + echo "[Skip] paranoid and not root" + return + fi + perf stat -x$csv_sep --per-cache -a true 2>&1 | commachecker --per-cache + echo "[Success]" +} + check_per_die() { echo -n "Checking CSV output: per die " @@ -222,6 +235,7 @@ if [ $skip_test -ne 1 ] then check_system_wide_no_aggr check_per_core + check_per_cache_instance check_per_die check_per_socket else diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index f3e4967cc72e..c282afa6217c 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -120,6 +120,18 @@ check_per_thread() echo "[Success]" } +check_per_cache_instance() +{ + echo -n "Checking json output: per cache_instance " + if ParanoidAndNotRoot 0 + then + echo "[Skip] paranoia and not root" + return + fi + perf stat -j --per-cache -a true 2>&1 | $PYTHON $pythonchecker --per-cache + echo "[Success]" +} + check_per_die() { echo -n "Checking json output: per die " @@ -197,6 +209,7 @@ if [ $skip_test -ne 1 ] then check_system_wide_no_aggr check_per_core + check_per_cache_instance check_per_die check_per_socket else diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index b154fbb15d54..3f1e67795490 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -103,10 +103,54 @@ test_topdown_weak_groups() { echo "Topdown weak groups test [Success]" } +test_cputype() { + # Test --cputype argument. + echo "cputype test" + + # Bogus PMU should fail. + if perf stat --cputype="123" -e instructions true > /dev/null 2>&1 + then + echo "cputype test [Bogus PMU didn't fail]" + err=1 + return + fi + + # Find a known PMU for cputype. + pmu="" + for i in cpu cpu_atom armv8_pmuv3_0 + do + if test -d "/sys/devices/$i" + then + pmu="$i" + break + fi + if perf stat -e "$i/instructions/" true > /dev/null 2>&1 + then + pmu="$i" + break + fi + done + if test "x$pmu" = "x" + then + echo "cputype test [Skipped known PMU not found]" + return + fi + + # Test running with cputype produces output. + if ! perf stat --cputype="$pmu" -e instructions true 2>&1 | grep -E -q "instructions" + then + echo "cputype test [Failed count missed with given filter]" + err=1 + return + fi + echo "cputype test [Success]" +} + test_default_stat test_stat_record_report test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups +test_cputype exit $err diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh new file mode 100755 index 000000000000..72ac6c83231c --- /dev/null +++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh @@ -0,0 +1,72 @@ +#!/bin/bash +# 'perf data convert --to-json' command test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +err=0 + +if [ "$PYTHON" = "" ] ; then + if which python3 > /dev/null ; then + PYTHON=python3 + elif which python > /dev/null ; then + PYTHON=python + else + echo Skipping test, python not detected please set environment variable PYTHON. + exit 2 + fi +fi + +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +result=$(mktemp /tmp/__perf_test.output.json.XXXXX) + +cleanup() +{ + rm -f "${perfdata}" + rm -f "${result}" + trap - exit term int +} + +trap_cleanup() +{ + cleanup + exit ${err} +} +trap trap_cleanup exit term int + +test_json_converter_command() +{ + echo "Testing Perf Data Convertion Command to JSON" + perf record -o "$perfdata" -F 99 -g -- perf test -w noploop > /dev/null 2>&1 + perf data convert --to-json "$result" --force -i "$perfdata" >/dev/null 2>&1 + if [ $(cat "${result}" | wc -l) -gt "0" ] ; then + echo "Perf Data Converter Command to JSON [SUCCESS]" + else + echo "Perf Data Converter Command to JSON [FAILED]" + err=1 + exit + fi +} + +validate_json_format() +{ + echo "Validating Perf Data Converted JSON file" + if [ -f "$result" ] ; then + if $PYTHON -c "import json; json.load(open('$result'))" >/dev/null 2>&1 ; then + echo "The file contains valid JSON format [SUCCESS]" + else + echo "The file does not contain valid JSON format [FAILED]" + err=1 + exit + fi + else + echo "File not found [FAILED]" + err=2 + exit + fi +} + +test_json_converter_command +validate_json_format + +exit ${err} diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index b3bd14b025a8..e52b031bedc5 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -20,7 +20,7 @@ #include "tests.h" #include "util/mmap.h" #include "util/sample.h" -#include "pmu.h" +#include "pmus.h" static int spin_sleep(void) { @@ -375,17 +375,7 @@ static int test__switch_tracking(struct test_suite *test __maybe_unused, int sub cpu_clocks_evsel = evlist__last(evlist); /* Second event */ - if (perf_pmu__has_hybrid()) { - cycles = "cpu_core/cycles/u"; - err = parse_event(evlist, cycles); - if (err) { - cycles = "cpu_atom/cycles/u"; - pr_debug("Trying %s\n", cycles); - err = parse_event(evlist, cycles); - } - } else { - err = parse_event(evlist, cycles); - } + err = parse_event(evlist, cycles); if (err) { pr_debug("Failed to parse event %s\n", cycles); goto out_err; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 9a0f3904e53d..f424c0b7f43f 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -118,15 +118,13 @@ DECLARE_SUITE(bpf); DECLARE_SUITE(session_topology); DECLARE_SUITE(thread_map_synthesize); DECLARE_SUITE(thread_map_remove); -DECLARE_SUITE(cpu_map_synthesize); +DECLARE_SUITE(cpu_map); DECLARE_SUITE(synthesize_stat_config); DECLARE_SUITE(synthesize_stat); DECLARE_SUITE(synthesize_stat_round); DECLARE_SUITE(event_update); DECLARE_SUITE(event_times); DECLARE_SUITE(backward_ring_buffer); -DECLARE_SUITE(cpu_map_print); -DECLARE_SUITE(cpu_map_merge); DECLARE_SUITE(sdt_event); DECLARE_SUITE(is_printable_array); DECLARE_SUITE(bitmap_print); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index c4630cfc80ea..9dee63734e66 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -8,7 +8,7 @@ #include "session.h" #include "evlist.h" #include "debug.h" -#include "pmu.h" +#include "pmus.h" #include <linux/err.h> #define TEMPL "/tmp/perf-test-XXXXXX" @@ -41,18 +41,8 @@ static int session_write_header(char *path) session = perf_session__new(&data, NULL); TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); - if (!perf_pmu__has_hybrid()) { - session->evlist = evlist__new_default(); - TEST_ASSERT_VAL("can't get evlist", session->evlist); - } else { - struct parse_events_error err; - - session->evlist = evlist__new(); - TEST_ASSERT_VAL("can't get evlist", session->evlist); - parse_events_error__init(&err); - parse_events(session->evlist, "cpu_core/cycles/", &err); - parse_events_error__exit(&err); - } + session->evlist = evlist__new_default(); + TEST_ASSERT_VAL("can't get evlist", session->evlist); perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); perf_header__set_feat(&session->header, HEADER_NRCPUS); diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 4c59edddd6a8..3d12bf0f6d07 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -11,7 +11,7 @@ struct strarray { u64 offset; int nr_entries; const char *prefix; - const char **entries; + const char * const *entries; }; #define DEFINE_STRARRAY(array, _prefix) struct strarray strarray__##array = { \ diff --git a/tools/perf/trace/beauty/tracepoints/x86_msr.sh b/tools/perf/trace/beauty/tracepoints/x86_msr.sh index 0078689963e0..fa3c4418e856 100755 --- a/tools/perf/trace/beauty/tracepoints/x86_msr.sh +++ b/tools/perf/trace/beauty/tracepoints/x86_msr.sh @@ -13,7 +13,7 @@ x86_msr_index=${arch_x86_header_dir}/msr-index.h # Just the ones starting with 0x00000 so as to have a simple # array. -printf "static const char *x86_MSRs[] = {\n" +printf "static const char * const x86_MSRs[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x00000[[:xdigit:]]+)[[:space:]]*.*' grep -E $regex ${x86_msr_index} | grep -E -v 'MSR_(ATOM|P[46]|IA32_(TSC_DEADLINE|UCODE_REV)|IDT_FCR4)' | \ sed -r "s/$regex/\2 \1/g" | sort -n | \ @@ -24,7 +24,7 @@ printf "};\n\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0xc0000[[:xdigit:]]+)[[:space:]]*.*' printf "#define x86_64_specific_MSRs_offset " grep -E $regex ${x86_msr_index} | sed -r "s/$regex/\2/g" | sort -n | head -1 -printf "static const char *x86_64_specific_MSRs[] = {\n" +printf "static const char * const x86_64_specific_MSRs[] = {\n" grep -E $regex ${x86_msr_index} | \ sed -r "s/$regex/\2 \1/g" | grep -E -vw 'K6_WHCR' | sort -n | \ xargs printf "\t[%s - x86_64_specific_MSRs_offset] = \"%s\",\n" @@ -33,7 +33,7 @@ printf "};\n\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0xc0010[[:xdigit:]]+)[[:space:]]*.*' printf "#define x86_AMD_V_KVM_MSRs_offset " grep -E $regex ${x86_msr_index} | sed -r "s/$regex/\2/g" | sort -n | head -1 -printf "static const char *x86_AMD_V_KVM_MSRs[] = {\n" +printf "static const char * const x86_AMD_V_KVM_MSRs[] = {\n" grep -E $regex ${x86_msr_index} | \ sed -r "s/$regex/\2 \1/g" | sort -n | \ xargs printf "\t[%s - x86_AMD_V_KVM_MSRs_offset] = \"%s\",\n" diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 12c3ce530e42..70bad42b807b 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -781,9 +781,9 @@ static int annotate_browser__run(struct annotate_browser *browser, ui_browser__help_window(&browser->b, "UP/DOWN/PGUP\n" "PGDN/SPACE Navigate\n" + "</> Move to prev/next symbol\n" "q/ESC/CTRL+C Exit\n\n" "ENTER Go to target\n" - "ESC Exit\n" "H Go to hottest instruction\n" "TAB/shift+TAB Cycle thru hottest instructions\n" "j Toggle showing jump to target arrows\n" @@ -913,6 +913,8 @@ show_sup_ins: annotation__toggle_full_addr(notes, ms); continue; case K_LEFT: + case '<': + case '>': case K_ESC: case 'q': case CTRL('c'): diff --git a/tools/perf/util/Build b/tools/perf/util/Build index f9df1df1eec0..c449741adf30 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -11,7 +11,6 @@ perf-y += db-export.o perf-y += env.o perf-y += event.o perf-y += evlist.o -perf-y += evlist-hybrid.o perf-y += sideband_evlist.o perf-y += evsel.o perf-y += evsel_fprintf.o @@ -24,7 +23,6 @@ perf-y += llvm-utils.o perf-y += mmap.o perf-y += memswap.o perf-y += parse-events.o -perf-y += parse-events-hybrid.o perf-y += print-events.o perf-y += tracepoint.o perf-y += perf_regs.o @@ -75,7 +73,6 @@ perf-y += pmu.o perf-y += pmus.o perf-y += pmu-flex.o perf-y += pmu-bison.o -perf-y += pmu-hybrid.o perf-y += svghelper.o perf-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o perf-y += trace-event-scripting.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 11992cfe271c..b708bbc49c9e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -558,6 +558,19 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy return -1; *s = '\0'; + + /* + * x86 SIB addressing has something like 0x8(%rax, %rcx, 1) + * then it needs to have the closing parenthesis. + */ + if (strchr(ops->raw, '(')) { + *s = ','; + s = strchr(ops->raw, ')'); + if (s == NULL || s[1] != ',') + return -1; + *++s = '\0'; + } + ops->source.raw = strdup(ops->raw); *s = ','; diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 9f2e36ef5072..0b61840d4226 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -26,6 +26,6 @@ static inline int is_absolute_path(const char *path) return path[0] == '/'; } -char *mkpath(const char *fmt, ...) __printf(1, 2); +char *mkpath(char *path_buf, size_t sz, const char *fmt, ...) __printf(3, 4); #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 658170b8dcef..f340dc73db6d 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -543,6 +543,7 @@ static char *home_perfconfig(void) const char *home = NULL; char *config; struct stat st; + char path[PATH_MAX]; home = getenv("HOME"); @@ -554,7 +555,7 @@ static char *home_perfconfig(void) if (!home || !*home || !perf_config_global()) return NULL; - config = strdup(mkpath("%s/.perfconfig", home)); + config = strdup(mkpath(path, sizeof(path), "%s/.perfconfig", home)); if (config == NULL) { pr_warning("Not enough memory to process %s/.perfconfig, ignoring it.\n", home); return NULL; diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 75d9c73e0184..0e090e8bc334 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -222,6 +222,10 @@ static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer) return a->socket - b->socket; else if (a->die != b->die) return a->die - b->die; + else if (a->cache_lvl != b->cache_lvl) + return a->cache_lvl - b->cache_lvl; + else if (a->cache != b->cache) + return a->cache - b->cache; else if (a->core != b->core) return a->core - b->core; else @@ -663,9 +667,9 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) return ptr - buf; } -const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ +struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ { - static const struct perf_cpu_map *online = NULL; + static struct perf_cpu_map *online; if (!online) online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ @@ -679,6 +683,8 @@ bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b a->node == b->node && a->socket == b->socket && a->die == b->die && + a->cache_lvl == b->cache_lvl && + a->cache == b->cache && a->core == b->core && a->cpu.cpu == b->cpu.cpu; } @@ -689,6 +695,8 @@ bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a) a->node == -1 && a->socket == -1 && a->die == -1 && + a->cache_lvl == -1 && + a->cache == -1 && a->core == -1 && a->cpu.cpu == -1; } @@ -700,6 +708,8 @@ struct aggr_cpu_id aggr_cpu_id__empty(void) .node = -1, .socket = -1, .die = -1, + .cache_lvl = -1, + .cache = -1, .core = -1, .cpu = (struct perf_cpu){ .cpu = -1 }, }; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index e3426541e0aa..9df2aeb34d3d 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -20,6 +20,13 @@ struct aggr_cpu_id { int socket; /** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */ int die; + /** The cache level as read from /sys/devices/system/cpu/cpuX/cache/indexY/level */ + int cache_lvl; + /** + * The cache instance ID, which is the first CPU in the + * /sys/devices/system/cpu/cpuX/cache/indexY/shared_cpu_list + */ + int cache; /** The core id as read from /sys/devices/system/cpu/cpuX/topology/core_id. */ int core; /** CPU aggregation, note there is one CPU for each SMT thread. */ @@ -48,7 +55,7 @@ struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *da size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); -const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ +struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ int cpu__setup_cpunode_map(void); @@ -59,7 +66,7 @@ struct perf_cpu cpu__max_present_cpu(void); /** * cpu_map__is_dummy - Events associated with a pid, rather than a CPU, use a single dummy map with an entry of -1. */ -static inline bool cpu_map__is_dummy(struct perf_cpu_map *cpus) +static inline bool cpu_map__is_dummy(const struct perf_cpu_map *cpus) { return perf_cpu_map__nr(cpus) == 1 && perf_cpu_map__cpu(cpus, 0).cpu == -1; } diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index ca1d833a0c26..81cfc85f4668 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -12,7 +12,8 @@ #include "cpumap.h" #include "debug.h" #include "env.h" -#include "pmu-hybrid.h" +#include "pmu.h" +#include "pmus.h" #define PACKAGE_CPUS_FMT \ "%s/devices/system/cpu/cpu%d/topology/package_cpus_list" @@ -469,12 +470,11 @@ err: struct hybrid_topology *hybrid_topology__new(void) { - struct perf_pmu *pmu; + struct perf_pmu *pmu = NULL; struct hybrid_topology *tp = NULL; - u32 nr, i = 0; + int nr = perf_pmus__num_core_pmus(), i = 0; - nr = perf_pmu__hybrid_pmu_num(); - if (nr == 0) + if (nr <= 1) return NULL; tp = zalloc(sizeof(*tp) + sizeof(tp->nodes[0]) * nr); @@ -482,7 +482,7 @@ struct hybrid_topology *hybrid_topology__new(void) return NULL; tp->nr = nr; - perf_pmu__for_each_hybrid_pmu(pmu) { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { if (load_hybrid_node(&tp->nodes[i], pmu)) { hybrid_topology__delete(tp); return NULL; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index a86614599269..046fbfcfdaab 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -67,6 +67,39 @@ char dso__symtab_origin(const struct dso *dso) return origin[dso->symtab_type]; } +bool dso__is_object_file(const struct dso *dso) +{ + switch (dso->binary_type) { + case DSO_BINARY_TYPE__KALLSYMS: + case DSO_BINARY_TYPE__GUEST_KALLSYMS: + case DSO_BINARY_TYPE__JAVA_JIT: + case DSO_BINARY_TYPE__BPF_PROG_INFO: + case DSO_BINARY_TYPE__BPF_IMAGE: + case DSO_BINARY_TYPE__OOL: + return false; + case DSO_BINARY_TYPE__VMLINUX: + case DSO_BINARY_TYPE__GUEST_VMLINUX: + case DSO_BINARY_TYPE__DEBUGLINK: + case DSO_BINARY_TYPE__BUILD_ID_CACHE: + case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO: + case DSO_BINARY_TYPE__FEDORA_DEBUGINFO: + case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO: + case DSO_BINARY_TYPE__BUILDID_DEBUGINFO: + case DSO_BINARY_TYPE__SYSTEM_PATH_DSO: + case DSO_BINARY_TYPE__GUEST_KMODULE: + case DSO_BINARY_TYPE__GUEST_KMODULE_COMP: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE: + case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP: + case DSO_BINARY_TYPE__KCORE: + case DSO_BINARY_TYPE__GUEST_KCORE: + case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO: + case DSO_BINARY_TYPE__NOT_FOUND: + default: + return true; + } +} + int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type, char *root_dir, char *filename, size_t size) diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 0b7c7633b9f6..b23a157c914d 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -379,23 +379,25 @@ void dso__reset_find_symbol_cache(struct dso *dso); size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp); size_t dso__fprintf(struct dso *dso, FILE *fp); -static inline bool dso__is_vmlinux(struct dso *dso) +static inline bool dso__is_vmlinux(const struct dso *dso) { return dso->binary_type == DSO_BINARY_TYPE__VMLINUX || dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX; } -static inline bool dso__is_kcore(struct dso *dso) +static inline bool dso__is_kcore(const struct dso *dso) { return dso->binary_type == DSO_BINARY_TYPE__KCORE || dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE; } -static inline bool dso__is_kallsyms(struct dso *dso) +static inline bool dso__is_kallsyms(const struct dso *dso) { return dso->kernel && dso->long_name[0] != '/'; } +bool dso__is_object_file(const struct dso *dso); + void dso__free_a2l(struct dso *dso); enum dso_type dso__type(struct dso *dso, struct machine *machine); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 4a4fdad820d6..9eabf3ec56e9 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -10,6 +10,7 @@ #include <sys/utsname.h> #include <stdlib.h> #include <string.h> +#include "pmus.h" #include "strbuf.h" struct perf_env perf_env; @@ -323,7 +324,7 @@ int perf_env__read_pmu_mappings(struct perf_env *env) u32 pmu_num = 0; struct strbuf sb; - while ((pmu = perf_pmu__scan(pmu))) { + while ((pmu = perf_pmus__scan(pmu))) { if (!pmu->name) continue; pmu_num++; @@ -337,7 +338,7 @@ int perf_env__read_pmu_mappings(struct perf_env *env) if (strbuf_init(&sb, 128 * pmu_num) < 0) return -ENOMEM; - while ((pmu = perf_pmu__scan(pmu))) { + while ((pmu = perf_pmus__scan(pmu))) { if (!pmu->name) continue; if (strbuf_addf(&sb, "%u:%s", pmu->type, pmu->name) < 0) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 8ae742e32e3c..e8b0666d913c 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -135,9 +135,10 @@ void perf_event__read_stat_config(struct perf_stat_config *config, config->__val = event->data[i].val; \ break; - CASE(AGGR_MODE, aggr_mode) - CASE(SCALE, scale) - CASE(INTERVAL, interval) + CASE(AGGR_MODE, aggr_mode) + CASE(SCALE, scale) + CASE(INTERVAL, interval) + CASE(AGGR_LEVEL, aggr_level) #undef CASE default: pr_warning("unknown stat config term %" PRI_lu64 "\n", diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c deleted file mode 100644 index 57f02beef023..000000000000 --- a/tools/perf/util/evlist-hybrid.c +++ /dev/null @@ -1,162 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include <errno.h> -#include <inttypes.h> -#include "cpumap.h" -#include "evlist.h" -#include "evsel.h" -#include "../perf.h" -#include "util/pmu-hybrid.h" -#include "util/evlist-hybrid.h" -#include "debug.h" -#include <unistd.h> -#include <stdlib.h> -#include <linux/err.h> -#include <linux/string.h> -#include <perf/evlist.h> -#include <perf/evsel.h> -#include <perf/cpumap.h> - -int evlist__add_default_hybrid(struct evlist *evlist, bool precise) -{ - struct evsel *evsel; - struct perf_pmu *pmu; - __u64 config; - struct perf_cpu_map *cpus; - - perf_pmu__for_each_hybrid_pmu(pmu) { - config = PERF_COUNT_HW_CPU_CYCLES | - ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT); - evsel = evsel__new_cycles(precise, PERF_TYPE_HARDWARE, - config); - if (!evsel) - return -ENOMEM; - - cpus = perf_cpu_map__get(pmu->cpus); - evsel->core.cpus = cpus; - evsel->core.own_cpus = perf_cpu_map__get(cpus); - evsel->pmu_name = strdup(pmu->name); - evlist__add(evlist, evsel); - } - - return 0; -} - -static bool group_hybrid_conflict(struct evsel *leader) -{ - struct evsel *pos, *prev = NULL; - - for_each_group_evsel(pos, leader) { - if (!evsel__is_hybrid(pos)) - continue; - - if (prev && strcmp(prev->pmu_name, pos->pmu_name)) - return true; - - prev = pos; - } - - return false; -} - -void evlist__warn_hybrid_group(struct evlist *evlist) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) { - if (evsel__is_group_leader(evsel) && - evsel->core.nr_members > 1 && - group_hybrid_conflict(evsel)) { - pr_warning("WARNING: events in group from " - "different hybrid PMUs!\n"); - return; - } - } -} - -bool evlist__has_hybrid(struct evlist *evlist) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) { - if (evsel->pmu_name && - perf_pmu__is_hybrid(evsel->pmu_name)) { - return true; - } - } - - return false; -} - -int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list) -{ - struct perf_cpu_map *cpus; - struct evsel *evsel, *tmp; - struct perf_pmu *pmu; - int ret, unmatched_count = 0, events_nr = 0; - - if (!perf_pmu__has_hybrid() || !cpu_list) - return 0; - - cpus = perf_cpu_map__new(cpu_list); - if (!cpus) - return -1; - - /* - * The evsels are created with hybrid pmu's cpus. But now we - * need to check and adjust the cpus of evsel by cpu_list because - * cpu_list may cause conflicts with cpus of evsel. For example, - * cpus of evsel is cpu0-7, but the cpu_list is cpu6-8, we need - * to adjust the cpus of evsel to cpu6-7. And then propatate maps - * in evlist__create_maps(). - */ - evlist__for_each_entry_safe(evlist, tmp, evsel) { - struct perf_cpu_map *matched_cpus, *unmatched_cpus; - char buf1[128], buf2[128]; - - pmu = perf_pmu__find_hybrid_pmu(evsel->pmu_name); - if (!pmu) - continue; - - ret = perf_pmu__cpus_match(pmu, cpus, &matched_cpus, - &unmatched_cpus); - if (ret) - goto out; - - events_nr++; - - if (perf_cpu_map__nr(matched_cpus) > 0 && - (perf_cpu_map__nr(unmatched_cpus) > 0 || - perf_cpu_map__nr(matched_cpus) < perf_cpu_map__nr(cpus) || - perf_cpu_map__nr(matched_cpus) < perf_cpu_map__nr(pmu->cpus))) { - perf_cpu_map__put(evsel->core.cpus); - perf_cpu_map__put(evsel->core.own_cpus); - evsel->core.cpus = perf_cpu_map__get(matched_cpus); - evsel->core.own_cpus = perf_cpu_map__get(matched_cpus); - - if (perf_cpu_map__nr(unmatched_cpus) > 0) { - cpu_map__snprint(matched_cpus, buf1, sizeof(buf1)); - pr_warning("WARNING: use %s in '%s' for '%s', skip other cpus in list.\n", - buf1, pmu->name, evsel->name); - } - } - - if (perf_cpu_map__nr(matched_cpus) == 0) { - evlist__remove(evlist, evsel); - evsel__delete(evsel); - - cpu_map__snprint(cpus, buf1, sizeof(buf1)); - cpu_map__snprint(pmu->cpus, buf2, sizeof(buf2)); - pr_warning("WARNING: %s isn't a '%s', please use a CPU list in the '%s' range (%s)\n", - buf1, pmu->name, pmu->name, buf2); - unmatched_count++; - } - - perf_cpu_map__put(matched_cpus); - perf_cpu_map__put(unmatched_cpus); - } - if (events_nr) - ret = (unmatched_count == events_nr) ? -1 : 0; -out: - perf_cpu_map__put(cpus); - return ret; -} diff --git a/tools/perf/util/evlist-hybrid.h b/tools/perf/util/evlist-hybrid.h deleted file mode 100644 index aacdb1b0f948..000000000000 --- a/tools/perf/util/evlist-hybrid.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_EVLIST_HYBRID_H -#define __PERF_EVLIST_HYBRID_H - -#include <linux/compiler.h> -#include <linux/kernel.h> -#include "evlist.h" -#include <unistd.h> - -int evlist__add_default_hybrid(struct evlist *evlist, bool precise); -void evlist__warn_hybrid_group(struct evlist *evlist); -bool evlist__has_hybrid(struct evlist *evlist); -int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list); - -#endif /* __PERF_EVLIST_HYBRID_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a0504316b06f..82c0b3d0c822 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -28,7 +28,6 @@ #include "util/string2.h" #include "util/perf_api_probe.h" #include "util/evsel_fprintf.h" -#include "util/evlist-hybrid.h" #include "util/pmu.h" #include "util/sample.h" #include "util/bpf-filter.h" @@ -93,8 +92,15 @@ struct evlist *evlist__new(void) struct evlist *evlist__new_default(void) { struct evlist *evlist = evlist__new(); + bool can_profile_kernel; + int err; + + if (!evlist) + return NULL; - if (evlist && evlist__add_default(evlist)) { + can_profile_kernel = perf_event_paranoid_check(1); + err = parse_event(evlist, can_profile_kernel ? "cycles:P" : "cycles:Pu"); + if (err) { evlist__delete(evlist); evlist = NULL; } @@ -237,19 +243,6 @@ static void evlist__set_leader(struct evlist *evlist) perf_evlist__set_leader(&evlist->core); } -int __evlist__add_default(struct evlist *evlist, bool precise) -{ - struct evsel *evsel; - - evsel = evsel__new_cycles(precise, PERF_TYPE_HARDWARE, - PERF_COUNT_HW_CPU_CYCLES); - if (evsel == NULL) - return -ENOMEM; - - evlist__add(evlist, evsel); - return 0; -} - static struct evsel *evlist__dummy_event(struct evlist *evlist) { struct perf_event_attr attr = { @@ -1067,7 +1060,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target) if (!cpus) goto out_delete_threads; - evlist->core.has_user_cpus = !!target->cpu_list && !target->hybrid; + evlist->core.has_user_cpus = !!target->cpu_list; perf_evlist__set_maps(&evlist->core, cpus, threads); @@ -2465,3 +2458,42 @@ void evlist__check_mem_load_aux(struct evlist *evlist) } } } + +/** + * evlist__warn_user_requested_cpus() - Check each evsel against requested CPUs + * and warn if the user CPU list is inapplicable for the event's PMU's + * CPUs. Not core PMUs list a CPU in sysfs, but this may be overwritten by a + * user requested CPU and so any online CPU is applicable. Core PMUs handle + * events on the CPUs in their list and otherwise the event isn't supported. + * @evlist: The list of events being checked. + * @cpu_list: The user provided list of CPUs. + */ +void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list) +{ + struct perf_cpu_map *user_requested_cpus; + struct evsel *pos; + + if (!cpu_list) + return; + + user_requested_cpus = perf_cpu_map__new(cpu_list); + if (!user_requested_cpus) + return; + + evlist__for_each_entry(evlist, pos) { + struct perf_cpu_map *intersect, *to_test; + const struct perf_pmu *pmu = evsel__find_pmu(pos); + + to_test = pmu && pmu->is_core ? pmu->cpus : cpu_map__online(); + intersect = perf_cpu_map__intersect(to_test, user_requested_cpus); + if (!perf_cpu_map__equal(intersect, user_requested_cpus)) { + char buf[128]; + + cpu_map__snprint(to_test, buf, sizeof(buf)); + pr_warning("WARNING: A requested CPU in '%s' is not supported by PMU '%s' (CPUs %s) for event '%s'\n", + cpu_list, pmu ? pmu->name : "cpu", buf, evsel__name(pos)); + } + perf_cpu_map__put(intersect); + } + perf_cpu_map__put(user_requested_cpus); +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 46cf402add93..664c6bf7b3e0 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -67,7 +67,6 @@ struct evlist { struct evsel *selected; struct events_stats stats; struct perf_env *env; - const char *hybrid_pmu_name; void (*trace_event_sample_raw)(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); @@ -101,13 +100,6 @@ void evlist__delete(struct evlist *evlist); void evlist__add(struct evlist *evlist, struct evsel *entry); void evlist__remove(struct evlist *evlist, struct evsel *evsel); -int __evlist__add_default(struct evlist *evlist, bool precise); - -static inline int evlist__add_default(struct evlist *evlist) -{ - return __evlist__add_default(evlist, true); -} - int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); int __evlist__add_default_attrs(struct evlist *evlist, @@ -448,4 +440,6 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx); int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf); void evlist__check_mem_load_aux(struct evlist *evlist); +void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c2dbb5647e75..ed2e07186b71 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -46,8 +46,9 @@ #include "memswap.h" #include "util.h" #include "util/hashmap.h" -#include "pmu-hybrid.h" #include "off_cpu.h" +#include "pmu.h" +#include "pmus.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" #include "util/bpf-filter.h" @@ -291,6 +292,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->group_pmu_name = NULL; evsel->skippable = false; } @@ -317,48 +319,6 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } -static bool perf_event_can_profile_kernel(void) -{ - return perf_event_paranoid_check(1); -} - -struct evsel *evsel__new_cycles(bool precise __maybe_unused, __u32 type, __u64 config) -{ - struct perf_event_attr attr = { - .type = type, - .config = config, - .exclude_kernel = !perf_event_can_profile_kernel(), - }; - struct evsel *evsel; - - event_attr_init(&attr); - - /* - * Now let the usual logic to set up the perf_event_attr defaults - * to kick in when we return and before perf_evsel__open() is called. - */ - evsel = evsel__new(&attr); - if (evsel == NULL) - goto out; - - arch_evsel__fixup_new_cycles(&evsel->core.attr); - - evsel->precise_max = true; - - /* use asprintf() because free(evsel) assumes name is allocated */ - if (asprintf(&evsel->name, "cycles%s%s%.*s", - (attr.precise_ip || attr.exclude_kernel) ? ":" : "", - attr.exclude_kernel ? "u" : "", - attr.precise_ip ? attr.precise_ip + 1 : 0, "ppp") < 0) - goto error_free; -out: - return evsel; -error_free: - evsel__delete(evsel); - evsel = NULL; - goto out; -} - int copy_config_terms(struct list_head *dst, struct list_head *src) { struct evsel_config_term *pos, *tmp; @@ -416,6 +376,7 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; evsel->core.requires_cpu = orig->core.requires_cpu; + evsel->core.is_pmu_core = orig->core.is_pmu_core; if (orig->name) { evsel->name = strdup(orig->name); @@ -432,6 +393,11 @@ struct evsel *evsel__clone(struct evsel *orig) if (evsel->pmu_name == NULL) goto out_err; } + if (orig->group_pmu_name) { + evsel->group_pmu_name = strdup(orig->group_pmu_name); + if (evsel->group_pmu_name == NULL) + goto out_err; + } if (orig->filter) { evsel->filter = strdup(orig->filter); if (evsel->filter == NULL) @@ -828,30 +794,6 @@ bool evsel__name_is(struct evsel *evsel, const char *name) return !strcmp(evsel__name(evsel), name); } -const char *evsel__group_pmu_name(const struct evsel *evsel) -{ - struct evsel *leader = evsel__leader(evsel); - struct evsel *pos; - - /* - * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the first non-software event to avoid breaking the - * software event out of the group. - * - * Aux event leaders, like intel_pt, expect a group with events from - * other PMUs, so substitute the AUX event's PMU in this case. - */ - if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { - /* Starting with the leader, find the first event with a named PMU. */ - for_each_group_evsel(pos, leader) { - if (pos->pmu_name) - return pos->pmu_name; - } - } - - return evsel->pmu_name ?: "cpu"; -} - const char *evsel__metric_id(const struct evsel *evsel) { if (evsel->metric_id) @@ -1131,10 +1073,6 @@ void __weak arch_evsel__set_sample_weight(struct evsel *evsel) evsel__set_sample_bit(evsel, WEIGHT); } -void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_unused) -{ -} - void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused, struct perf_event_attr *attr __maybe_unused) { @@ -1537,6 +1475,7 @@ void evsel__exit(struct evsel *evsel) zfree(&evsel->group_name); zfree(&evsel->name); zfree(&evsel->pmu_name); + zfree(&evsel->group_pmu_name); zfree(&evsel->unit); zfree(&evsel->metric_id); evsel__zero_per_pkg(evsel); @@ -3178,9 +3117,17 @@ void evsel__zero_per_pkg(struct evsel *evsel) } } +/** + * evsel__is_hybrid - does the evsel have a known PMU that is hybrid. Note, this + * will be false on hybrid systems for hardware and legacy + * cache events. + */ bool evsel__is_hybrid(const struct evsel *evsel) { - return evsel->pmu_name && perf_pmu__is_hybrid(evsel->pmu_name); + if (perf_pmus__num_core_pmus() == 1) + return false; + + return evsel->core.is_pmu_core; } struct evsel *evsel__leader(const struct evsel *evsel) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0f54f28a69c2..b365b449c6ea 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -72,6 +72,7 @@ struct evsel { char *name; char *group_name; const char *pmu_name; + const char *group_pmu_name; #ifdef HAVE_LIBTRACEEVENT struct tep_event *tp_format; #endif @@ -241,8 +242,6 @@ static inline struct evsel *evsel__newtp(const char *sys, const char *name) } #endif -struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config); - #ifdef HAVE_LIBTRACEEVENT struct tep_event *event_format__new(const char *sys, const char *name); #endif @@ -287,7 +286,6 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size); int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *evsel__name(struct evsel *evsel); bool evsel__name_is(struct evsel *evsel, const char *name); -const char *evsel__group_pmu_name(const struct evsel *evsel); const char *evsel__metric_id(const struct evsel *evsel); static inline bool evsel__is_tool(const struct evsel *evsel) @@ -310,7 +308,6 @@ void __evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_forma void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier); void arch_evsel__set_sample_weight(struct evsel *evsel); -void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr); void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr); int evsel__set_filter(struct evsel *evsel, const char *filter); @@ -460,16 +457,24 @@ static inline int evsel__group_idx(struct evsel *evsel) } /* Iterates group WITHOUT the leader. */ -#define for_each_group_member(_evsel, _leader) \ -for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node); \ - (_evsel) && (_evsel)->core.leader == (&_leader->core); \ - (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) +#define for_each_group_member_head(_evsel, _leader, _head) \ +for ((_evsel) = list_entry((_leader)->core.node.next, struct evsel, core.node); \ + (_evsel) && &(_evsel)->core.node != (_head) && \ + (_evsel)->core.leader == &(_leader)->core; \ + (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) + +#define for_each_group_member(_evsel, _leader) \ + for_each_group_member_head(_evsel, _leader, &(_leader)->evlist->core.entries) /* Iterates group WITH the leader. */ -#define for_each_group_evsel(_evsel, _leader) \ -for ((_evsel) = _leader; \ - (_evsel) && (_evsel)->core.leader == (&_leader->core); \ - (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) +#define for_each_group_evsel_head(_evsel, _leader, _head) \ +for ((_evsel) = _leader; \ + (_evsel) && &(_evsel)->core.node != (_head) && \ + (_evsel)->core.leader == &(_leader)->core; \ + (_evsel) = list_entry((_evsel)->core.node.next, struct evsel, core.node)) + +#define for_each_group_evsel(_evsel, _leader) \ + for_each_group_evsel_head(_evsel, _leader, &(_leader)->evlist->core.entries) static inline bool evsel__has_branch_callstack(const struct evsel *evsel) { diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index cc80ec554c0a..a1655fd7ed9b 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -2,6 +2,7 @@ #include <inttypes.h> #include <stdio.h> #include <stdbool.h> +#include "util/evlist.h" #include "evsel.h" #include "util/evsel_fprintf.h" #include "util/event.h" @@ -116,6 +117,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, int print_ip = print_opts & EVSEL__PRINT_IP; int print_sym = print_opts & EVSEL__PRINT_SYM; int print_dso = print_opts & EVSEL__PRINT_DSO; + int print_dsoff = print_opts & EVSEL__PRINT_DSOFF; int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET; int print_oneline = print_opts & EVSEL__PRINT_ONELINE; int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; @@ -171,11 +173,8 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, } } - if (print_dso && (!sym || !sym->inlined)) { - printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(map, fp); - printed += fprintf(fp, ")"); - } + if (print_dso && (!sym || !sym->inlined)) + printed += map__fprintf_dsoname_dsoff(map, print_dsoff, addr, fp); if (print_srcline) printed += map__fprintf_srcline(map, addr, "\n ", fp); @@ -209,6 +208,7 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, int print_ip = print_opts & EVSEL__PRINT_IP; int print_sym = print_opts & EVSEL__PRINT_SYM; int print_dso = print_opts & EVSEL__PRINT_DSO; + int print_dsoff = print_opts & EVSEL__PRINT_DSOFF; int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET; int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; @@ -234,11 +234,8 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, } } - if (print_dso) { - printed += fprintf(fp, " ("); - printed += map__fprintf_dsoname(al->map, fp); - printed += fprintf(fp, ")"); - } + if (print_dso) + printed += map__fprintf_dsoname_dsoff(al->map, print_dsoff, al->addr, fp); if (print_srcline) printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); diff --git a/tools/perf/util/evsel_fprintf.h b/tools/perf/util/evsel_fprintf.h index 3093d096c29f..c8a9fac2f2dd 100644 --- a/tools/perf/util/evsel_fprintf.h +++ b/tools/perf/util/evsel_fprintf.h @@ -26,6 +26,7 @@ int evsel__fprintf(struct evsel *evsel, struct perf_attr_details *details, FILE #define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) #define EVSEL__PRINT_CALLCHAIN_ARROW (1<<7) #define EVSEL__PRINT_SKIP_IGNORED (1<<8) +#define EVSEL__PRINT_DSOFF (1<<9) struct addr_location; struct perf_event_attr; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 276870221ce0..d85b39079c31 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -24,6 +24,7 @@ #include <bpf/libbpf.h> #endif #include <perf/cpumap.h> +#include <tools/libc_compat.h> // reallocarray #include "dso.h" #include "evlist.h" @@ -37,6 +38,7 @@ #include "debug.h" #include "cpumap.h" #include "pmu.h" +#include "pmus.h" #include "vdso.h" #include "strbuf.h" #include "build-id.h" @@ -51,7 +53,6 @@ #include "bpf-event.h" #include "bpf-utils.h" #include "clockid.h" -#include "pmu-hybrid.h" #include <linux/ctype.h> #include <internal/lib.h> @@ -745,7 +746,7 @@ static int write_pmu_mappings(struct feat_fd *ff, * Do a first pass to count number of pmu to avoid lseek so this * works in pipe mode as well. */ - while ((pmu = perf_pmu__scan(pmu))) { + while ((pmu = perf_pmus__scan(pmu))) { if (!pmu->name) continue; pmu_num++; @@ -755,7 +756,7 @@ static int write_pmu_mappings(struct feat_fd *ff, if (ret < 0) return ret; - while ((pmu = perf_pmu__scan(pmu))) { + while ((pmu = perf_pmus__scan(pmu))) { if (!pmu->name) continue; @@ -1213,38 +1214,54 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c) fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map); } -#define MAX_CACHE_LVL 4 - -static int build_caches(struct cpu_cache_level caches[], u32 *cntp) +/* + * Build caches levels for a particular CPU from the data in + * /sys/devices/system/cpu/cpu<cpu>/cache/ + * The cache level data is stored in caches[] from index at + * *cntp. + */ +int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp) { - u32 i, cnt = 0; - u32 nr, cpu; u16 level; - nr = cpu__max_cpu().cpu; + for (level = 0; level < MAX_CACHE_LVL; level++) { + struct cpu_cache_level c; + int err; + u32 i; - for (cpu = 0; cpu < nr; cpu++) { - for (level = 0; level < MAX_CACHE_LVL; level++) { - struct cpu_cache_level c; - int err; + err = cpu_cache_level__read(&c, cpu, level); + if (err < 0) + return err; - err = cpu_cache_level__read(&c, cpu, level); - if (err < 0) - return err; + if (err == 1) + break; - if (err == 1) + for (i = 0; i < *cntp; i++) { + if (cpu_cache_level__cmp(&c, &caches[i])) break; + } - for (i = 0; i < cnt; i++) { - if (cpu_cache_level__cmp(&c, &caches[i])) - break; - } + if (i == *cntp) { + caches[*cntp] = c; + *cntp = *cntp + 1; + } else + cpu_cache_level__free(&c); + } - if (i == cnt) - caches[cnt++] = c; - else - cpu_cache_level__free(&c); - } + return 0; +} + +static int build_caches(struct cpu_cache_level caches[], u32 *cntp) +{ + u32 nr, cpu, cnt = 0; + + nr = cpu__max_cpu().cpu; + + for (cpu = 0; cpu < nr; cpu++) { + int ret = build_caches_for_cpu(cpu, caches, &cnt); + + if (ret) + return ret; } *cntp = cnt; return 0; @@ -1380,13 +1397,14 @@ static int memory_node__sort(const void *a, const void *b) return na->node - nb->node; } -static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) +static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) { char path[PATH_MAX]; struct dirent *ent; DIR *dir; - u64 cnt = 0; int ret = 0; + size_t cnt = 0, size = 0; + struct memory_node *nodes = NULL; scnprintf(path, PATH_MAX, "%s/devices/system/node/", sysfs__mountpoint()); @@ -1410,26 +1428,32 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) if (r != 1) continue; - if (WARN_ONCE(cnt >= size, - "failed to write MEM_TOPOLOGY, way too many nodes\n")) { - closedir(dir); - return -1; - } + if (cnt >= size) { + struct memory_node *new_nodes = + reallocarray(nodes, cnt + 4, sizeof(*nodes)); + if (!new_nodes) { + pr_err("Failed to write MEM_TOPOLOGY, size %zd nodes\n", size); + ret = -ENOMEM; + goto out; + } + nodes = new_nodes; + size += 4; + } ret = memory_node__read(&nodes[cnt++], idx); } - - *cntp = cnt; +out: closedir(dir); - - if (!ret) + if (!ret) { + *cntp = cnt; + *nodesp = nodes; qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort); + } else + free(nodes); return ret; } -#define MAX_MEMORY_NODES 2000 - /* * The MEM_TOPOLOGY holds physical memory map for every * node in system. The format of data is as follows: @@ -1448,8 +1472,8 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp) static int write_mem_topology(struct feat_fd *ff __maybe_unused, struct evlist *evlist __maybe_unused) { - static struct memory_node nodes[MAX_MEMORY_NODES]; - u64 bsize, version = 1, i, nr; + struct memory_node *nodes = NULL; + u64 bsize, version = 1, i, nr = 0; int ret; ret = sysfs__read_xll("devices/system/memory/block_size_bytes", @@ -1457,7 +1481,7 @@ static int write_mem_topology(struct feat_fd *ff __maybe_unused, if (ret) return ret; - ret = build_mem_topology(&nodes[0], MAX_MEMORY_NODES, &nr); + ret = build_mem_topology(&nodes, &nr); if (ret) return ret; @@ -1492,6 +1516,7 @@ static int write_mem_topology(struct feat_fd *ff __maybe_unused, } out: + free(nodes); return ret; } @@ -1551,7 +1576,7 @@ static int __write_pmu_caps(struct feat_fd *ff, struct perf_pmu *pmu, static int write_cpu_pmu_caps(struct feat_fd *ff, struct evlist *evlist __maybe_unused) { - struct perf_pmu *cpu_pmu = perf_pmu__find("cpu"); + struct perf_pmu *cpu_pmu = perf_pmus__find("cpu"); int ret; if (!cpu_pmu) @@ -1571,7 +1596,7 @@ static int write_pmu_caps(struct feat_fd *ff, int nr_pmu = 0; int ret; - while ((pmu = perf_pmu__scan(pmu))) { + while ((pmu = perf_pmus__scan(pmu))) { if (!pmu->name || !strcmp(pmu->name, "cpu") || perf_pmu__caps_parse(pmu) <= 0) continue; @@ -1589,17 +1614,18 @@ static int write_pmu_caps(struct feat_fd *ff, * Write hybrid pmu caps first to maintain compatibility with * older perf tool. */ - pmu = NULL; - perf_pmu__for_each_hybrid_pmu(pmu) { - ret = __write_pmu_caps(ff, pmu, true); - if (ret < 0) - return ret; + if (perf_pmus__num_core_pmus() > 1) { + pmu = NULL; + while ((pmu = perf_pmus__scan_core(pmu))) { + ret = __write_pmu_caps(ff, pmu, true); + if (ret < 0) + return ret; + } } pmu = NULL; - while ((pmu = perf_pmu__scan(pmu))) { - if (!pmu->name || !strcmp(pmu->name, "cpu") || - !pmu->nr_caps || perf_pmu__is_hybrid(pmu->name)) + while ((pmu = perf_pmus__scan(pmu))) { + if (pmu->is_core || !pmu->nr_caps) continue; ret = __write_pmu_caps(ff, pmu, true); diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 59eeb4a32ac5..7c16a250e738 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -179,7 +179,11 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size); int write_padded(struct feat_fd *fd, const void *bf, size_t count, size_t count_aligned); +#define MAX_CACHE_LVL 4 + int is_cpu_online(unsigned int cpu); +int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp); + /* * arch specific callback */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index b7f890950909..4d9944bbf5e4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -431,14 +431,21 @@ size_t map__fprintf(struct map *map, FILE *fp) map__start(map), map__end(map), map__pgoff(map), dso->name); } -size_t map__fprintf_dsoname(struct map *map, FILE *fp) +static bool prefer_dso_long_name(const struct dso *dso, bool print_off) +{ + return dso->long_name && + (symbol_conf.show_kernel_path || + (print_off && (dso->name[0] == '[' || dso__is_kcore(dso)))); +} + +static size_t __map__fprintf_dsoname(struct map *map, bool print_off, FILE *fp) { char buf[symbol_conf.pad_output_len_dso + 1]; const char *dsoname = "[unknown]"; const struct dso *dso = map ? map__dso(map) : NULL; if (dso) { - if (symbol_conf.show_kernel_path && dso->long_name) + if (prefer_dso_long_name(dso, print_off)) dsoname = dso->long_name; else dsoname = dso->name; @@ -452,6 +459,27 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) return fprintf(fp, "%s", dsoname); } +size_t map__fprintf_dsoname(struct map *map, FILE *fp) +{ + return __map__fprintf_dsoname(map, false, fp); +} + +size_t map__fprintf_dsoname_dsoff(struct map *map, bool print_off, u64 addr, FILE *fp) +{ + const struct dso *dso = map ? map__dso(map) : NULL; + int printed = 0; + + if (print_off && (!dso || !dso__is_object_file(dso))) + print_off = false; + printed += fprintf(fp, " ("); + printed += __map__fprintf_dsoname(map, print_off, fp); + if (print_off) + printed += fprintf(fp, "+0x%" PRIx64, addr); + printed += fprintf(fp, ")"); + + return printed; +} + char *map__srcline(struct map *map, u64 addr, struct symbol *sym) { if (map == NULL) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 823ab7fc0acf..66a87b3d9965 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -194,6 +194,7 @@ static inline void __map__zput(struct map **map) size_t map__fprintf(struct map *map, FILE *fp); size_t map__fprintf_dsoname(struct map *map, FILE *fp); +size_t map__fprintf_dsoname_dsoff(struct map *map, bool print_off, u64 addr, FILE *fp); char *map__srcline(struct map *map, u64 addr, struct symbol *sym); int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index ed1ee4b05356..be15aadb6b14 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -13,7 +13,7 @@ #include "debug.h" #include "symbol.h" #include "pmu.h" -#include "pmu-hybrid.h" +#include "pmus.h" unsigned int perf_mem_events__loads_ldlat = 30; @@ -120,8 +120,8 @@ int perf_mem_events__init(void) for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { struct perf_mem_event *e = perf_mem_events__ptr(j); - struct perf_pmu *pmu; char sysfs_name[100]; + struct perf_pmu *pmu = NULL; /* * If the event entry isn't valid, skip initialization @@ -130,16 +130,9 @@ int perf_mem_events__init(void) if (!e->tag) continue; - if (!perf_pmu__has_hybrid()) { - scnprintf(sysfs_name, sizeof(sysfs_name), - e->sysfs_name, "cpu"); - e->supported = perf_mem_event__supported(mnt, sysfs_name); - } else { - perf_pmu__for_each_hybrid_pmu(pmu) { - scnprintf(sysfs_name, sizeof(sysfs_name), - e->sysfs_name, pmu->name); - e->supported |= perf_mem_event__supported(mnt, sysfs_name); - } + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name); + e->supported |= perf_mem_event__supported(mnt, sysfs_name); } if (e->supported) @@ -170,9 +163,9 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e, { const char *mnt = sysfs__mount(); char sysfs_name[100]; - struct perf_pmu *pmu; + struct perf_pmu *pmu = NULL; - perf_pmu__for_each_hybrid_pmu(pmu) { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name); if (!perf_mem_event__supported(mnt, sysfs_name)) { @@ -195,7 +188,7 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, if (!e->record) continue; - if (!perf_pmu__has_hybrid()) { + if (perf_pmus__num_core_pmus() == 1) { if (!e->supported) { pr_err("failed: event '%s' not supported\n", perf_mem_events__name(j, NULL)); @@ -210,7 +203,7 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, return -1; } - perf_pmu__for_each_hybrid_pmu(pmu) { + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { rec_argv[i++] = "-e"; s = perf_mem_events__name(j, pmu->name); if (s) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 5e9c657dd3f7..70ef2e23a710 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -11,7 +11,7 @@ #include "evsel.h" #include "strbuf.h" #include "pmu.h" -#include "pmu-hybrid.h" +#include "pmus.h" #include "print-events.h" #include "smt.h" #include "expr.h" @@ -123,6 +123,7 @@ struct metric { * within the expression. */ struct expr_parse_ctx *pctx; + const char *pmu; /** The name of the metric such as "IPC". */ const char *metric_name; /** Modifier on the metric such as "u" or NULL for none. */ @@ -216,6 +217,7 @@ static struct metric *metric__new(const struct pmu_metric *pm, if (!m->pctx) goto out_err; + m->pmu = pm->pmu ?: "cpu"; m->metric_name = pm->metric_name; m->modifier = NULL; if (modifier) { @@ -259,11 +261,12 @@ static bool contains_metric_id(struct evsel **metric_events, int num_events, /** * setup_metric_events - Find a group of events in metric_evlist that correspond * to the IDs from a parsed metric expression. + * @pmu: The PMU for the IDs. * @ids: the metric IDs to match. * @metric_evlist: the list of perf events. * @out_metric_events: holds the created metric events array. */ -static int setup_metric_events(struct hashmap *ids, +static int setup_metric_events(const char *pmu, struct hashmap *ids, struct evlist *metric_evlist, struct evsel ***out_metric_events) { @@ -271,6 +274,7 @@ static int setup_metric_events(struct hashmap *ids, const char *metric_id; struct evsel *ev; size_t ids_size, matched_events, i; + bool all_pmus = !strcmp(pmu, "all") || perf_pmus__num_core_pmus() == 1 || !is_pmu_core(pmu); *out_metric_events = NULL; ids_size = hashmap__size(ids); @@ -283,6 +287,10 @@ static int setup_metric_events(struct hashmap *ids, evlist__for_each_entry(metric_evlist, ev) { struct expr_id_data *val_ptr; + /* Don't match events for the wrong hybrid PMU. */ + if (!all_pmus && ev->pmu_name && evsel__is_hybrid(ev) && + strcmp(ev->pmu_name, pmu)) + continue; /* * Check for duplicate events with the same name. For * example, uncore_imc/cas_count_read/ will turn into 6 @@ -298,6 +306,7 @@ static int setup_metric_events(struct hashmap *ids, * about this event. */ if (hashmap__find(ids, metric_id, &val_ptr)) { + pr_debug("Matched metric-id %s to %s\n", metric_id, evsel__name(ev)); metric_events[matched_events++] = ev; if (matched_events >= ids_size) @@ -355,8 +364,13 @@ static bool match_metric(const char *n, const char *list) return false; } -static bool match_pm_metric(const struct pmu_metric *pm, const char *metric) +static bool match_pm_metric(const struct pmu_metric *pm, const char *pmu, const char *metric) { + const char *pm_pmu = pm->pmu ?: "cpu"; + + if (strcmp(pmu, "all") && strcmp(pm_pmu, pmu)) + return false; + return match_metric(pm->metric_group, metric) || match_metric(pm->metric_name, metric); } @@ -475,7 +489,7 @@ static int metricgroup__sys_event_iter(const struct pmu_metric *pm, if (!pm->metric_expr || !pm->compat) return 0; - while ((pmu = perf_pmu__scan(pmu))) { + while ((pmu = perf_pmus__scan(pmu))) { if (!pmu->id || strcmp(pmu->id, pm->compat)) continue; @@ -766,6 +780,7 @@ struct visited_metric { struct metricgroup_add_iter_data { struct list_head *metric_list; + const char *pmu; const char *metric_name; const char *modifier; int *ret; @@ -779,7 +794,8 @@ struct metricgroup_add_iter_data { const struct pmu_metrics_table *table; }; -static bool metricgroup__find_metric(const char *metric, +static bool metricgroup__find_metric(const char *pmu, + const char *metric, const struct pmu_metrics_table *table, struct pmu_metric *pm); @@ -798,6 +814,7 @@ static int add_metric(struct list_head *metric_list, * resolve_metric - Locate metrics within the root metric and recursively add * references to them. * @metric_list: The list the metric is added to. + * @pmu: The PMU name to resolve metrics on, or "all" for all PMUs. * @modifier: if non-null event modifiers like "u". * @metric_no_group: Should events written to events be grouped "{}" or * global. Grouping is the default but due to multiplexing the @@ -813,6 +830,7 @@ static int add_metric(struct list_head *metric_list, * architecture perf is running upon. */ static int resolve_metric(struct list_head *metric_list, + const char *pmu, const char *modifier, bool metric_no_group, bool metric_no_threshold, @@ -842,7 +860,7 @@ static int resolve_metric(struct list_head *metric_list, hashmap__for_each_entry(root_metric->pctx->ids, cur, bkt) { struct pmu_metric pm; - if (metricgroup__find_metric(cur->pkey, table, &pm)) { + if (metricgroup__find_metric(pmu, cur->pkey, table, &pm)) { pending = realloc(pending, (pending_cnt + 1) * sizeof(struct to_resolve)); if (!pending) @@ -993,9 +1011,12 @@ static int __add_metric(struct list_head *metric_list, } if (!ret) { /* Resolve referenced metrics. */ - ret = resolve_metric(metric_list, modifier, metric_no_group, + const char *pmu = pm->pmu ?: "cpu"; + + ret = resolve_metric(metric_list, pmu, modifier, metric_no_group, metric_no_threshold, user_requested_cpu_list, - system_wide, root_metric, &visited_node, table); + system_wide, root_metric, &visited_node, + table); } if (ret) { if (is_root) @@ -1008,6 +1029,7 @@ static int __add_metric(struct list_head *metric_list, } struct metricgroup__find_metric_data { + const char *pmu; const char *metric; struct pmu_metric *pm; }; @@ -1017,6 +1039,10 @@ static int metricgroup__find_metric_callback(const struct pmu_metric *pm, void *vdata) { struct metricgroup__find_metric_data *data = vdata; + const char *pm_pmu = pm->pmu ?: "cpu"; + + if (strcmp(data->pmu, "all") && strcmp(pm_pmu, data->pmu)) + return 0; if (!match_metric(pm->metric_name, data->metric)) return 0; @@ -1025,11 +1051,13 @@ static int metricgroup__find_metric_callback(const struct pmu_metric *pm, return 1; } -static bool metricgroup__find_metric(const char *metric, +static bool metricgroup__find_metric(const char *pmu, + const char *metric, const struct pmu_metrics_table *table, struct pmu_metric *pm) { struct metricgroup__find_metric_data data = { + .pmu = pmu, .metric = metric, .pm = pm, }; @@ -1083,7 +1111,7 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm, struct metricgroup_add_iter_data *d = data; int ret; - if (!match_pm_metric(pm, d->metric_name)) + if (!match_pm_metric(pm, d->pmu, d->metric_name)) return 0; ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group, @@ -1128,6 +1156,7 @@ static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l, struct metricgroup__add_metric_data { struct list_head *list; + const char *pmu; const char *metric_name; const char *modifier; const char *user_requested_cpu_list; @@ -1144,7 +1173,7 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + if (pm->metric_expr && match_pm_metric(pm, data->pmu, data->metric_name)) { bool metric_no_group = data->metric_no_group || match_metric(data->metric_name, pm->metricgroup_no_group); @@ -1159,6 +1188,7 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, /** * metricgroup__add_metric - Find and add a metric, or a metric group. + * @pmu: The PMU name to search for metrics on, or "all" for all PMUs. * @metric_name: The name of the metric or metric group. For example, "IPC" * could be the name of a metric and "TopDownL1" the name of a * metric group. @@ -1172,7 +1202,7 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, * @table: The table that is searched for metrics, most commonly the table for the * architecture perf is running upon. */ -static int metricgroup__add_metric(const char *metric_name, const char *modifier, +static int metricgroup__add_metric(const char *pmu, const char *metric_name, const char *modifier, bool metric_no_group, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, @@ -1186,6 +1216,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier { struct metricgroup__add_metric_data data = { .list = &list, + .pmu = pmu, .metric_name = metric_name, .modifier = modifier, .metric_no_group = metric_no_group, @@ -1210,6 +1241,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier .fn = metricgroup__add_metric_sys_event_iter, .data = (void *) &(struct metricgroup_add_iter_data) { .metric_list = &list, + .pmu = pmu, .metric_name = metric_name, .modifier = modifier, .metric_no_group = metric_no_group, @@ -1239,6 +1271,7 @@ out: /** * metricgroup__add_metric_list - Find and add metrics, or metric groups, * specified in a list. + * @pmu: A pmu to restrict the metrics to, or "all" for all PMUS. * @list: the list of metrics or metric groups. For example, "IPC,CPI,TopDownL1" * would match the IPC and CPI metrics, and TopDownL1 would match all * the metrics in the TopDownL1 group. @@ -1251,7 +1284,8 @@ out: * @table: The table that is searched for metrics, most commonly the table for the * architecture perf is running upon. */ -static int metricgroup__add_metric_list(const char *list, bool metric_no_group, +static int metricgroup__add_metric_list(const char *pmu, const char *list, + bool metric_no_group, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, @@ -1270,7 +1304,7 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, if (modifier) *modifier++ = '\0'; - ret = metricgroup__add_metric(metric_name, modifier, + ret = metricgroup__add_metric(pmu, metric_name, modifier, metric_no_group, metric_no_threshold, user_requested_cpu_list, system_wide, metric_list, table); @@ -1441,8 +1475,8 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, } pr_debug("Parsing metric events '%s'\n", events.buf); parse_events_error__init(&parse_error); - ret = __parse_events(parsed_evlist, events.buf, &parse_error, fake_pmu, - /*warn_if_reordered=*/false); + ret = __parse_events(parsed_evlist, events.buf, /*pmu_filter=*/NULL, + &parse_error, fake_pmu, /*warn_if_reordered=*/false); if (ret) { parse_events_error__print(&parse_error, events.buf); goto err_out; @@ -1460,7 +1494,8 @@ err_out: return ret; } -static int parse_groups(struct evlist *perf_evlist, const char *str, +static int parse_groups(struct evlist *perf_evlist, + const char *pmu, const char *str, bool metric_no_group, bool metric_no_merge, bool metric_no_threshold, @@ -1478,7 +1513,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, if (metric_events_list->nr_entries == 0) metricgroup__rblist_init(metric_events_list); - ret = metricgroup__add_metric_list(str, metric_no_group, metric_no_threshold, + ret = metricgroup__add_metric_list(pmu, str, metric_no_group, metric_no_threshold, user_requested_cpu_list, system_wide, &metric_list, table); if (ret) @@ -1535,6 +1570,11 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, strcmp(m->modifier, n->modifier))) continue; + if ((!m->pmu && n->pmu) || + (m->pmu && !n->pmu) || + (m->pmu && n->pmu && strcmp(m->pmu, n->pmu))) + continue; + if (expr__subset_of_ids(n->pctx, m->pctx)) { pr_debug("Events in '%s' fully contained within '%s'\n", m->metric_name, n->metric_name); @@ -1552,9 +1592,10 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, metric_evlist = m->evlist; } - ret = setup_metric_events(m->pctx->ids, metric_evlist, &metric_events); + ret = setup_metric_events(fake_pmu ? "all" : m->pmu, m->pctx->ids, + metric_evlist, &metric_events); if (ret) { - pr_debug("Cannot resolve IDs for %s: %s\n", + pr_err("Cannot resolve IDs for %s: %s\n", m->metric_name, m->metric_expr); goto out; } @@ -1610,6 +1651,7 @@ out: } int metricgroup__parse_groups(struct evlist *perf_evlist, + const char *pmu, const char *str, bool metric_no_group, bool metric_no_merge, @@ -1623,7 +1665,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, if (!table) return -EINVAL; - return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, + return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge, metric_no_threshold, user_requested_cpu_list, system_wide, /*fake_pmu=*/NULL, metric_events, table); } @@ -1633,7 +1675,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist, const char *str, struct rblist *metric_events) { - return parse_groups(evlist, str, + return parse_groups(evlist, "all", str, /*metric_no_group=*/false, /*metric_no_merge=*/false, /*metric_no_threshold=*/false, @@ -1642,28 +1684,32 @@ int metricgroup__parse_groups_test(struct evlist *evlist, &perf_pmu__fake, metric_events, table); } +struct metricgroup__has_metric_data { + const char *pmu; + const char *metric; +}; static int metricgroup__has_metric_callback(const struct pmu_metric *pm, const struct pmu_metrics_table *table __maybe_unused, void *vdata) { - const char *metric = vdata; - - if (match_metric(pm->metric_name, metric) || - match_metric(pm->metric_group, metric)) - return 1; + struct metricgroup__has_metric_data *data = vdata; - return 0; + return match_pm_metric(pm, data->pmu, data->metric) ? 1 : 0; } -bool metricgroup__has_metric(const char *metric) +bool metricgroup__has_metric(const char *pmu, const char *metric) { const struct pmu_metrics_table *table = pmu_metrics_table__find(); + struct metricgroup__has_metric_data data = { + .pmu = pmu, + .metric = metric, + }; if (!table) return false; - return pmu_metrics_table_for_each_metric(table, metricgroup__has_metric_callback, - (void *)metric) ? true : false; + return pmu_metrics_table_for_each_metric(table, metricgroup__has_metric_callback, &data) + ? true : false; } static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 77472e35705e..bf18274c15df 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -67,6 +67,7 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events, struct evsel *evsel, bool create); int metricgroup__parse_groups(struct evlist *perf_evlist, + const char *pmu, const char *str, bool metric_no_group, bool metric_no_merge, @@ -80,7 +81,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist, struct rblist *metric_events); void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); -bool metricgroup__has_metric(const char *metric); +bool metricgroup__has_metric(const char *pmu, const char *metric); unsigned int metricgroups__topdown_max_level(void); int arch_get_runtimeparam(const struct pmu_metric *pm); void metricgroup__rblist_exit(struct rblist *metric_events); diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c deleted file mode 100644 index 7c9f9150bad5..000000000000 --- a/tools/perf/util/parse-events-hybrid.c +++ /dev/null @@ -1,214 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/err.h> -#include <linux/zalloc.h> -#include <errno.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <sys/param.h> -#include "evlist.h" -#include "evsel.h" -#include "parse-events.h" -#include "parse-events-hybrid.h" -#include "debug.h" -#include "pmu.h" -#include "pmu-hybrid.h" -#include "perf.h" - -static void config_hybrid_attr(struct perf_event_attr *attr, - int type, int pmu_type) -{ - /* - * attr.config layout for type PERF_TYPE_HARDWARE and - * PERF_TYPE_HW_CACHE - * - * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA - * AA: hardware event ID - * EEEEEEEE: PMU type ID - * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB - * BB: hardware cache ID - * CC: hardware cache op ID - * DD: hardware cache op result ID - * EEEEEEEE: PMU type ID - * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. - */ - attr->type = type; - attr->config = (attr->config & PERF_HW_EVENT_MASK) | - ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT); -} - -static int create_event_hybrid(__u32 config_type, int *idx, - struct list_head *list, - struct perf_event_attr *attr, const char *name, - const char *metric_id, - struct list_head *config_terms, - struct perf_pmu *pmu) -{ - struct evsel *evsel; - __u32 type = attr->type; - __u64 config = attr->config; - - config_hybrid_attr(attr, config_type, pmu->type); - - /* - * Some hybrid hardware cache events are only available on one CPU - * PMU. For example, the 'L1-dcache-load-misses' is only available - * on cpu_core, while the 'L1-icache-loads' is only available on - * cpu_atom. We need to remove "not supported" hybrid cache events. - */ - if (attr->type == PERF_TYPE_HW_CACHE - && !is_event_supported(attr->type, attr->config)) - return 0; - - evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id, - pmu, config_terms); - if (evsel) { - evsel->pmu_name = strdup(pmu->name); - if (!evsel->pmu_name) - return -ENOMEM; - } else - return -ENOMEM; - attr->type = type; - attr->config = config; - return 0; -} - -static int pmu_cmp(struct parse_events_state *parse_state, - struct perf_pmu *pmu) -{ - if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name) - return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name); - - if (parse_state->hybrid_pmu_name) - return strcmp(parse_state->hybrid_pmu_name, pmu->name); - - return 0; -} - -static int add_hw_hybrid(struct parse_events_state *parse_state, - struct list_head *list, struct perf_event_attr *attr, - const char *name, const char *metric_id, - struct list_head *config_terms) -{ - struct perf_pmu *pmu; - int ret; - - perf_pmu__for_each_hybrid_pmu(pmu) { - LIST_HEAD(terms); - - if (pmu_cmp(parse_state, pmu)) - continue; - - copy_config_terms(&terms, config_terms); - ret = create_event_hybrid(PERF_TYPE_HARDWARE, - &parse_state->idx, list, attr, name, - metric_id, &terms, pmu); - free_config_terms(&terms); - if (ret) - return ret; - } - - return 0; -} - -static int create_raw_event_hybrid(int *idx, struct list_head *list, - struct perf_event_attr *attr, - const char *name, - const char *metric_id, - struct list_head *config_terms, - struct perf_pmu *pmu) -{ - struct evsel *evsel; - - attr->type = pmu->type; - evsel = parse_events__add_event_hybrid(list, idx, attr, name, metric_id, - pmu, config_terms); - if (evsel) - evsel->pmu_name = strdup(pmu->name); - else - return -ENOMEM; - - return 0; -} - -static int add_raw_hybrid(struct parse_events_state *parse_state, - struct list_head *list, struct perf_event_attr *attr, - const char *name, const char *metric_id, - struct list_head *config_terms) -{ - struct perf_pmu *pmu; - int ret; - - perf_pmu__for_each_hybrid_pmu(pmu) { - LIST_HEAD(terms); - - if (pmu_cmp(parse_state, pmu)) - continue; - - copy_config_terms(&terms, config_terms); - ret = create_raw_event_hybrid(&parse_state->idx, list, attr, - name, metric_id, &terms, pmu); - free_config_terms(&terms); - if (ret) - return ret; - } - - return 0; -} - -int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, - struct list_head *list, - struct perf_event_attr *attr, - const char *name, const char *metric_id, - struct list_head *config_terms, - bool *hybrid) -{ - *hybrid = false; - if (attr->type == PERF_TYPE_SOFTWARE) - return 0; - - if (!perf_pmu__has_hybrid()) - return 0; - - *hybrid = true; - if (attr->type != PERF_TYPE_RAW) { - return add_hw_hybrid(parse_state, list, attr, name, metric_id, - config_terms); - } - - return add_raw_hybrid(parse_state, list, attr, name, metric_id, - config_terms); -} - -int parse_events__add_cache_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, - const char *name, - const char *metric_id, - struct list_head *config_terms, - bool *hybrid, - struct parse_events_state *parse_state) -{ - struct perf_pmu *pmu; - int ret; - - *hybrid = false; - if (!perf_pmu__has_hybrid()) - return 0; - - *hybrid = true; - perf_pmu__for_each_hybrid_pmu(pmu) { - LIST_HEAD(terms); - - if (pmu_cmp(parse_state, pmu)) - continue; - - copy_config_terms(&terms, config_terms); - ret = create_event_hybrid(PERF_TYPE_HW_CACHE, idx, list, - attr, name, metric_id, &terms, pmu); - free_config_terms(&terms); - if (ret) - return ret; - } - - return 0; -} diff --git a/tools/perf/util/parse-events-hybrid.h b/tools/perf/util/parse-events-hybrid.h deleted file mode 100644 index cbc05fec02a2..000000000000 --- a/tools/perf/util/parse-events-hybrid.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PERF_PARSE_EVENTS_HYBRID_H -#define __PERF_PARSE_EVENTS_HYBRID_H - -#include <linux/list.h> -#include <stdbool.h> -#include <linux/types.h> -#include <linux/perf_event.h> -#include <string.h> - -int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, - struct list_head *list, - struct perf_event_attr *attr, - const char *name, const char *metric_id, - struct list_head *config_terms, - bool *hybrid); - -int parse_events__add_cache_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, - const char *name, const char *metric_id, - struct list_head *config_terms, - bool *hybrid, - struct parse_events_state *parse_state); - -#endif /* __PERF_PARSE_EVENTS_HYBRID_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 34ba840ae19a..7f047ac11168 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -21,42 +21,23 @@ #include "parse-events-bison.h" #include "parse-events-flex.h" #include "pmu.h" +#include "pmus.h" #include "asm/bug.h" #include "util/parse-branch-options.h" #include "util/evsel_config.h" #include "util/event.h" -#include "util/parse-events-hybrid.h" -#include "util/pmu-hybrid.h" #include "util/bpf-filter.h" #include "util/util.h" #include "tracepoint.h" -#include "thread_map.h" #define MAX_NAME_LEN 100 -struct perf_pmu_event_symbol { - char *symbol; - enum perf_pmu_event_symbol_type type; -}; - #ifdef PARSER_DEBUG extern int parse_events_debug; #endif int parse_events_parse(void *parse_state, void *scanner); static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused); -static int parse_events__with_hybrid_pmu(struct parse_events_state *parse_state, - const char *str, char *pmu_name, - struct list_head *list); - -static struct perf_pmu_event_symbol *perf_pmu_events_list; -/* - * The variable indicates the number of supported pmu event symbols. - * 0 means not initialized and ready to init - * -1 means failed to init, don't try anymore - * >0 is the number of supported pmu event symbols - */ -static int perf_pmu_events_list_num; struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { @@ -152,44 +133,6 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { }, }; -bool is_event_supported(u8 type, u64 config) -{ - bool ret = true; - int open_return; - struct evsel *evsel; - struct perf_event_attr attr = { - .type = type, - .config = config, - .disabled = 1, - }; - struct perf_thread_map *tmap = thread_map__new_by_tid(0); - - if (tmap == NULL) - return false; - - evsel = evsel__new(&attr); - if (evsel) { - open_return = evsel__open(evsel, NULL, tmap); - ret = open_return >= 0; - - if (open_return == -EACCES) { - /* - * This happens if the paranoid value - * /proc/sys/kernel/perf_event_paranoid is set to 2 - * Re-run with exclude_kernel set; we don't do that - * by default as some ARM machines do not support it. - * - */ - evsel->core.attr.exclude_kernel = 1; - ret = evsel__open(evsel, NULL, tmap) >= 0; - } - evsel__delete(evsel); - } - - perf_thread_map__put(tmap); - return ret; -} - const char *event_type(int type) { switch (type) { @@ -236,6 +179,57 @@ static char *get_config_name(struct list_head *head_terms) return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME); } +/** + * fix_raw - For each raw term see if there is an event (aka alias) in pmu that + * matches the raw's string value. If the string value matches an + * event then change the term to be an event, if not then change it to + * be a config term. For example, "read" may be an event of the PMU or + * a raw hex encoding of 0xead. The fix-up is done late so the PMU of + * the event can be determined and we don't need to scan all PMUs + * ahead-of-time. + * @config_terms: the list of terms that may contain a raw term. + * @pmu: the PMU to scan for events from. + */ +static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu) +{ + struct parse_events_term *term; + + list_for_each_entry(term, config_terms, list) { + struct perf_pmu_alias *alias; + bool matched = false; + + if (term->type_term != PARSE_EVENTS__TERM_TYPE_RAW) + continue; + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcmp(alias->name, term->val.str)) { + free(term->config); + term->config = term->val.str; + term->type_val = PARSE_EVENTS__TERM_TYPE_NUM; + term->type_term = PARSE_EVENTS__TERM_TYPE_USER; + term->val.num = 1; + term->no_value = true; + matched = true; + break; + } + } + if (!matched) { + u64 num; + + free(term->config); + term->config = strdup("config"); + errno = 0; + num = strtoull(term->val.str + 1, NULL, 16); + assert(errno == 0); + free(term->val.str); + term->type_val = PARSE_EVENTS__TERM_TYPE_NUM; + term->type_term = PARSE_EVENTS__TERM_TYPE_CONFIG; + term->val.num = num; + term->no_value = false; + } + } +} + static struct evsel * __add_event(struct list_head *list, int *idx, struct perf_event_attr *attr, @@ -267,8 +261,10 @@ __add_event(struct list_head *list, int *idx, evsel->core.cpus = cpus; evsel->core.own_cpus = perf_cpu_map__get(cpus); evsel->core.requires_cpu = pmu ? pmu->is_uncore : false; + evsel->core.is_pmu_core = pmu ? pmu->is_core : false; evsel->auto_merge_stats = auto_merge_stats; evsel->pmu = pmu; + evsel->pmu_name = pmu && pmu->name ? strdup(pmu->name) : NULL; if (name) evsel->name = strdup(name); @@ -328,18 +324,27 @@ static int add_event_tool(struct list_head *list, int *idx, return 0; } -static int parse_aliases(char *str, const char *const names[][EVSEL__MAX_ALIASES], int size) +/** + * parse_aliases - search names for entries beginning or equalling str ignoring + * case. If mutliple entries in names match str then the longest + * is chosen. + * @str: The needle to look for. + * @names: The haystack to search. + * @size: The size of the haystack. + * @longest: Out argument giving the length of the matching entry. + */ +static int parse_aliases(const char *str, const char *const names[][EVSEL__MAX_ALIASES], int size, + int *longest) { - int i, j; - int n, longest = -1; + *longest = -1; + for (int i = 0; i < size; i++) { + for (int j = 0; j < EVSEL__MAX_ALIASES && names[i][j]; j++) { + int n = strlen(names[i][j]); - for (i = 0; i < size; i++) { - for (j = 0; j < EVSEL__MAX_ALIASES && names[i][j]; j++) { - n = strlen(names[i][j]); - if (n > longest && !strncasecmp(str, names[i][j], n)) - longest = n; + if (n > *longest && !strncasecmp(str, names[i][j], n)) + *longest = n; } - if (longest > 0) + if (*longest > 0) return i; } @@ -357,52 +362,52 @@ static int config_attr(struct perf_event_attr *attr, struct parse_events_error *err, config_term_func_t config_term); -int parse_events_add_cache(struct list_head *list, int *idx, - char *type, char *op_result1, char *op_result2, - struct parse_events_error *err, - struct list_head *head_config, - struct parse_events_state *parse_state) +/** + * parse_events__decode_legacy_cache - Search name for the legacy cache event + * name composed of 1, 2 or 3 hyphen + * separated sections. The first section is + * the cache type while the others are the + * optional op and optional result. To make + * life hard the names in the table also + * contain hyphens and the longest name + * should always be selected. + */ +int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config) { - struct perf_event_attr attr; - LIST_HEAD(config_terms); - char name[MAX_NAME_LEN]; - const char *config_name, *metric_id; - int cache_type = -1, cache_op = -1, cache_result = -1; - char *op_result[2] = { op_result1, op_result2 }; - int i, n, ret; - bool hybrid; + int len, cache_type = -1, cache_op = -1, cache_result = -1; + const char *name_end = &name[strlen(name) + 1]; + const char *str = name; - /* - * No fallback - if we cannot get a clear cache type - * then bail out: - */ - cache_type = parse_aliases(type, evsel__hw_cache, PERF_COUNT_HW_CACHE_MAX); + cache_type = parse_aliases(str, evsel__hw_cache, PERF_COUNT_HW_CACHE_MAX, &len); if (cache_type == -1) return -EINVAL; - - config_name = get_config_name(head_config); - n = snprintf(name, MAX_NAME_LEN, "%s", type); - - for (i = 0; (i < 2) && (op_result[i]); i++) { - char *str = op_result[i]; - - n += snprintf(name + n, MAX_NAME_LEN - n, "-%s", str); - - if (cache_op == -1) { + str += len + 1; + + if (str < name_end) { + cache_op = parse_aliases(str, evsel__hw_cache_op, + PERF_COUNT_HW_CACHE_OP_MAX, &len); + if (cache_op >= 0) { + if (!evsel__is_cache_op_valid(cache_type, cache_op)) + return -EINVAL; + str += len + 1; + } else { + cache_result = parse_aliases(str, evsel__hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX, &len); + if (cache_result >= 0) + str += len + 1; + } + } + if (str < name_end) { + if (cache_op < 0) { cache_op = parse_aliases(str, evsel__hw_cache_op, - PERF_COUNT_HW_CACHE_OP_MAX); + PERF_COUNT_HW_CACHE_OP_MAX, &len); if (cache_op >= 0) { if (!evsel__is_cache_op_valid(cache_type, cache_op)) return -EINVAL; - continue; } - } - - if (cache_result == -1) { + } else if (cache_result < 0) { cache_result = parse_aliases(str, evsel__hw_cache_result, - PERF_COUNT_HW_CACHE_RESULT_MAX); - if (cache_result >= 0) - continue; + PERF_COUNT_HW_CACHE_RESULT_MAX, &len); } } @@ -418,33 +423,70 @@ int parse_events_add_cache(struct list_head *list, int *idx, if (cache_result == -1) cache_result = PERF_COUNT_HW_CACHE_RESULT_ACCESS; - memset(&attr, 0, sizeof(attr)); - attr.config = cache_type | (cache_op << 8) | (cache_result << 16); - attr.type = PERF_TYPE_HW_CACHE; + *config = ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT) | + cache_type | (cache_op << 8) | (cache_result << 16); + return 0; +} - if (head_config) { - if (config_attr(&attr, head_config, err, - config_term_common)) - return -EINVAL; +/** + * parse_events__filter_pmu - returns false if a wildcard PMU should be + * considered, true if it should be filtered. + */ +bool parse_events__filter_pmu(const struct parse_events_state *parse_state, + const struct perf_pmu *pmu) +{ + if (parse_state->pmu_filter == NULL) + return false; - if (get_config_terms(head_config, &config_terms)) + if (pmu->name == NULL) + return true; + + return strcmp(parse_state->pmu_filter, pmu->name) != 0; +} + +int parse_events_add_cache(struct list_head *list, int *idx, const char *name, + struct parse_events_state *parse_state, + struct list_head *head_config) +{ + struct perf_pmu *pmu = NULL; + bool found_supported = false; + const char *config_name = get_config_name(head_config); + const char *metric_id = get_config_metric_id(head_config); + + /* Legacy cache events are only supported by core PMUs. */ + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + LIST_HEAD(config_terms); + struct perf_event_attr attr; + int ret; + + if (parse_events__filter_pmu(parse_state, pmu)) + continue; + + memset(&attr, 0, sizeof(attr)); + attr.type = PERF_TYPE_HW_CACHE; + + ret = parse_events__decode_legacy_cache(name, pmu->type, &attr.config); + if (ret) + return ret; + + found_supported = true; + + if (head_config) { + if (config_attr(&attr, head_config, parse_state->error, config_term_common)) + return -EINVAL; + + if (get_config_terms(head_config, &config_terms)) + return -ENOMEM; + } + + if (__add_event(list, idx, &attr, /*init_attr*/true, config_name ?: name, + metric_id, pmu, &config_terms, /*auto_merge_stats=*/false, + /*cpu_list=*/NULL) == NULL) return -ENOMEM; - } - metric_id = get_config_metric_id(head_config); - ret = parse_events__add_cache_hybrid(list, idx, &attr, - config_name ? : name, - metric_id, - &config_terms, - &hybrid, parse_state); - if (hybrid) - goto out_free_terms; - - ret = add_event(list, idx, &attr, config_name ? : name, metric_id, - &config_terms); -out_free_terms: - free_config_terms(&config_terms); - return ret; + free_config_terms(&config_terms); + } + return found_supported ? 0 : -EINVAL; } #ifdef HAVE_LIBTRACEEVENT @@ -968,6 +1010,9 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] = "aux-output", [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] = "aux-sample-size", [PARSE_EVENTS__TERM_TYPE_METRIC_ID] = "metric-id", + [PARSE_EVENTS__TERM_TYPE_RAW] = "raw", + [PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE] = "legacy-cache", + [PARSE_EVENTS__TERM_TYPE_HARDWARE] = "hardware", }; static bool config_term_shrinked; @@ -1089,6 +1134,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_METRIC_ID: CHECK_TYPE_VAL(STR); break; + case PARSE_EVENTS__TERM_TYPE_RAW: + CHECK_TYPE_VAL(STR); + break; case PARSE_EVENTS__TERM_TYPE_MAX_STACK: CHECK_TYPE_VAL(NUM); break; @@ -1142,15 +1190,36 @@ static int config_term_pmu(struct perf_event_attr *attr, struct parse_events_term *term, struct parse_events_error *err) { + if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) { + const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + + if (perf_pmu__supports_legacy_cache(pmu)) { + attr->type = PERF_TYPE_HW_CACHE; + return parse_events__decode_legacy_cache(term->config, pmu->type, + &attr->config); + } else + term->type_term = PARSE_EVENTS__TERM_TYPE_USER; + } + if (term->type_term == PARSE_EVENTS__TERM_TYPE_HARDWARE) { + const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + + if (!pmu) { + pr_debug("Failed to find PMU for type %d", attr->type); + return -EINVAL; + } + attr->type = PERF_TYPE_HARDWARE; + attr->config = ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT) | term->val.num; + return 0; + } if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER || - term->type_term == PARSE_EVENTS__TERM_TYPE_DRV_CFG) + term->type_term == PARSE_EVENTS__TERM_TYPE_DRV_CFG) { /* * Always succeed for sysfs terms, as we dont know * at this point what type they need to have. */ return 0; - else - return config_term_common(attr, term, err); + } + return config_term_common(attr, term, err); } #ifdef HAVE_LIBTRACEEVENT @@ -1364,15 +1433,14 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, #endif } -int parse_events_add_numeric(struct parse_events_state *parse_state, - struct list_head *list, - u32 type, u64 config, - struct list_head *head_config) +static int __parse_events_add_numeric(struct parse_events_state *parse_state, + struct list_head *list, + struct perf_pmu *pmu, u32 type, u64 config, + struct list_head *head_config) { struct perf_event_attr attr; LIST_HEAD(config_terms); const char *name, *metric_id; - bool hybrid; int ret; memset(&attr, 0, sizeof(attr)); @@ -1390,19 +1458,42 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, name = get_config_name(head_config); metric_id = get_config_metric_id(head_config); - ret = parse_events__add_numeric_hybrid(parse_state, list, &attr, - name, metric_id, - &config_terms, &hybrid); - if (hybrid) - goto out_free_terms; - - ret = add_event(list, &parse_state->idx, &attr, name, metric_id, - &config_terms); -out_free_terms: + ret = __add_event(list, &parse_state->idx, &attr, /*init_attr*/true, name, + metric_id, pmu, &config_terms, /*auto_merge_stats=*/false, + /*cpu_list=*/NULL) ? 0 : -ENOMEM; free_config_terms(&config_terms); return ret; } +int parse_events_add_numeric(struct parse_events_state *parse_state, + struct list_head *list, + u32 type, u64 config, + struct list_head *head_config, + bool wildcard) +{ + struct perf_pmu *pmu = NULL; + bool found_supported = false; + + if (!wildcard) + return __parse_events_add_numeric(parse_state, list, /*pmu=*/NULL, + type, config, head_config); + + /* Wildcards on numeric values are only supported by core PMUs. */ + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + int ret; + + if (parse_events__filter_pmu(parse_state, pmu)) + continue; + + found_supported = true; + ret = __parse_events_add_numeric(parse_state, list, pmu, pmu->type, + config, head_config); + if (ret) + return ret; + } + return found_supported ? 0 : -EINVAL; +} + int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, int tool_event) @@ -1422,33 +1513,6 @@ static bool config_term_percore(struct list_head *config_terms) return false; } -static int parse_events__inside_hybrid_pmu(struct parse_events_state *parse_state, - struct list_head *list, char *name, - struct list_head *head_config) -{ - struct parse_events_term *term; - int ret = -1; - - if (parse_state->fake_pmu || !head_config || list_empty(head_config) || - !perf_pmu__is_hybrid(name)) { - return -1; - } - - /* - * More than one term in list. - */ - if (head_config->next && head_config->next->next != head_config) - return -1; - - term = list_first_entry(head_config, struct parse_events_term, list); - if (term && term->config && strcmp(term->config, "event")) { - ret = parse_events__with_hybrid_pmu(parse_state, term->config, - name, list); - } - - return ret; -} - int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, @@ -1461,7 +1525,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, struct parse_events_error *err = parse_state->error; LIST_HEAD(config_terms); - pmu = parse_state->fake_pmu ?: perf_pmu__find(name); + pmu = parse_state->fake_pmu ?: perf_pmus__find(name); if (verbose > 1 && !(pmu && pmu->selectable)) { fprintf(stderr, "Attempting to add event pmu '%s' with '", @@ -1485,6 +1549,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, parse_events_error__handle(err, 0, err_str, NULL); return -EINVAL; } + if (head_config) + fix_raw(head_config, pmu); if (pmu->default_config) { memcpy(&attr, pmu->default_config, @@ -1492,20 +1558,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, } else { memset(&attr, 0, sizeof(attr)); } + attr.type = pmu->type; if (!head_config) { - attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, /*name=*/NULL, /*metric_id=*/NULL, pmu, /*config_terms=*/NULL, auto_merge_stats, /*cpu_list=*/NULL); - if (evsel) { - evsel->pmu_name = name ? strdup(name) : NULL; - return 0; - } else { - return -ENOMEM; - } + return evsel ? 0 : -ENOMEM; } if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info)) @@ -1541,11 +1602,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms)) return -ENOMEM; - if (!parse_events__inside_hybrid_pmu(parse_state, list, name, - head_config)) { - return 0; - } - if (!parse_state->fake_pmu && perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { free_config_terms(&config_terms); return -EINVAL; @@ -1561,7 +1617,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (evsel->name) evsel->use_config_name = true; - evsel->pmu_name = name ? strdup(name) : NULL; evsel->percore = config_term_percore(&evsel->config_terms); if (parse_state->fake_pmu) @@ -1615,15 +1670,21 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, INIT_LIST_HEAD(list); - while ((pmu = perf_pmu__scan(pmu)) != NULL) { + while ((pmu = perf_pmus__scan(pmu)) != NULL) { struct perf_pmu_alias *alias; + bool auto_merge_stats; + + if (parse_events__filter_pmu(parse_state, pmu)) + continue; + + auto_merge_stats = perf_pmu__auto_merge_stats(pmu); list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, pmu->name, orig_head, - /*auto_merge_stats=*/true)) { + auto_merge_stats)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1875,180 +1936,6 @@ int parse_events_name(struct list_head *list, const char *name) return 0; } -static int -comp_pmu(const void *p1, const void *p2) -{ - struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1; - struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2; - - return strcasecmp(pmu1->symbol, pmu2->symbol); -} - -static void perf_pmu__parse_cleanup(void) -{ - if (perf_pmu_events_list_num > 0) { - struct perf_pmu_event_symbol *p; - int i; - - for (i = 0; i < perf_pmu_events_list_num; i++) { - p = perf_pmu_events_list + i; - zfree(&p->symbol); - } - zfree(&perf_pmu_events_list); - perf_pmu_events_list_num = 0; - } -} - -#define SET_SYMBOL(str, stype) \ -do { \ - p->symbol = str; \ - if (!p->symbol) \ - goto err; \ - p->type = stype; \ -} while (0) - -/* - * Read the pmu events list from sysfs - * Save it into perf_pmu_events_list - */ -static void perf_pmu__parse_init(void) -{ - - struct perf_pmu *pmu = NULL; - struct perf_pmu_alias *alias; - int len = 0; - - pmu = NULL; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - list_for_each_entry(alias, &pmu->aliases, list) { - char *tmp = strchr(alias->name, '-'); - - if (tmp) { - char *tmp2 = NULL; - - tmp2 = strchr(tmp + 1, '-'); - len++; - if (tmp2) - len++; - } - - len++; - } - } - - if (len == 0) { - perf_pmu_events_list_num = -1; - return; - } - perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len); - if (!perf_pmu_events_list) - return; - perf_pmu_events_list_num = len; - - len = 0; - pmu = NULL; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - list_for_each_entry(alias, &pmu->aliases, list) { - struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; - char *tmp = strchr(alias->name, '-'); - char *tmp2 = NULL; - - if (tmp) - tmp2 = strchr(tmp + 1, '-'); - if (tmp2) { - SET_SYMBOL(strndup(alias->name, tmp - alias->name), - PMU_EVENT_SYMBOL_PREFIX); - p++; - tmp++; - SET_SYMBOL(strndup(tmp, tmp2 - tmp), PMU_EVENT_SYMBOL_SUFFIX); - p++; - SET_SYMBOL(strdup(++tmp2), PMU_EVENT_SYMBOL_SUFFIX2); - len += 3; - } else if (tmp) { - SET_SYMBOL(strndup(alias->name, tmp - alias->name), - PMU_EVENT_SYMBOL_PREFIX); - p++; - SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); - len += 2; - } else { - SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); - len++; - } - } - } - qsort(perf_pmu_events_list, len, - sizeof(struct perf_pmu_event_symbol), comp_pmu); - - return; -err: - perf_pmu__parse_cleanup(); -} - -/* - * This function injects special term in - * perf_pmu_events_list so the test code - * can check on this functionality. - */ -int perf_pmu__test_parse_init(void) -{ - struct perf_pmu_event_symbol *list, *tmp, symbols[] = { - {(char *)"read", PMU_EVENT_SYMBOL}, - {(char *)"event", PMU_EVENT_SYMBOL_PREFIX}, - {(char *)"two", PMU_EVENT_SYMBOL_SUFFIX}, - {(char *)"hyphen", PMU_EVENT_SYMBOL_SUFFIX}, - {(char *)"hyph", PMU_EVENT_SYMBOL_SUFFIX2}, - }; - unsigned long i, j; - - tmp = list = malloc(sizeof(*list) * ARRAY_SIZE(symbols)); - if (!list) - return -ENOMEM; - - for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { - tmp->type = symbols[i].type; - tmp->symbol = strdup(symbols[i].symbol); - if (!tmp->symbol) - goto err_free; - } - - perf_pmu_events_list = list; - perf_pmu_events_list_num = ARRAY_SIZE(symbols); - - qsort(perf_pmu_events_list, ARRAY_SIZE(symbols), - sizeof(struct perf_pmu_event_symbol), comp_pmu); - return 0; - -err_free: - for (j = 0, tmp = list; j < i; j++, tmp++) - zfree(&tmp->symbol); - free(list); - return -ENOMEM; -} - -enum perf_pmu_event_symbol_type -perf_pmu__parse_check(const char *name) -{ - struct perf_pmu_event_symbol p, *r; - - /* scan kernel pmu events from sysfs if needed */ - if (perf_pmu_events_list_num == 0) - perf_pmu__parse_init(); - /* - * name "cpu" could be prefix of cpu-cycles or cpu// events. - * cpu-cycles has been handled by hardcode. - * So it must be cpu// events, not kernel pmu event. - */ - if ((perf_pmu_events_list_num <= 0) || !strcmp(name, "cpu")) - return PMU_EVENT_SYMBOL_ERR; - - p.symbol = strdup(name); - r = bsearch(&p, perf_pmu_events_list, - (size_t) perf_pmu_events_list_num, - sizeof(struct perf_pmu_event_symbol), comp_pmu); - zfree(&p.symbol); - return r ? r->type : PMU_EVENT_SYMBOL_ERR; -} - static int parse_events__scanner(const char *str, struct parse_events_state *parse_state) { @@ -2086,7 +1973,6 @@ int parse_events_terms(struct list_head *terms, const char *str) int ret; ret = parse_events__scanner(str, &parse_state); - perf_pmu__parse_cleanup(); if (!ret) { list_splice(parse_state.terms, terms); @@ -2098,31 +1984,40 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -static int parse_events__with_hybrid_pmu(struct parse_events_state *parse_state, - const char *str, char *pmu_name, - struct list_head *list) +static int evsel__compute_group_pmu_name(struct evsel *evsel, + const struct list_head *head) { - struct parse_events_state ps = { - .list = LIST_HEAD_INIT(ps.list), - .stoken = PE_START_EVENTS, - .hybrid_pmu_name = pmu_name, - .idx = parse_state->idx, - }; - int ret; - - ret = parse_events__scanner(str, &ps); - perf_pmu__parse_cleanup(); + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; + const char *group_pmu_name = evsel->pmu_name ?: "cpu"; - if (!ret) { - if (!list_empty(&ps.list)) { - list_splice(&ps.list, list); - parse_state->idx = ps.idx; - return 0; - } else - return -1; + /* + * Software events may be in a group with other uncore PMU events. Use + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. + * + * Aux event leaders, like intel_pt, expect a group with events from + * other PMUs, so substitute the AUX event's PMU in this case. + */ + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* + * Starting with the leader, find the first event with a named + * PMU. for_each_group_(member|evsel) isn't used as the list + * isn't yet sorted putting evsel's in the same group together. + */ + if (leader->pmu_name) { + group_pmu_name = leader->pmu_name; + } else if (leader->core.nr_members > 1) { + list_for_each_entry(pos, head, core.node) { + if (evsel__leader(pos) == leader && pos->pmu_name) { + group_pmu_name = pos->pmu_name; + break; + } + } + } } - - return ret; + evsel->group_pmu_name = strdup(group_pmu_name); + return evsel->group_pmu_name ? 0 : -ENOMEM; } __weak int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) @@ -2144,7 +2039,11 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list /* * First sort by grouping/leader. Read the leader idx only if the evsel - * is part of a group, as -1 indicates no group. + * is part of a group, by default ungrouped events will be sorted + * relative to grouped events based on where the first ungrouped event + * occurs. If both events don't have a group we want to fall-through to + * the arch specific sorting, that can reorder and fix things like + * Intel's topdown events. */ if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { lhs_has_group = true; @@ -2160,8 +2059,8 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list /* Group by PMU if there is a group. Groups can't span PMUs. */ if (lhs_has_group && rhs_has_group) { - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); + lhs_pmu_name = lhs->group_pmu_name; + rhs_pmu_name = rhs->group_pmu_name; ret = strcmp(lhs_pmu_name, rhs_pmu_name); if (ret) return ret; @@ -2171,13 +2070,14 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list return arch_evlist__cmp(lhs, rhs); } -static bool parse_events__sort_events_and_fix_groups(struct list_head *list) +static int parse_events__sort_events_and_fix_groups(struct list_head *list) { int idx = 0, unsorted_idx = -1; struct evsel *pos, *cur_leader = NULL; struct perf_evsel *cur_leaders_grp = NULL; bool idx_changed = false; int orig_num_leaders = 0, num_leaders = 0; + int ret; /* * Compute index to insert ungrouped events at. Place them where the @@ -2186,6 +2086,10 @@ static bool parse_events__sort_events_and_fix_groups(struct list_head *list) list_for_each_entry(pos, list, core.node) { const struct evsel *pos_leader = evsel__leader(pos); + ret = evsel__compute_group_pmu_name(pos, list); + if (ret) + return ret; + if (pos == pos_leader) orig_num_leaders++; @@ -2210,7 +2114,7 @@ static bool parse_events__sort_events_and_fix_groups(struct list_head *list) idx = 0; list_for_each_entry(pos, list, core.node) { const struct evsel *pos_leader = evsel__leader(pos); - const char *pos_pmu_name = evsel__group_pmu_name(pos); + const char *pos_pmu_name = pos->group_pmu_name; const char *cur_leader_pmu_name, *pos_leader_pmu_name; bool force_grouped = arch_evsel__must_be_in_group(pos); @@ -2227,7 +2131,7 @@ static bool parse_events__sort_events_and_fix_groups(struct list_head *list) if (!cur_leader) cur_leader = pos; - cur_leader_pmu_name = evsel__group_pmu_name(cur_leader); + cur_leader_pmu_name = cur_leader->group_pmu_name; if ((cur_leaders_grp != pos->core.leader && !force_grouped) || strcmp(cur_leader_pmu_name, pos_pmu_name)) { /* Event is for a different group/PMU than last. */ @@ -2239,7 +2143,7 @@ static bool parse_events__sort_events_and_fix_groups(struct list_head *list) */ cur_leaders_grp = pos->core.leader; } - pos_leader_pmu_name = evsel__group_pmu_name(pos_leader); + pos_leader_pmu_name = pos_leader->group_pmu_name; if (strcmp(pos_leader_pmu_name, pos_pmu_name) || force_grouped) { /* * Event's PMU differs from its leader's. Groups can't @@ -2256,10 +2160,10 @@ static bool parse_events__sort_events_and_fix_groups(struct list_head *list) num_leaders++; pos_leader->core.nr_members++; } - return idx_changed || num_leaders != orig_num_leaders; + return (idx_changed || num_leaders != orig_num_leaders) ? 1 : 0; } -int __parse_events(struct evlist *evlist, const char *str, +int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filter, struct parse_events_error *err, struct perf_pmu *fake_pmu, bool warn_if_reordered) { @@ -2270,19 +2174,23 @@ int __parse_events(struct evlist *evlist, const char *str, .evlist = evlist, .stoken = PE_START_EVENTS, .fake_pmu = fake_pmu, + .pmu_filter = pmu_filter, + .match_legacy_cache_terms = true, }; - int ret; + int ret, ret2; ret = parse_events__scanner(str, &parse_state); - perf_pmu__parse_cleanup(); if (!ret && list_empty(&parse_state.list)) { WARN_ONCE(true, "WARNING: event parser found nothing\n"); return -1; } - if (parse_events__sort_events_and_fix_groups(&parse_state.list) && - warn_if_reordered && !parse_state.wild_card_pmus) + ret2 = parse_events__sort_events_and_fix_groups(&parse_state.list); + if (ret2 < 0) + return ret; + + if (ret2 && warn_if_reordered && !parse_state.wild_card_pmus) pr_warning("WARNING: events were regrouped to match PMUs\n"); /* @@ -2451,12 +2359,13 @@ void parse_events_error__print(struct parse_events_error *err, int parse_events_option(const struct option *opt, const char *str, int unset __maybe_unused) { - struct evlist *evlist = *(struct evlist **)opt->value; + struct parse_events_option_args *args = opt->value; struct parse_events_error err; int ret; parse_events_error__init(&err); - ret = parse_events(evlist, str, &err); + ret = __parse_events(*args->evlistp, str, args->pmu_filter, &err, + /*fake_pmu=*/NULL, /*warn_if_reordered=*/true); if (ret) { parse_events_error__print(&err, str); @@ -2469,22 +2378,21 @@ int parse_events_option(const struct option *opt, const char *str, int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset) { - struct evlist **evlistp = opt->value; + struct parse_events_option_args *args = opt->value; int ret; - if (*evlistp == NULL) { - *evlistp = evlist__new(); + if (*args->evlistp == NULL) { + *args->evlistp = evlist__new(); - if (*evlistp == NULL) { + if (*args->evlistp == NULL) { fprintf(stderr, "Not enough memory to create evlist\n"); return -1; } } - ret = parse_events_option(opt, str, unset); if (ret) { - evlist__delete(*evlistp); - *evlistp = NULL; + evlist__delete(*args->evlistp); + *args->evlistp = NULL; } return ret; @@ -2546,7 +2454,7 @@ static int set_filter(struct evsel *evsel, const void *arg) return 0; } - while ((pmu = perf_pmu__scan(pmu)) != NULL) + while ((pmu = perf_pmus__scan(pmu)) != NULL) if (pmu->type == evsel->core.attr.type) { found = true; break; @@ -2682,29 +2590,13 @@ int parse_events_term__str(struct parse_events_term **term, return new_term(term, &temp, str, 0); } -int parse_events_term__sym_hw(struct parse_events_term **term, - char *config, unsigned idx) +int parse_events_term__term(struct parse_events_term **term, + int term_lhs, int term_rhs, + void *loc_term, void *loc_val) { - struct event_symbol *sym; - char *str; - struct parse_events_term temp = { - .type_val = PARSE_EVENTS__TERM_TYPE_STR, - .type_term = PARSE_EVENTS__TERM_TYPE_USER, - .config = config, - }; - - if (!temp.config) { - temp.config = strdup("event"); - if (!temp.config) - return -ENOMEM; - } - BUG_ON(idx >= PERF_COUNT_HW_MAX); - sym = &event_symbols_hw[idx]; - - str = strdup(sym->symbol); - if (!str) - return -ENOMEM; - return new_term(term, &temp, str, 0); + return parse_events_term__str(term, term_lhs, NULL, + strdup(config_term_names[term_rhs]), + loc_term, loc_val); } int parse_events_term__clone(struct parse_events_term **new, @@ -2855,15 +2747,3 @@ char *parse_events_formats_error_string(char *additional_terms) fail: return NULL; } - -struct evsel *parse_events__add_event_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, - const char *name, - const char *metric_id, - struct perf_pmu *pmu, - struct list_head *config_terms) -{ - return __add_event(list, idx, attr, /*init_attr=*/true, name, metric_id, - pmu, config_terms, /*auto_merge_stats=*/false, - /*cpu_list=*/NULL); -} diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 86ad4438a2aa..2021fe145410 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -18,21 +18,26 @@ struct parse_events_error; struct option; struct perf_pmu; -bool is_event_supported(u8 type, u64 config); - const char *event_type(int type); +/* Arguments encoded in opt->value. */ +struct parse_events_option_args { + struct evlist **evlistp; + const char *pmu_filter; +}; int parse_events_option(const struct option *opt, const char *str, int unset); int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset); -__attribute__((nonnull(1, 2, 3))) -int __parse_events(struct evlist *evlist, const char *str, struct parse_events_error *error, - struct perf_pmu *fake_pmu, bool warn_if_reordered); +__attribute__((nonnull(1, 2, 4))) +int __parse_events(struct evlist *evlist, const char *str, const char *pmu_filter, + struct parse_events_error *error, struct perf_pmu *fake_pmu, + bool warn_if_reordered); __attribute__((nonnull(1, 2, 3))) static inline int parse_events(struct evlist *evlist, const char *str, struct parse_events_error *err) { - return __parse_events(evlist, str, err, /*fake_pmu=*/NULL, /*warn_if_reordered=*/true); + return __parse_events(evlist, str, /*pmu_filter=*/NULL, err, /*fake_pmu=*/NULL, + /*warn_if_reordered=*/true); } int parse_event(struct evlist *evlist, const char *str); @@ -41,14 +46,6 @@ int parse_events_terms(struct list_head *terms, const char *str); int parse_filter(const struct option *opt, const char *str, int unset); int exclude_perf(const struct option *opt, const char *arg, int unset); -enum perf_pmu_event_symbol_type { - PMU_EVENT_SYMBOL_ERR, /* not a PMU EVENT */ - PMU_EVENT_SYMBOL, /* normal style PMU event */ - PMU_EVENT_SYMBOL_PREFIX, /* prefix of pre-suf style event */ - PMU_EVENT_SYMBOL_SUFFIX, /* suffix of pre-suf style event */ - PMU_EVENT_SYMBOL_SUFFIX2, /* suffix of pre-suf2 style event */ -}; - enum { PARSE_EVENTS__TERM_TYPE_NUM, PARSE_EVENTS__TERM_TYPE_STR, @@ -78,6 +75,9 @@ enum { PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, PARSE_EVENTS__TERM_TYPE_METRIC_ID, + PARSE_EVENTS__TERM_TYPE_RAW, + PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, + PARSE_EVENTS__TERM_TYPE_HARDWARE, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -128,10 +128,15 @@ struct parse_events_state { struct list_head *terms; int stoken; struct perf_pmu *fake_pmu; - char *hybrid_pmu_name; + /* If non-null, when wildcard matching only match the given PMU. */ + const char *pmu_filter; + /* Should PE_LEGACY_NAME tokens be generated for config terms? */ + bool match_legacy_cache_terms; bool wild_card_pmus; }; +bool parse_events__filter_pmu(const struct parse_events_state *parse_state, + const struct perf_pmu *pmu); void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, @@ -141,8 +146,9 @@ int parse_events_term__num(struct parse_events_term **term, int parse_events_term__str(struct parse_events_term **term, int type_term, char *config, char *str, void *loc_term, void *loc_val); -int parse_events_term__sym_hw(struct parse_events_term **term, - char *config, unsigned idx); +int parse_events_term__term(struct parse_events_term **term, + int term_lhs, int term_rhs, + void *loc_term, void *loc_val); int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term); void parse_events_term__delete(struct parse_events_term *term); @@ -170,15 +176,15 @@ int parse_events_load_bpf_obj(struct parse_events_state *parse_state, int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, - struct list_head *head_config); + struct list_head *head_config, + bool wildcard); int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, int tool_event); -int parse_events_add_cache(struct list_head *list, int *idx, - char *type, char *op_result1, char *op_result2, - struct parse_events_error *error, - struct list_head *head_config, - struct parse_events_state *parse_state); +int parse_events_add_cache(struct list_head *list, int *idx, const char *name, + struct parse_events_state *parse_state, + struct list_head *head_config); +int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config); int parse_events_add_breakpoint(struct list_head *list, int *idx, u64 addr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, @@ -198,8 +204,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, int parse_events_copy_term_list(struct list_head *old, struct list_head **new); -enum perf_pmu_event_symbol_type -perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); @@ -241,13 +245,4 @@ static inline bool is_sdt_event(char *str __maybe_unused) } #endif /* HAVE_LIBELF_SUPPORT */ -int perf_pmu__test_parse_init(void); - -struct evsel *parse_events__add_event_hybrid(struct list_head *list, int *idx, - struct perf_event_attr *attr, - const char *name, - const char *metric_id, - struct perf_pmu *pmu, - struct list_head *config_terms); - #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 51fe0a9fb3de..6deb70c25984 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -63,15 +63,9 @@ static int str(yyscan_t scanner, int token) return token; } -static int raw(yyscan_t scanner) +static int lc_str(yyscan_t scanner, const struct parse_events_state *state) { - YYSTYPE *yylval = parse_events_get_lval(scanner); - char *text = parse_events_get_text(scanner); - - if (perf_pmu__parse_check(text) == PMU_EVENT_SYMBOL) - return str(scanner, PE_NAME); - - return __value(yylval, text + 1, 16, PE_RAW); + return str(scanner, state->match_legacy_cache_terms ? PE_LEGACY_CACHE : PE_NAME); } static bool isbpf_suffix(char *text) @@ -131,35 +125,6 @@ do { \ yyless(0); \ } while (0) -static int pmu_str_check(yyscan_t scanner, struct parse_events_state *parse_state) -{ - YYSTYPE *yylval = parse_events_get_lval(scanner); - char *text = parse_events_get_text(scanner); - - yylval->str = strdup(text); - - /* - * If we're not testing then parse check determines the PMU event type - * which if it isn't a PMU returns PE_NAME. When testing the result of - * parse check can't be trusted so we return PE_PMU_EVENT_FAKE unless - * an '!' is present in which case the text can't be a PMU name. - */ - switch (perf_pmu__parse_check(text)) { - case PMU_EVENT_SYMBOL_PREFIX: - return PE_PMU_EVENT_PRE; - case PMU_EVENT_SYMBOL_SUFFIX: - return PE_PMU_EVENT_SUF; - case PMU_EVENT_SYMBOL_SUFFIX2: - return PE_PMU_EVENT_SUF2; - case PMU_EVENT_SYMBOL: - return parse_state->fake_pmu - ? PE_PMU_EVENT_FAKE : PE_KERNEL_PMU_EVENT; - default: - return parse_state->fake_pmu && !strchr(text,'!') - ? PE_PMU_EVENT_FAKE : PE_NAME; - } -} - static int sym(yyscan_t scanner, int type, int config) { YYSTYPE *yylval = parse_events_get_lval(scanner); @@ -184,6 +149,16 @@ static int term(yyscan_t scanner, int type) return PE_TERM; } +static int hw_term(yyscan_t scanner, int config) +{ + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + yylval->hardware_term.str = strdup(text); + yylval->hardware_term.num = PERF_TYPE_HARDWARE + config; + return PE_TERM_HW; +} + #define YY_USER_ACTION \ do { \ yylloc->last_column = yylloc->first_column; \ @@ -211,19 +186,20 @@ bpf_source [^,{}]+\.c[a-zA-Z0-9._]* num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ -name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!]* +name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]* name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ modifier_event [ukhpPGHSDIWeb]+ modifier_bp [rwx]{1,3} +lc_type (L1-dcache|l1-d|l1d|L1-data|L1-icache|l1-i|l1i|L1-instruction|LLC|L2|dTLB|d-tlb|Data-TLB|iTLB|i-tlb|Instruction-TLB|branch|branches|bpu|btb|bpc|node) +lc_op_result (load|loads|read|store|stores|write|prefetch|prefetches|speculative-read|speculative-load|refs|Reference|ops|access|misses|miss) %% %{ struct parse_events_state *_parse_state = parse_events_get_extra(yyscanner); - { int start_token = _parse_state->stoken; @@ -303,10 +279,23 @@ percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } -r{num_raw_hex} { return raw(yyscanner); } -r0x{num_raw_hex} { return raw(yyscanner); } +cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); } +stalled-cycles-frontend|idle-cycles-frontend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } +stalled-cycles-backend|idle-cycles-backend { return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } +instructions { return hw_term(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); } +cache-references { return hw_term(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); } +cache-misses { return hw_term(yyscanner, PERF_COUNT_HW_CACHE_MISSES); } +branch-instructions|branches { return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } +branch-misses { return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); } +bus-cycles { return hw_term(yyscanner, PERF_COUNT_HW_BUS_CYCLES); } +ref-cycles { return hw_term(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); } +r{num_raw_hex} { return str(yyscanner, PE_RAW); } +r0x{num_raw_hex} { return str(yyscanner, PE_RAW); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } +{lc_type} { return lc_str(yyscanner, _parse_state); } +{lc_type}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } +{lc_type}-{lc_op_result}-{lc_op_result} { return lc_str(yyscanner, _parse_state); } {name_minus} { return str(yyscanner, PE_NAME); } \[all\] { return PE_ARRAY_ALL; } "[" { BEGIN(array); return '['; } @@ -359,47 +348,20 @@ system_time { return tool(yyscanner, PERF_TOOL_SYSTEM_TIME); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } cgroup-switches { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); } - /* - * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately. - * Because the prefix cycles is mixed up with cpu-cycles. - * loads and stores are mixed up with cache event - */ -cycles-ct | -cycles-t | -mem-loads | -mem-loads-aux | -mem-stores | -topdown-[a-z-]+ | -tx-capacity-[a-z-]+ | -el-capacity-[a-z-]+ { return str(yyscanner, PE_KERNEL_PMU_EVENT); } - -L1-dcache|l1-d|l1d|L1-data | -L1-icache|l1-i|l1i|L1-instruction | -LLC|L2 | -dTLB|d-tlb|Data-TLB | -iTLB|i-tlb|Instruction-TLB | -branch|branches|bpu|btb|bpc | -node { return str(yyscanner, PE_NAME_CACHE_TYPE); } - -load|loads|read | -store|stores|write | -prefetch|prefetches | -speculative-read|speculative-load | -refs|Reference|ops|access | -misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } - +{lc_type} { return str(yyscanner, PE_LEGACY_CACHE); } +{lc_type}-{lc_op_result} { return str(yyscanner, PE_LEGACY_CACHE); } +{lc_type}-{lc_op_result}-{lc_op_result} { return str(yyscanner, PE_LEGACY_CACHE); } mem: { BEGIN(mem); return PE_PREFIX_MEM; } -r{num_raw_hex} { return raw(yyscanner); } +r{num_raw_hex} { return str(yyscanner, PE_RAW); } {num_dec} { return value(yyscanner, 10); } {num_hex} { return value(yyscanner, 16); } {modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } {bpf_object} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); } {bpf_source} { if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); } -{name} { return pmu_str_check(yyscanner, _parse_state); } +{name} { return str(yyscanner, PE_NAME); } {name_tag} { return str(yyscanner, PE_NAME); } "/" { BEGIN(config); return '/'; } -- { return '-'; } , { BEGIN(event); return ','; } : { return ':'; } "{" { BEGIN(event); return '{'; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 4488443e506e..abd6ab460e12 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -8,12 +8,14 @@ #define YYDEBUG 1 +#include <errno.h> #include <fnmatch.h> #include <stdio.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/zalloc.h> #include "pmu.h" +#include "pmus.h" #include "evsel.h" #include "parse-events.h" #include "parse-events-bison.h" @@ -52,36 +54,36 @@ static void free_list_evsel(struct list_head* list_evsel) %} %token PE_START_EVENTS PE_START_TERMS -%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM +%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM %token PE_VALUE_SYM_TOOL %token PE_EVENT_NAME -%token PE_NAME +%token PE_RAW PE_NAME %token PE_BPF_OBJECT PE_BPF_SOURCE %token PE_MODIFIER_EVENT PE_MODIFIER_BP -%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT +%token PE_LEGACY_CACHE %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP %token PE_ERROR -%token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE +%token PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %token PE_ARRAY_ALL PE_ARRAY_RANGE %token PE_DRV_CFG_TERM +%token PE_TERM_HW %type <num> PE_VALUE %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW %type <num> PE_VALUE_SYM_TOOL -%type <num> PE_RAW %type <num> PE_TERM %type <num> value_sym +%type <str> PE_RAW %type <str> PE_NAME %type <str> PE_BPF_OBJECT %type <str> PE_BPF_SOURCE -%type <str> PE_NAME_CACHE_TYPE -%type <str> PE_NAME_CACHE_OP_RESULT +%type <str> PE_LEGACY_CACHE %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME -%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_PMU_EVENT_SUF2 PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE +%type <str> PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE %type <str> PE_DRV_CFG_TERM -%type <str> event_pmu_name +%type <str> name_or_raw name_or_legacy %destructor { free ($$); } <str> %type <term> event_term %destructor { parse_events_term__delete ($$); } <term> @@ -112,6 +114,8 @@ static void free_list_evsel(struct list_head* list_evsel) %type <array> array_term %type <array> array_terms %destructor { free ($$.ranges); } <array> +%type <hardware_term> PE_TERM_HW +%destructor { free ($$.str); } <hardware_term> %union { @@ -125,6 +129,10 @@ static void free_list_evsel(struct list_head* list_evsel) char *event; } tracepoint_name; struct parse_events_array array; + struct hardware_term { + char *str; + u64 num; + } hardware_term; } %% @@ -273,11 +281,8 @@ event_def: event_pmu | event_legacy_raw sep_dc | event_bpf_file -event_pmu_name: -PE_NAME | PE_PMU_EVENT_PRE - event_pmu: -event_pmu_name opt_pmu_config +PE_NAME opt_pmu_config { struct parse_events_state *parse_state = _parse_state; struct parse_events_error *error = parse_state->error; @@ -303,25 +308,32 @@ event_pmu_name opt_pmu_config list = alloc_list(); if (!list) CLEANUP_YYABORT; - if (parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false)) { + /* Attempt to add to list assuming $1 is a PMU name. */ + if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false)) { struct perf_pmu *pmu = NULL; int ok = 0; + /* Failure to add, try wildcard expansion of $1 as a PMU name. */ if (asprintf(&pattern, "%s*", $1) < 0) CLEANUP_YYABORT; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { + while ((pmu = perf_pmus__scan(pmu)) != NULL) { char *name = pmu->name; + if (parse_events__filter_pmu(parse_state, pmu)) + continue; + if (!strncmp(name, "uncore_", 7) && strncmp($1, "uncore_", 7)) name += 7; if (!perf_pmu__match(pattern, name, $1) || !perf_pmu__match(pattern, pmu->alias_name, $1)) { + bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu); + if (parse_events_copy_term_list(orig_terms, &terms)) CLEANUP_YYABORT; - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, - /*auto_merge_stats=*/true)) { + if (!parse_events_add_pmu(parse_state, list, pmu->name, terms, + auto_merge_stats)) { ok++; parse_state->wild_card_pmus = true; } @@ -329,6 +341,12 @@ event_pmu_name opt_pmu_config } } + if (!ok) { + /* Failure to add, assume $1 is an event name. */ + zfree(&list); + ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list); + $2 = NULL; + } if (!ok) CLEANUP_YYABORT; } @@ -352,41 +370,27 @@ PE_KERNEL_PMU_EVENT sep_dc $$ = list; } | -PE_KERNEL_PMU_EVENT opt_pmu_config +PE_NAME sep_dc { struct list_head *list; int err; - /* frees $2 */ - err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list); + err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list); free($1); if (err < 0) YYABORT; $$ = list; } | -PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF '-' PE_PMU_EVENT_SUF2 sep_dc -{ - struct list_head *list; - char pmu_name[128]; - snprintf(pmu_name, sizeof(pmu_name), "%s-%s-%s", $1, $3, $5); - free($1); - free($3); - free($5); - if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0) - YYABORT; - $$ = list; -} -| -PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc +PE_KERNEL_PMU_EVENT opt_pmu_config { struct list_head *list; - char pmu_name[128]; + int err; - snprintf(pmu_name, sizeof(pmu_name), "%s-%s", $1, $3); + /* frees $2 */ + err = parse_events_multi_pmu_add(_parse_state, $1, $2, &list); free($1); - free($3); - if (parse_events_multi_pmu_add(_parse_state, pmu_name, NULL, &list) < 0) + if (err < 0) YYABORT; $$ = list; } @@ -444,7 +448,8 @@ value_sym '/' event_config '/' list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_numeric(_parse_state, list, type, config, $3); + err = parse_events_add_numeric(_parse_state, list, type, config, $3, + /*wildcard=*/false); parse_events_terms__delete($3); if (err) { free_list_evsel(list); @@ -461,7 +466,9 @@ value_sym sep_slash_slash_dc list = alloc_list(); ABORT_ON(!list); - ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL)); + ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, + /*head_config=*/NULL, + /*wildcard=*/false)); $$ = list; } | @@ -476,60 +483,16 @@ PE_VALUE_SYM_TOOL sep_slash_slash_dc } event_legacy_cache: -PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config -{ - struct parse_events_state *parse_state = _parse_state; - struct parse_events_error *error = parse_state->error; - struct list_head *list; - int err; - - list = alloc_list(); - ABORT_ON(!list); - err = parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6, - parse_state); - parse_events_terms__delete($6); - free($1); - free($3); - free($5); - if (err) { - free_list_evsel(list); - YYABORT; - } - $$ = list; -} -| -PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config +PE_LEGACY_CACHE opt_event_config { struct parse_events_state *parse_state = _parse_state; - struct parse_events_error *error = parse_state->error; struct list_head *list; int err; list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4, - parse_state); - parse_events_terms__delete($4); - free($1); - free($3); - if (err) { - free_list_evsel(list); - YYABORT; - } - $$ = list; -} -| -PE_NAME_CACHE_TYPE opt_event_config -{ - struct parse_events_state *parse_state = _parse_state; - struct parse_events_error *error = parse_state->error; - struct list_head *list; - int err; + err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2); - list = alloc_list(); - ABORT_ON(!list); - err = parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2, - parse_state); parse_events_terms__delete($2); free($1); if (err) { @@ -633,17 +596,6 @@ tracepoint_name opt_event_config } tracepoint_name: -PE_NAME '-' PE_NAME ':' PE_NAME -{ - struct tracepoint_name tracepoint; - - ABORT_ON(asprintf(&tracepoint.sys, "%s-%s", $1, $3) < 0); - tracepoint.event = $5; - free($1); - free($3); - $$ = tracepoint; -} -| PE_NAME ':' PE_NAME { struct tracepoint_name tracepoint = {$1, $3}; @@ -659,7 +611,8 @@ PE_VALUE ':' PE_VALUE opt_event_config list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4); + err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4, + /*wildcard=*/false); parse_events_terms__delete($4); if (err) { free(list); @@ -673,10 +626,16 @@ PE_RAW opt_event_config { struct list_head *list; int err; + u64 num; list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, $1, $2); + errno = 0; + num = strtoull($1 + 1, NULL, 16); + ABORT_ON(errno); + free($1); + err = parse_events_add_numeric(_parse_state, list, PERF_TYPE_RAW, num, $2, + /*wildcard=*/true); parse_events_terms__delete($2); if (err) { free(list); @@ -781,17 +740,24 @@ event_term $$ = head; } +name_or_raw: PE_RAW | PE_NAME | PE_LEGACY_CACHE + +name_or_legacy: PE_NAME | PE_LEGACY_CACHE + event_term: PE_RAW { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_CONFIG, - NULL, $1, false, &@1, NULL)); + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW, + strdup("raw"), $1, &@1, &@1)) { + free($1); + YYABORT; + } $$ = term; } | -PE_NAME '=' PE_NAME +name_or_raw '=' name_or_legacy { struct parse_events_term *term; @@ -804,7 +770,7 @@ PE_NAME '=' PE_NAME $$ = term; } | -PE_NAME '=' PE_VALUE +name_or_raw '=' PE_VALUE { struct parse_events_term *term; @@ -816,12 +782,25 @@ PE_NAME '=' PE_VALUE $$ = term; } | -PE_NAME '=' PE_VALUE_SYM_HW +name_or_raw '=' PE_TERM_HW +{ + struct parse_events_term *term; + + if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3.str, &@1, &@3)) { + free($1); + free($3.str); + YYABORT; + } + $$ = term; +} +| +PE_LEGACY_CACHE { struct parse_events_term *term; - int config = $3 & 255; - if (parse_events_term__sym_hw(&term, $1, config)) { + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE, + $1, 1, true, &@1, NULL)) { free($1); YYABORT; } @@ -840,16 +819,19 @@ PE_NAME $$ = term; } | -PE_VALUE_SYM_HW +PE_TERM_HW { struct parse_events_term *term; - int config = $1 & 255; - ABORT_ON(parse_events_term__sym_hw(&term, NULL, config)); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE, + $1.str, $1.num & 255, false, &@1, NULL)) { + free($1.str); + YYABORT; + } $$ = term; } | -PE_TERM '=' PE_NAME +PE_TERM '=' name_or_legacy { struct parse_events_term *term; @@ -860,6 +842,25 @@ PE_TERM '=' PE_NAME $$ = term; } | +PE_TERM '=' PE_TERM_HW +{ + struct parse_events_term *term; + + if (parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3)) { + free($3.str); + YYABORT; + } + $$ = term; +} +| +PE_TERM '=' PE_TERM +{ + struct parse_events_term *term; + + ABORT_ON(parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3)); + $$ = term; +} +| PE_TERM '=' PE_VALUE { struct parse_events_term *term; @@ -876,7 +877,7 @@ PE_TERM $$ = term; } | -PE_NAME array '=' PE_NAME +name_or_raw array '=' name_or_legacy { struct parse_events_term *term; @@ -891,7 +892,7 @@ PE_NAME array '=' PE_NAME $$ = term; } | -PE_NAME array '=' PE_VALUE +name_or_raw array '=' PE_VALUE { struct parse_events_term *term; diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index ce80b79be103..00adf872bf00 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -1,16 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -/* - * I'm tired of doing "vsnprintf()" etc just to open a - * file, so here's a "return static buffer with printf" - * interface for paths. - * - * It's obviously not thread-safe. Sue me. But it's quite - * useful for doing things like - * - * f = open(mkpath("%s/%s.perf", base, name), O_RDONLY); - * - * which is what it's designed for. - */ #include "path.h" #include "cache.h" #include <linux/kernel.h> @@ -22,18 +10,6 @@ #include <dirent.h> #include <unistd.h> -static char bad_path[] = "/bad-path/"; -/* - * One hack: - */ -static char *get_pathname(void) -{ - static char pathname_array[4][PATH_MAX]; - static int idx; - - return pathname_array[3 & ++idx]; -} - static char *cleanup_path(char *path) { /* Clean it up */ @@ -45,18 +21,17 @@ static char *cleanup_path(char *path) return path; } -char *mkpath(const char *fmt, ...) +char *mkpath(char *path_buf, size_t sz, const char *fmt, ...) { va_list args; unsigned len; - char *pathname = get_pathname(); va_start(args, fmt); - len = vsnprintf(pathname, PATH_MAX, fmt, args); + len = vsnprintf(path_buf, sz, fmt, args); va_end(args); - if (len >= PATH_MAX) - return bad_path; - return cleanup_path(pathname); + if (len >= sz) + strncpy(path_buf, "/bad-path/", sz); + return cleanup_path(path_buf); } int path__join(char *bf, size_t size, const char *path1, const char *path2) diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index 6c11914c179f..076aecc22c16 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -10,7 +10,7 @@ #include "util/evlist.h" #include "util/evsel.h" #include "util/parse-events.h" -#include "util/pmu.h" +#include "util/pmus.h" #include "util/pfm.h" #include "util/strbuf.h" @@ -49,7 +49,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, /* * force loading of the PMU list */ - perf_pmu__scan(NULL); + perf_pmus__scan(NULL); for (q = p; strsep(&p, ",{}"); q = p) { sep = p ? str + (p - p_orig - 1) : ""; @@ -86,7 +86,7 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, goto error; } - pmu = perf_pmu__find_by_type((unsigned int)attr.type); + pmu = perf_pmus__find_by_type((unsigned int)attr.type); evsel = parse_events__add_event(evlist->core.nr_entries, &attr, q, /*metric_id=*/NULL, pmu); diff --git a/tools/perf/util/pmu-hybrid.c b/tools/perf/util/pmu-hybrid.c deleted file mode 100644 index 38628805a952..000000000000 --- a/tools/perf/util/pmu-hybrid.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/list.h> -#include <linux/compiler.h> -#include <linux/string.h> -#include <linux/zalloc.h> -#include <sys/types.h> -#include <errno.h> -#include <fcntl.h> -#include <sys/stat.h> -#include <unistd.h> -#include <stdio.h> -#include <stdbool.h> -#include <stdarg.h> -#include <locale.h> -#include <api/fs/fs.h> -#include "fncache.h" -#include "pmu-hybrid.h" - -LIST_HEAD(perf_pmu__hybrid_pmus); - -bool perf_pmu__hybrid_mounted(const char *name) -{ - int cpu; - char pmu_name[PATH_MAX]; - struct perf_pmu pmu = {.name = pmu_name}; - - if (strncmp(name, "cpu_", 4)) - return false; - - strlcpy(pmu_name, name, sizeof(pmu_name)); - return perf_pmu__scan_file(&pmu, "cpus", "%u", &cpu) > 0; -} - -struct perf_pmu *perf_pmu__find_hybrid_pmu(const char *name) -{ - struct perf_pmu *pmu; - - if (!name) - return NULL; - - perf_pmu__for_each_hybrid_pmu(pmu) { - if (!strcmp(name, pmu->name)) - return pmu; - } - - return NULL; -} - -bool perf_pmu__is_hybrid(const char *name) -{ - return perf_pmu__find_hybrid_pmu(name) != NULL; -} - -char *perf_pmu__hybrid_type_to_pmu(const char *type) -{ - char *pmu_name = NULL; - - if (asprintf(&pmu_name, "cpu_%s", type) < 0) - return NULL; - - if (perf_pmu__is_hybrid(pmu_name)) - return pmu_name; - - /* - * pmu may be not scanned, check the sysfs. - */ - if (perf_pmu__hybrid_mounted(pmu_name)) - return pmu_name; - - free(pmu_name); - return NULL; -} diff --git a/tools/perf/util/pmu-hybrid.h b/tools/perf/util/pmu-hybrid.h deleted file mode 100644 index 2b186c26a43e..000000000000 --- a/tools/perf/util/pmu-hybrid.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PMU_HYBRID_H -#define __PMU_HYBRID_H - -#include <linux/perf_event.h> -#include <linux/compiler.h> -#include <linux/list.h> -#include <stdbool.h> -#include "pmu.h" - -extern struct list_head perf_pmu__hybrid_pmus; - -#define perf_pmu__for_each_hybrid_pmu(pmu) \ - list_for_each_entry(pmu, &perf_pmu__hybrid_pmus, hybrid_list) - -bool perf_pmu__hybrid_mounted(const char *name); - -struct perf_pmu *perf_pmu__find_hybrid_pmu(const char *name); -bool perf_pmu__is_hybrid(const char *name); -char *perf_pmu__hybrid_type_to_pmu(const char *type); - -static inline int perf_pmu__hybrid_pmu_num(void) -{ - struct perf_pmu *pmu; - int num = 0; - - perf_pmu__for_each_hybrid_pmu(pmu) - num++; - - return num; -} - -#endif /* __PMU_HYBRID_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index ad209c88a124..0520aa9fe991 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -4,20 +4,15 @@ #include <linux/string.h> #include <linux/zalloc.h> #include <linux/ctype.h> -#include <subcmd/pager.h> #include <sys/types.h> -#include <errno.h> #include <fcntl.h> #include <sys/stat.h> #include <unistd.h> #include <stdio.h> #include <stdbool.h> -#include <stdarg.h> #include <dirent.h> #include <api/fs/fs.h> #include <locale.h> -#include <regex.h> -#include <perf/cpumap.h> #include <fnmatch.h> #include <math.h> #include "debug.h" @@ -32,7 +27,6 @@ #include "string2.h" #include "strbuf.h" #include "fncache.h" -#include "pmu-hybrid.h" #include "util/evsel_config.h" struct perf_pmu perf_pmu__fake; @@ -60,10 +54,6 @@ struct perf_pmu_format { struct list_head list; }; -static bool hybrid_scanned; - -static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name); - /* * Parse & process all the sysfs attributes located under * the directory specified in 'dir' parameter. @@ -557,31 +547,6 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, return 0; } -/* Add all pmus in sysfs to pmu list: */ -static void pmu_read_sysfs(void) -{ - int fd; - DIR *dir; - struct dirent *dent; - - fd = perf_pmu__event_source_devices_fd(); - if (fd < 0) - return; - - dir = fdopendir(fd); - if (!dir) - return; - - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) - continue; - /* add to static LIST_HEAD(pmus): */ - perf_pmu__find2(fd, dent->d_name); - } - - closedir(dir); -} - /* * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. @@ -610,16 +575,13 @@ static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name) return cpus; } - return NULL; + return !strcmp(name, "cpu") ? perf_cpu_map__get(cpu_map__online()) : NULL; } static bool pmu_is_uncore(int dirfd, const char *name) { int fd; - if (perf_pmu__hybrid_mounted(name)) - return false; - fd = perf_pmu__pathname_fd(dirfd, name, "cpumask", O_PATH); if (fd < 0) return false; @@ -643,12 +605,14 @@ static char *pmu_id(const char *name) return str; } -/* - * PMU CORE devices have different name other than cpu in sysfs on some - * platforms. - * Looking for possible sysfs files to identify the arm core device. +/** + * is_sysfs_pmu_core() - PMU CORE devices have different name other than cpu in + * sysfs on some platforms like ARM or Intel hybrid. Looking for + * possible the cpus file in sysfs files to identify whether this is a + * core device. + * @name: The PMU name such as "cpu_atom". */ -static int is_arm_pmu_core(const char *name) +static int is_sysfs_pmu_core(const char *name) { char path[PATH_MAX]; @@ -814,7 +778,7 @@ void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu, struct pmu_add_cpu_aliases_map_data data = { .head = head, .name = pmu->name, - .cpu_name = is_arm_pmu_core(pmu->name) ? pmu->name : "cpu", + .cpu_name = is_sysfs_pmu_core(pmu->name) ? pmu->name : "cpu", .pmu = pmu, }; @@ -898,23 +862,16 @@ static int pmu_max_precise(int dirfd, struct perf_pmu *pmu) return max_precise; } -static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) +struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name) { struct perf_pmu *pmu; LIST_HEAD(format); LIST_HEAD(aliases); __u32 type; char *name = pmu_find_real_name(lookup_name); - bool is_hybrid = perf_pmu__hybrid_mounted(name); char *alias_name; /* - * Check pmu name for hybrid and the pmu may be invalid in sysfs - */ - if (!strncmp(name, "cpu_", 4) && !is_hybrid) - return NULL; - - /* * The pmu data we store & need consists of the pmu * type value and format definitions. Load both right * now. @@ -934,7 +891,6 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) pmu->cpus = pmu_cpumask(dirfd, name); pmu->name = strdup(name); - if (!pmu->name) goto err; @@ -950,6 +906,7 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) } pmu->type = type; + pmu->is_core = is_pmu_core(name); pmu->is_uncore = pmu_is_uncore(dirfd, name); if (pmu->is_uncore) pmu->id = pmu_id(name); @@ -962,12 +919,7 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) INIT_LIST_HEAD(&pmu->caps); list_splice(&format, &pmu->format); list_splice(&aliases, &pmu->aliases); - list_add_tail(&pmu->list, &pmus); - - if (is_hybrid) - list_add_tail(&pmu->hybrid_list, &perf_pmu__hybrid_pmus); - else - INIT_LIST_HEAD(&pmu->hybrid_list); + list_add_tail(&pmu->list, pmus); pmu->default_config = perf_pmu__get_default_config(pmu); @@ -995,61 +947,6 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) } } -static struct perf_pmu *pmu_find(const char *name) -{ - struct perf_pmu *pmu; - - list_for_each_entry(pmu, &pmus, list) { - if (!strcmp(pmu->name, name) || - (pmu->alias_name && !strcmp(pmu->alias_name, name))) - return pmu; - } - - return NULL; -} - -struct perf_pmu *perf_pmu__find_by_type(unsigned int type) -{ - struct perf_pmu *pmu; - - list_for_each_entry(pmu, &pmus, list) - if (pmu->type == type) - return pmu; - - return NULL; -} - -struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) -{ - /* - * pmu iterator: If pmu is NULL, we start at the begin, - * otherwise return the next pmu. Returns NULL on end. - */ - if (!pmu) { - pmu_read_sysfs(); - pmu = list_prepare_entry(pmu, &pmus, list); - } - list_for_each_entry_continue(pmu, &pmus, list) - return pmu; - return NULL; -} - -struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) -{ - struct perf_pmu *pmu = NULL; - - if (evsel->pmu) - return evsel->pmu; - - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - if (pmu->type == evsel->core.attr.type) - break; - } - - ((struct evsel *)evsel)->pmu = pmu; - return pmu; -} - bool evsel__is_aux_event(const struct evsel *evsel) { struct perf_pmu *pmu = evsel__find_pmu(evsel); @@ -1086,43 +983,6 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, evsel->core.attr.config |= field_prep(bits, val); } -struct perf_pmu *perf_pmu__find(const char *name) -{ - struct perf_pmu *pmu; - int dirfd; - - /* - * Once PMU is loaded it stays in the list, - * so we keep us from multiple reading/parsing - * the pmu format definitions. - */ - pmu = pmu_find(name); - if (pmu) - return pmu; - - dirfd = perf_pmu__event_source_devices_fd(); - pmu = pmu_lookup(dirfd, name); - close(dirfd); - - return pmu; -} - -static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) -{ - struct perf_pmu *pmu; - - /* - * Once PMU is loaded it stays in the list, - * so we keep us from multiple reading/parsing - * the pmu format definitions. - */ - pmu = pmu_find(name); - if (pmu) - return pmu; - - return pmu_lookup(dirfd, name); -} - static struct perf_pmu_format * pmu_find_format(struct list_head *formats, const char *name) { @@ -1398,7 +1258,6 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, { bool zero = !!pmu->default_config; - attr->type = pmu->type; return perf_pmu__config_terms(pmu->name, &pmu->format, attr, head_terms, zero, err); } @@ -1553,248 +1412,28 @@ void perf_pmu__del_formats(struct list_head *formats) } } -static int sub_non_neg(int a, int b) -{ - if (b > a) - return 0; - return a - b; -} - -static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, - const struct perf_pmu_alias *alias) -{ - struct parse_events_term *term; - int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name); - - list_for_each_entry(term, &alias->terms, list) { - if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) - used += snprintf(buf + used, sub_non_neg(len, used), - ",%s=%s", term->config, - term->val.str); - } - - if (sub_non_neg(len, used) > 0) { - buf[used] = '/'; - used++; - } - if (sub_non_neg(len, used) > 0) { - buf[used] = '\0'; - used++; - } else - buf[len - 1] = '\0'; - - return buf; -} - -/** Struct for ordering events as output in perf list. */ -struct sevent { - /** PMU for event. */ - const struct perf_pmu *pmu; - /** - * Optional event for name, desc, etc. If not present then this is a - * selectable PMU and the event name is shown as "//". - */ - const struct perf_pmu_alias *event; - /** Is the PMU for the CPU? */ - bool is_cpu; -}; - -static int cmp_sevent(const void *a, const void *b) -{ - const struct sevent *as = a; - const struct sevent *bs = b; - const char *a_pmu_name = NULL, *b_pmu_name = NULL; - const char *a_name = "//", *a_desc = NULL, *a_topic = ""; - const char *b_name = "//", *b_desc = NULL, *b_topic = ""; - int ret; - - if (as->event) { - a_name = as->event->name; - a_desc = as->event->desc; - a_topic = as->event->topic ?: ""; - a_pmu_name = as->event->pmu_name; - } - if (bs->event) { - b_name = bs->event->name; - b_desc = bs->event->desc; - b_topic = bs->event->topic ?: ""; - b_pmu_name = bs->event->pmu_name; - } - /* Put extra events last. */ - if (!!a_desc != !!b_desc) - return !!a_desc - !!b_desc; - - /* Order by topics. */ - ret = strcmp(a_topic, b_topic); - if (ret) - return ret; - - /* Order CPU core events to be first */ - if (as->is_cpu != bs->is_cpu) - return as->is_cpu ? -1 : 1; - - /* Order by PMU name. */ - if (as->pmu != bs->pmu) { - a_pmu_name = a_pmu_name ?: (as->pmu->name ?: ""); - b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: ""); - ret = strcmp(a_pmu_name, b_pmu_name); - if (ret) - return ret; - } - - /* Order by event name. */ - return strcmp(a_name, b_name); -} - bool is_pmu_core(const char *name) { - return !strcmp(name, "cpu") || is_arm_pmu_core(name); + return !strcmp(name, "cpu") || is_sysfs_pmu_core(name); } -static bool pmu_alias_is_duplicate(struct sevent *alias_a, - struct sevent *alias_b) +bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu) { - const char *a_pmu_name = NULL, *b_pmu_name = NULL; - const char *a_name = "//", *b_name = "//"; - - - if (alias_a->event) { - a_name = alias_a->event->name; - a_pmu_name = alias_a->event->pmu_name; - } - if (alias_b->event) { - b_name = alias_b->event->name; - b_pmu_name = alias_b->event->pmu_name; - } - - /* Different names -> never duplicates */ - if (strcmp(a_name, b_name)) - return false; - - /* Don't remove duplicates for different PMUs */ - a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: ""); - b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: ""); - return strcmp(a_pmu_name, b_pmu_name) == 0; + return pmu->is_core; } -void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) +bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu) { - struct perf_pmu *pmu; - struct perf_pmu_alias *event; - char buf[1024]; - int printed = 0; - int len, j; - struct sevent *aliases; - - pmu = NULL; - len = 0; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - list_for_each_entry(event, &pmu->aliases, list) - len++; - if (pmu->selectable) - len++; - } - aliases = zalloc(sizeof(struct sevent) * len); - if (!aliases) { - pr_err("FATAL: not enough memory to print PMU events\n"); - return; - } - pmu = NULL; - j = 0; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - bool is_cpu = is_pmu_core(pmu->name) || perf_pmu__is_hybrid(pmu->name); - - list_for_each_entry(event, &pmu->aliases, list) { - aliases[j].event = event; - aliases[j].pmu = pmu; - aliases[j].is_cpu = is_cpu; - j++; - } - if (pmu->selectable) { - aliases[j].event = NULL; - aliases[j].pmu = pmu; - aliases[j].is_cpu = is_cpu; - j++; - } - } - len = j; - qsort(aliases, len, sizeof(struct sevent), cmp_sevent); - for (j = 0; j < len; j++) { - const char *name, *alias = NULL, *scale_unit = NULL, - *desc = NULL, *long_desc = NULL, - *encoding_desc = NULL, *topic = NULL, - *pmu_name = NULL; - bool deprecated = false; - size_t buf_used; - - /* Skip duplicates */ - if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) - continue; - - if (!aliases[j].event) { - /* A selectable event. */ - pmu_name = aliases[j].pmu->name; - buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1; - name = buf; - } else { - if (aliases[j].event->desc) { - name = aliases[j].event->name; - buf_used = 0; - } else { - name = format_alias(buf, sizeof(buf), aliases[j].pmu, - aliases[j].event); - if (aliases[j].is_cpu) { - alias = name; - name = aliases[j].event->name; - } - buf_used = strlen(buf) + 1; - } - pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: ""); - if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) { - scale_unit = buf + buf_used; - buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%G%s", aliases[j].event->scale, - aliases[j].event->unit) + 1; - } - desc = aliases[j].event->desc; - long_desc = aliases[j].event->long_desc; - topic = aliases[j].event->topic; - encoding_desc = buf + buf_used; - buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%s/%s/", pmu_name, aliases[j].event->str) + 1; - deprecated = aliases[j].event->deprecated; - } - print_cb->print_event(print_state, - pmu_name, - topic, - name, - alias, - scale_unit, - deprecated, - "Kernel PMU event", - desc, - long_desc, - encoding_desc); - } - if (printed && pager_in_use()) - printf("\n"); - - zfree(&aliases); - return; + return pmu->is_core && perf_pmus__num_core_pmus() > 1; } -bool pmu_have_event(const char *pname, const char *name) +bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name) { - struct perf_pmu *pmu; struct perf_pmu_alias *alias; - pmu = NULL; - while ((pmu = perf_pmu__scan(pmu)) != NULL) { - if (strcmp(pname, pmu->name)) - continue; - list_for_each_entry(alias, &pmu->aliases, list) - if (!strcmp(alias->name, name)) - return true; + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcmp(alias->name, name)) + return true; } return false; } @@ -2000,16 +1639,6 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, name ?: "N/A", buf, config); } -bool perf_pmu__has_hybrid(void) -{ - if (!hybrid_scanned) { - hybrid_scanned = true; - perf_pmu__scan(NULL); - } - - return !list_empty(&perf_pmu__hybrid_pmus); -} - int perf_pmu__match(char *pattern, char *name, char *tok) { if (!name) @@ -2024,39 +1653,6 @@ int perf_pmu__match(char *pattern, char *name, char *tok) return 0; } -int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus, - struct perf_cpu_map **mcpus_ptr, - struct perf_cpu_map **ucpus_ptr) -{ - struct perf_cpu_map *pmu_cpus = pmu->cpus; - struct perf_cpu_map *matched_cpus, *unmatched_cpus; - struct perf_cpu cpu; - int i, matched_nr = 0, unmatched_nr = 0; - - matched_cpus = perf_cpu_map__default_new(); - if (!matched_cpus) - return -1; - - unmatched_cpus = perf_cpu_map__default_new(); - if (!unmatched_cpus) { - perf_cpu_map__put(matched_cpus); - return -1; - } - - perf_cpu_map__for_each_cpu(cpu, i, cpus) { - if (!perf_cpu_map__has(pmu_cpus, cpu)) - RC_CHK_ACCESS(unmatched_cpus)->map[unmatched_nr++] = cpu; - else - RC_CHK_ACCESS(matched_cpus)->map[matched_nr++] = cpu; - } - - perf_cpu_map__set_nr(unmatched_cpus, unmatched_nr); - perf_cpu_map__set_nr(matched_cpus, matched_nr); - *mcpus_ptr = matched_cpus; - *ucpus_ptr = unmatched_cpus; - return 0; -} - double __weak perf_pmu__cpu_slots_per_cycle(void) { return NAN; @@ -2110,7 +1706,7 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, return openat(dirfd, path, flags); } -static void perf_pmu__delete(struct perf_pmu *pmu) +void perf_pmu__delete(struct perf_pmu *pmu) { perf_pmu__del_formats(&pmu->format); perf_pmu__del_aliases(pmu); @@ -2123,15 +1719,3 @@ static void perf_pmu__delete(struct perf_pmu *pmu) zfree(&pmu->alias_name); free(pmu); } - -void perf_pmu__destroy(void) -{ - struct perf_pmu *pmu, *tmp; - - list_for_each_entry_safe(pmu, tmp, &pmus, list) { - list_del(&pmu->list); - list_del(&pmu->hybrid_list); - - perf_pmu__delete(pmu); - } -} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index b9a02dedd473..287f593b15c7 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -60,6 +60,13 @@ struct perf_pmu { */ bool selectable; /** + * @is_core: Is the PMU the core CPU PMU? Determined by the name being + * "cpu" or by the presence of + * <sysfs>/bus/event_source/devices/<name>/cpus. There may be >1 core + * PMU on systems like Intel hybrid. + */ + bool is_core; + /** * @is_uncore: Is the PMU not within the CPU core? Determined by the * presence of <sysfs>/bus/event_source/devices/<name>/cpumask. */ @@ -112,8 +119,6 @@ struct perf_pmu { struct list_head caps; /** @list: Element on pmus list in pmu.c. */ struct list_head list; - /** @hybrid_list: Element on perf_pmu__hybrid_pmus. */ - struct list_head hybrid_list; /** * @missing_features: Features to inhibit when events on this PMU are @@ -193,8 +198,6 @@ struct perf_pmu_alias { char *pmu_name; }; -struct perf_pmu *perf_pmu__find(const char *name); -struct perf_pmu *perf_pmu__find_by_type(unsigned int type); void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms, @@ -217,11 +220,10 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to); int perf_pmu__format_parse(int dirfd, struct list_head *head); void perf_pmu__del_formats(struct list_head *formats); -struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); - bool is_pmu_core(const char *name); -void print_pmu_events(const struct print_callbacks *print_cb, void *print_state); -bool pmu_have_event(const char *pname, const char *name); +bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu); +bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu); +bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name); FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name); @@ -251,13 +253,8 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *name); void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); -bool perf_pmu__has_hybrid(void); int perf_pmu__match(char *pattern, char *name, char *tok); -int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus, - struct perf_cpu_map **mcpus_ptr, - struct perf_cpu_map **ucpus_ptr); - char *pmu_find_real_name(const char *name); char *pmu_find_alias_name(const char *name); double perf_pmu__cpu_slots_per_cycle(void); @@ -267,6 +264,7 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size, int perf_pmu__event_source_devices_fd(void); int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags); -void perf_pmu__destroy(void); +struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name); +void perf_pmu__delete(struct perf_pmu *pmu); #endif /* __PMU_H */ diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index 7f3b93c4d229..53f11f6ce878 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -1,5 +1,489 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/list.h> -#include <pmus.h> +#include <linux/zalloc.h> +#include <subcmd/pager.h> +#include <sys/types.h> +#include <dirent.h> +#include <string.h> +#include <unistd.h> +#include "debug.h" +#include "evsel.h" +#include "pmus.h" +#include "pmu.h" +#include "print-events.h" -LIST_HEAD(pmus); +static LIST_HEAD(core_pmus); +static LIST_HEAD(other_pmus); +static bool read_sysfs_core_pmus; +static bool read_sysfs_all_pmus; + +void perf_pmus__destroy(void) +{ + struct perf_pmu *pmu, *tmp; + + list_for_each_entry_safe(pmu, tmp, &core_pmus, list) { + list_del(&pmu->list); + + perf_pmu__delete(pmu); + } + list_for_each_entry_safe(pmu, tmp, &other_pmus, list) { + list_del(&pmu->list); + + perf_pmu__delete(pmu); + } + read_sysfs_core_pmus = false; + read_sysfs_all_pmus = false; +} + +static struct perf_pmu *pmu_find(const char *name) +{ + struct perf_pmu *pmu; + + list_for_each_entry(pmu, &core_pmus, list) { + if (!strcmp(pmu->name, name) || + (pmu->alias_name && !strcmp(pmu->alias_name, name))) + return pmu; + } + list_for_each_entry(pmu, &other_pmus, list) { + if (!strcmp(pmu->name, name) || + (pmu->alias_name && !strcmp(pmu->alias_name, name))) + return pmu; + } + + return NULL; +} + +struct perf_pmu *perf_pmus__find(const char *name) +{ + struct perf_pmu *pmu; + int dirfd; + bool core_pmu; + + /* + * Once PMU is loaded it stays in the list, + * so we keep us from multiple reading/parsing + * the pmu format definitions. + */ + pmu = pmu_find(name); + if (pmu) + return pmu; + + if (read_sysfs_all_pmus) + return NULL; + + core_pmu = is_pmu_core(name); + if (core_pmu && read_sysfs_core_pmus) + return NULL; + + dirfd = perf_pmu__event_source_devices_fd(); + pmu = perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name); + close(dirfd); + + return pmu; +} + +static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) +{ + struct perf_pmu *pmu; + bool core_pmu; + + /* + * Once PMU is loaded it stays in the list, + * so we keep us from multiple reading/parsing + * the pmu format definitions. + */ + pmu = pmu_find(name); + if (pmu) + return pmu; + + if (read_sysfs_all_pmus) + return NULL; + + core_pmu = is_pmu_core(name); + if (core_pmu && read_sysfs_core_pmus) + return NULL; + + return perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name); +} + +/* Add all pmus in sysfs to pmu list: */ +static void pmu_read_sysfs(bool core_only) +{ + int fd; + DIR *dir; + struct dirent *dent; + + if (read_sysfs_all_pmus || (core_only && read_sysfs_core_pmus)) + return; + + fd = perf_pmu__event_source_devices_fd(); + if (fd < 0) + return; + + dir = fdopendir(fd); + if (!dir) + return; + + while ((dent = readdir(dir))) { + if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) + continue; + if (core_only && !is_pmu_core(dent->d_name)) + continue; + /* add to static LIST_HEAD(core_pmus) or LIST_HEAD(other_pmus): */ + perf_pmu__find2(fd, dent->d_name); + } + + closedir(dir); + if (core_only) { + read_sysfs_core_pmus = true; + } else { + read_sysfs_core_pmus = true; + read_sysfs_all_pmus = true; + } +} + +static struct perf_pmu *__perf_pmus__find_by_type(unsigned int type) +{ + struct perf_pmu *pmu; + + list_for_each_entry(pmu, &core_pmus, list) { + if (pmu->type == type) + return pmu; + } + + list_for_each_entry(pmu, &other_pmus, list) { + if (pmu->type == type) + return pmu; + } + return NULL; +} + +struct perf_pmu *perf_pmus__find_by_type(unsigned int type) +{ + struct perf_pmu *pmu = __perf_pmus__find_by_type(type); + + if (pmu || read_sysfs_all_pmus) + return pmu; + + pmu_read_sysfs(/*core_only=*/false); + pmu = __perf_pmus__find_by_type(type); + return pmu; +} + +/* + * pmu iterator: If pmu is NULL, we start at the begin, otherwise return the + * next pmu. Returns NULL on end. + */ +struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu) +{ + bool use_core_pmus = !pmu || pmu->is_core; + + if (!pmu) { + pmu_read_sysfs(/*core_only=*/false); + pmu = list_prepare_entry(pmu, &core_pmus, list); + } + if (use_core_pmus) { + list_for_each_entry_continue(pmu, &core_pmus, list) + return pmu; + + pmu = NULL; + pmu = list_prepare_entry(pmu, &other_pmus, list); + } + list_for_each_entry_continue(pmu, &other_pmus, list) + return pmu; + return NULL; +} + +struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) +{ + if (!pmu) { + pmu_read_sysfs(/*core_only=*/true); + pmu = list_prepare_entry(pmu, &core_pmus, list); + } + list_for_each_entry_continue(pmu, &core_pmus, list) + return pmu; + + return NULL; +} + +const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str) +{ + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmus__scan(pmu)) != NULL) { + if (!strcmp(pmu->name, str)) + return pmu; + /* Ignore "uncore_" prefix. */ + if (!strncmp(pmu->name, "uncore_", 7)) { + if (!strcmp(pmu->name + 7, str)) + return pmu; + } + /* Ignore "cpu_" prefix on Intel hybrid PMUs. */ + if (!strncmp(pmu->name, "cpu_", 4)) { + if (!strcmp(pmu->name + 4, str)) + return pmu; + } + } + return NULL; +} + +int perf_pmus__num_mem_pmus(void) +{ + /* All core PMUs are for mem events. */ + return perf_pmus__num_core_pmus(); +} + +/** Struct for ordering events as output in perf list. */ +struct sevent { + /** PMU for event. */ + const struct perf_pmu *pmu; + /** + * Optional event for name, desc, etc. If not present then this is a + * selectable PMU and the event name is shown as "//". + */ + const struct perf_pmu_alias *event; + /** Is the PMU for the CPU? */ + bool is_cpu; +}; + +static int cmp_sevent(const void *a, const void *b) +{ + const struct sevent *as = a; + const struct sevent *bs = b; + const char *a_pmu_name = NULL, *b_pmu_name = NULL; + const char *a_name = "//", *a_desc = NULL, *a_topic = ""; + const char *b_name = "//", *b_desc = NULL, *b_topic = ""; + int ret; + + if (as->event) { + a_name = as->event->name; + a_desc = as->event->desc; + a_topic = as->event->topic ?: ""; + a_pmu_name = as->event->pmu_name; + } + if (bs->event) { + b_name = bs->event->name; + b_desc = bs->event->desc; + b_topic = bs->event->topic ?: ""; + b_pmu_name = bs->event->pmu_name; + } + /* Put extra events last. */ + if (!!a_desc != !!b_desc) + return !!a_desc - !!b_desc; + + /* Order by topics. */ + ret = strcmp(a_topic, b_topic); + if (ret) + return ret; + + /* Order CPU core events to be first */ + if (as->is_cpu != bs->is_cpu) + return as->is_cpu ? -1 : 1; + + /* Order by PMU name. */ + if (as->pmu != bs->pmu) { + a_pmu_name = a_pmu_name ?: (as->pmu->name ?: ""); + b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: ""); + ret = strcmp(a_pmu_name, b_pmu_name); + if (ret) + return ret; + } + + /* Order by event name. */ + return strcmp(a_name, b_name); +} + +static bool pmu_alias_is_duplicate(struct sevent *alias_a, + struct sevent *alias_b) +{ + const char *a_pmu_name = NULL, *b_pmu_name = NULL; + const char *a_name = "//", *b_name = "//"; + + + if (alias_a->event) { + a_name = alias_a->event->name; + a_pmu_name = alias_a->event->pmu_name; + } + if (alias_b->event) { + b_name = alias_b->event->name; + b_pmu_name = alias_b->event->pmu_name; + } + + /* Different names -> never duplicates */ + if (strcmp(a_name, b_name)) + return false; + + /* Don't remove duplicates for different PMUs */ + a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: ""); + b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: ""); + return strcmp(a_pmu_name, b_pmu_name) == 0; +} + +static int sub_non_neg(int a, int b) +{ + if (b > a) + return 0; + return a - b; +} + +static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, + const struct perf_pmu_alias *alias) +{ + struct parse_events_term *term; + int used = snprintf(buf, len, "%s/%s", pmu->name, alias->name); + + list_for_each_entry(term, &alias->terms, list) { + if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) + used += snprintf(buf + used, sub_non_neg(len, used), + ",%s=%s", term->config, + term->val.str); + } + + if (sub_non_neg(len, used) > 0) { + buf[used] = '/'; + used++; + } + if (sub_non_neg(len, used) > 0) { + buf[used] = '\0'; + used++; + } else + buf[len - 1] = '\0'; + + return buf; +} + +void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state) +{ + struct perf_pmu *pmu; + struct perf_pmu_alias *event; + char buf[1024]; + int printed = 0; + int len, j; + struct sevent *aliases; + + pmu = NULL; + len = 0; + while ((pmu = perf_pmus__scan(pmu)) != NULL) { + list_for_each_entry(event, &pmu->aliases, list) + len++; + if (pmu->selectable) + len++; + } + aliases = zalloc(sizeof(struct sevent) * len); + if (!aliases) { + pr_err("FATAL: not enough memory to print PMU events\n"); + return; + } + pmu = NULL; + j = 0; + while ((pmu = perf_pmus__scan(pmu)) != NULL) { + bool is_cpu = pmu->is_core; + + list_for_each_entry(event, &pmu->aliases, list) { + aliases[j].event = event; + aliases[j].pmu = pmu; + aliases[j].is_cpu = is_cpu; + j++; + } + if (pmu->selectable) { + aliases[j].event = NULL; + aliases[j].pmu = pmu; + aliases[j].is_cpu = is_cpu; + j++; + } + } + len = j; + qsort(aliases, len, sizeof(struct sevent), cmp_sevent); + for (j = 0; j < len; j++) { + const char *name, *alias = NULL, *scale_unit = NULL, + *desc = NULL, *long_desc = NULL, + *encoding_desc = NULL, *topic = NULL, + *pmu_name = NULL; + bool deprecated = false; + size_t buf_used; + + /* Skip duplicates */ + if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) + continue; + + if (!aliases[j].event) { + /* A selectable event. */ + pmu_name = aliases[j].pmu->name; + buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1; + name = buf; + } else { + if (aliases[j].event->desc) { + name = aliases[j].event->name; + buf_used = 0; + } else { + name = format_alias(buf, sizeof(buf), aliases[j].pmu, + aliases[j].event); + if (aliases[j].is_cpu) { + alias = name; + name = aliases[j].event->name; + } + buf_used = strlen(buf) + 1; + } + pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: ""); + if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) { + scale_unit = buf + buf_used; + buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, + "%G%s", aliases[j].event->scale, + aliases[j].event->unit) + 1; + } + desc = aliases[j].event->desc; + long_desc = aliases[j].event->long_desc; + topic = aliases[j].event->topic; + encoding_desc = buf + buf_used; + buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, + "%s/%s/", pmu_name, aliases[j].event->str) + 1; + deprecated = aliases[j].event->deprecated; + } + print_cb->print_event(print_state, + pmu_name, + topic, + name, + alias, + scale_unit, + deprecated, + "Kernel PMU event", + desc, + long_desc, + encoding_desc); + } + if (printed && pager_in_use()) + printf("\n"); + + zfree(&aliases); +} + +bool perf_pmus__have_event(const char *pname, const char *name) +{ + struct perf_pmu *pmu = perf_pmus__find(pname); + + return pmu && perf_pmu__have_event(pmu, name); +} + +int perf_pmus__num_core_pmus(void) +{ + static int count; + + if (!count) { + struct perf_pmu *pmu = NULL; + + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) + count++; + } + return count; +} + +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel->pmu; + + if (!pmu) { + pmu = perf_pmus__find_by_type(evsel->core.attr.type); + ((struct evsel *)evsel)->pmu = pmu; + } + return pmu; +} diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h index 5ec12007eb5c..1e710720aec7 100644 --- a/tools/perf/util/pmus.h +++ b/tools/perf/util/pmus.h @@ -2,8 +2,22 @@ #ifndef __PMUS_H #define __PMUS_H -extern struct list_head pmus; +struct perf_pmu; +struct print_callbacks; -#define perf_pmus__for_each_pmu(pmu) list_for_each_entry(pmu, &pmus, list) +void perf_pmus__destroy(void); + +struct perf_pmu *perf_pmus__find(const char *name); +struct perf_pmu *perf_pmus__find_by_type(unsigned int type); + +struct perf_pmu *perf_pmus__scan(struct perf_pmu *pmu); +struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu); + +const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str); + +int perf_pmus__num_mem_pmus(void); +void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state); +bool perf_pmus__have_event(const char *pname, const char *name); +int perf_pmus__num_core_pmus(void); #endif /* __PMUS_H */ diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index ee145cec42c0..7a5f87392720 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -20,13 +20,14 @@ #include "metricgroup.h" #include "parse-events.h" #include "pmu.h" +#include "pmus.h" #include "print-events.h" #include "probe-file.h" #include "string2.h" #include "strlist.h" #include "tracepoint.h" #include "pfm.h" -#include "pmu-hybrid.h" +#include "thread_map.h" #define MAX_NAME_LEN 100 @@ -228,60 +229,93 @@ void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) strlist__delete(sdtlist); } +static bool is_event_supported(u8 type, u64 config) +{ + bool ret = true; + int open_return; + struct evsel *evsel; + struct perf_event_attr attr = { + .type = type, + .config = config, + .disabled = 1, + }; + struct perf_thread_map *tmap = thread_map__new_by_tid(0); + + if (tmap == NULL) + return false; + + evsel = evsel__new(&attr); + if (evsel) { + open_return = evsel__open(evsel, NULL, tmap); + ret = open_return >= 0; + + if (open_return == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->core.attr.exclude_kernel = 1; + ret = evsel__open(evsel, NULL, tmap) >= 0; + } + evsel__delete(evsel); + } + + perf_thread_map__put(tmap); + return ret; +} + int print_hwcache_events(const struct print_callbacks *print_cb, void *print_state) { - struct strlist *evt_name_list = strlist__new(NULL, NULL); - struct str_node *nd; + struct perf_pmu *pmu = NULL; + const char *event_type_descriptor = event_type_descriptors[PERF_TYPE_HW_CACHE]; - if (!evt_name_list) { - pr_debug("Failed to allocate new strlist for hwcache events\n"); - return -ENOMEM; - } - for (int type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (int op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { - /* skip invalid cache type */ - if (!evsel__is_cache_op_valid(type, op)) - continue; - - for (int i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - struct perf_pmu *pmu = NULL; - char name[64]; - - __evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); - if (!perf_pmu__has_hybrid()) { - if (is_event_supported(PERF_TYPE_HW_CACHE, - type | (op << 8) | (i << 16))) - strlist__add(evt_name_list, name); + /* + * Only print core PMUs, skipping uncore for performance and + * PERF_TYPE_SOFTWARE that can succeed in opening legacy cache evenst. + */ + while ((pmu = perf_pmus__scan_core(pmu)) != NULL) { + if (pmu->is_uncore || pmu->type == PERF_TYPE_SOFTWARE) + continue; + + for (int type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (int op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!evsel__is_cache_op_valid(type, op)) continue; - } - perf_pmu__for_each_hybrid_pmu(pmu) { - if (is_event_supported(PERF_TYPE_HW_CACHE, - type | (op << 8) | (i << 16) | - ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT))) { - char new_name[128]; - snprintf(new_name, sizeof(new_name), - "%s/%s/", pmu->name, name); - strlist__add(evt_name_list, new_name); - } + + for (int res = 0; res < PERF_COUNT_HW_CACHE_RESULT_MAX; res++) { + char name[64]; + char alias_name[128]; + __u64 config; + int ret; + + __evsel__hw_cache_type_op_res_name(type, op, res, + name, sizeof(name)); + + ret = parse_events__decode_legacy_cache(name, pmu->type, + &config); + if (ret || !is_event_supported(PERF_TYPE_HW_CACHE, config)) + continue; + snprintf(alias_name, sizeof(alias_name), "%s/%s/", + pmu->name, name); + print_cb->print_event(print_state, + "cache", + pmu->name, + name, + alias_name, + /*scale_unit=*/NULL, + /*deprecated=*/false, + event_type_descriptor, + /*desc=*/NULL, + /*long_desc=*/NULL, + /*encoding_desc=*/NULL); } } } } - - strlist__for_each_entry(nd, evt_name_list) { - print_cb->print_event(print_state, - "cache", - /*pmu_name=*/NULL, - nd->s, - /*event_alias=*/NULL, - /*scale_unit=*/NULL, - /*deprecated=*/false, - event_type_descriptors[PERF_TYPE_HW_CACHE], - /*desc=*/NULL, - /*long_desc=*/NULL, - /*encoding_desc=*/NULL); - } - strlist__delete(evt_name_list); return 0; } @@ -370,7 +404,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) print_hwcache_events(print_cb, print_state); - print_pmu_events(print_cb, print_state); + perf_pmus__print_pmu_events(print_cb, print_state); print_cb->print_event(print_state, /*topic=*/NULL, diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index aa5156c2bcff..d4c9b4cd35ef 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -39,5 +39,4 @@ util/affinity.c util/rwsem.c util/hashmap.c util/perf_regs.c -util/pmu-hybrid.c util/fncache.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 0faea4c75eed..8de1b759bbaa 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -22,6 +22,7 @@ #include "util/bpf-filter.h" #include "util/env.h" #include "util/pmu.h" +#include "util/pmus.h" #include <internal/lib.h> #include "util.h" @@ -50,6 +51,14 @@ #endif /* + * Avoid bringing in event parsing. + */ +int parse_event(struct evlist *evlist __maybe_unused, const char *str __maybe_unused) +{ + return 0; +} + +/* * Provide these two so that we don't have to link against callchain.c and * start dragging hist.c, etc. */ @@ -94,6 +103,11 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, return EOF; } +int perf_pmus__num_core_pmus(void) +{ + return 1; +} + bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused) { return false; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 039d0365ad41..65b761d83a1f 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -67,8 +67,6 @@ INTERP my_perl; #define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(unsigned short) * 8)) - 1) -static DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX); - extern struct scripting_context *scripting_context; static char *cur_field_name; @@ -353,7 +351,9 @@ static void perl_process_tracepoint(struct perf_sample *sample, void *data = sample->raw_data; unsigned long long nsecs = sample->time; const char *comm = thread__comm_str(thread); + DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX); + bitmap_zero(events_defined, TRACE_EVENT_TYPE_MAX); dSP; if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 41d4f9e6a8b7..40964078f92f 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -93,8 +93,6 @@ PyMODINIT_FUNC PyInit_perf_trace_context(void); #define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(unsigned short) * 8)) - 1) -static DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX); - #define N_COMMON_FIELDS 7 static char *cur_field_name; @@ -934,6 +932,9 @@ static void python_process_tracepoint(struct perf_sample *sample, unsigned long long nsecs = sample->time; const char *comm = thread__comm_str(al->thread); const char *default_handler_name = "trace_unhandled"; + DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX); + + bitmap_zero(events_defined, TRACE_EVENT_TYPE_MAX); if (!event) { snprintf(handler_name, sizeof(handler_name), diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index c294db713677..869738fc06c3 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -36,6 +36,10 @@ if cc_is_clang: vars[var] = sub("-fno-semantic-interposition", "", vars[var]) if not clang_has_option("-ffat-lto-objects"): vars[var] = sub("-ffat-lto-objects", "", vars[var]) + if not clang_has_option("-ftree-loop-distribute-patterns"): + vars[var] = sub("-ftree-loop-distribute-patterns", "", vars[var]) + if not clang_has_option("-gno-variable-location-views"): + vars[var] = sub("-gno-variable-location-views", "", vars[var]) from setuptools import setup, Extension diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index bf5a6c14dfcd..a2bbdc25d979 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -19,8 +19,8 @@ #include <api/fs/fs.h> #include "util.h" #include "iostat.h" -#include "pmu-hybrid.h" -#include "evlist-hybrid.h" +#include "pmu.h" +#include "pmus.h" #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" @@ -36,6 +36,7 @@ static int aggr_header_lens[] = { [AGGR_CORE] = 18, + [AGGR_CACHE] = 22, [AGGR_DIE] = 12, [AGGR_SOCKET] = 6, [AGGR_NODE] = 6, @@ -46,6 +47,7 @@ static int aggr_header_lens[] = { static const char *aggr_header_csv[] = { [AGGR_CORE] = "core,cpus,", + [AGGR_CACHE] = "cache,cpus,", [AGGR_DIE] = "die,cpus,", [AGGR_SOCKET] = "socket,cpus,", [AGGR_NONE] = "cpu,", @@ -56,6 +58,7 @@ static const char *aggr_header_csv[] = { static const char *aggr_header_std[] = { [AGGR_CORE] = "core", + [AGGR_CACHE] = "cache", [AGGR_DIE] = "die", [AGGR_SOCKET] = "socket", [AGGR_NONE] = "cpu", @@ -193,6 +196,10 @@ static void print_aggr_id_std(struct perf_stat_config *config, case AGGR_CORE: snprintf(buf, sizeof(buf), "S%d-D%d-C%d", id.socket, id.die, id.core); break; + case AGGR_CACHE: + snprintf(buf, sizeof(buf), "S%d-D%d-L%d-ID%d", + id.socket, id.die, id.cache_lvl, id.cache); + break; case AGGR_DIE: snprintf(buf, sizeof(buf), "S%d-D%d", id.socket, id.die); break; @@ -239,6 +246,10 @@ static void print_aggr_id_csv(struct perf_stat_config *config, fprintf(output, "S%d-D%d-C%d%s%d%s", id.socket, id.die, id.core, sep, aggr_nr, sep); break; + case AGGR_CACHE: + fprintf(config->output, "S%d-D%d-L%d-ID%d%s%d%s", + id.socket, id.die, id.cache_lvl, id.cache, sep, aggr_nr, sep); + break; case AGGR_DIE: fprintf(output, "S%d-D%d%s%d%s", id.socket, id.die, sep, aggr_nr, sep); @@ -284,6 +295,10 @@ static void print_aggr_id_json(struct perf_stat_config *config, fprintf(output, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d, ", id.socket, id.die, id.core, aggr_nr); break; + case AGGR_CACHE: + fprintf(output, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d, ", + id.socket, id.die, id.cache_lvl, id.cache, aggr_nr); + break; case AGGR_DIE: fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ", id.socket, id.die, aggr_nr); @@ -677,6 +692,21 @@ static bool is_mixed_hw_group(struct evsel *counter) return false; } +static bool evlist__has_hybrid(struct evlist *evlist) +{ + struct evsel *evsel; + + if (perf_pmus__num_core_pmus() == 1) + return false; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.is_pmu_core) + return true; + } + + return false; +} + static void printout(struct perf_stat_config *config, struct outstate *os, double uval, u64 run, u64 ena, double noise, int aggr_idx) { @@ -1125,6 +1155,7 @@ static void print_header_interval_std(struct perf_stat_config *config, case AGGR_NODE: case AGGR_SOCKET: case AGGR_DIE: + case AGGR_CACHE: case AGGR_CORE: fprintf(output, "#%*s %-*s cpus", INTERVAL_LEN - 1, "time", @@ -1425,6 +1456,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf switch (config->aggr_mode) { case AGGR_CORE: + case AGGR_CACHE: case AGGR_DIE: case AGGR_SOCKET: case AGGR_NODE: diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index e35e188237c8..7abff7cbb5a1 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -48,6 +48,7 @@ enum aggr_mode { AGGR_GLOBAL, AGGR_SOCKET, AGGR_DIE, + AGGR_CACHE, AGGR_CORE, AGGR_THREAD, AGGR_UNSET, @@ -64,6 +65,7 @@ typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, str struct perf_stat_config { enum aggr_mode aggr_mode; + u32 aggr_level; bool scale; bool no_inherit; bool identifier; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index b2e4afa5efa1..45714a2785fd 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1375,6 +1375,7 @@ int perf_event__synthesize_stat_config(struct perf_tool *tool, ADD(AGGR_MODE, config->aggr_mode) ADD(INTERVAL, config->interval) ADD(SCALE, config->scale) + ADD(AGGR_LEVEL, config->aggr_level) WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX, "stat config terms unbalanced\n"); diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index 880f1af7f6ad..d582cae8e105 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -17,7 +17,6 @@ struct target { bool default_per_cpu; bool per_thread; bool use_bpf; - bool hybrid; int initial_delay; const char *attr_map; }; |