@@ -241,45 +241,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
update_runtime_stat(st, STAT_TRANSACTION, map_idx, count, &rsd);
else if (perf_stat_evsel__is(counter, ELISION_START))
update_runtime_stat(st, STAT_ELISION, map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
- update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
- update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
- update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
- update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
- update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
- update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
- update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
- update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
- update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS))
- update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT))
- update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT))
- update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT,
- map_idx, count, &rsd);
- else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND))
- update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND,
- map_idx, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
map_idx, count, &rsd);
@@ -524,156 +485,6 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio);
}
-/*
- * High level "TopDown" CPU core pipe line bottleneck break down.
- *
- * Basic concept following
- * Yasin, A Top Down Method for Performance analysis and Counter architecture
- * ISPASS14
- *
- * The CPU pipeline is divided into 4 areas that can be bottlenecks:
- *
- * Frontend -> Backend -> Retiring
- * BadSpeculation in addition means out of order execution that is thrown away
- * (for example branch mispredictions)
- * Frontend is instruction decoding.
- * Backend is execution, like computation and accessing data in memory
- * Retiring is good execution that is not directly bottlenecked
- *
- * The formulas are computed in slots.
- * A slot is an entry in the pipeline each for the pipeline width
- * (for example a 4-wide pipeline has 4 slots for each cycle)
- *
- * Formulas:
- * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) /
- * TotalSlots
- * Retiring = SlotsRetired / TotalSlots
- * FrontendBound = FetchBubbles / TotalSlots
- * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound
- *
- * The kernel provides the mapping to the low level CPU events and any scaling
- * needed for the CPU pipeline width, for example:
- *
- * TotalSlots = Cycles * 4
- *
- * The scaling factor is communicated in the sysfs unit.
- *
- * In some cases the CPU may not be able to measure all the formulas due to
- * missing events. In this case multiple formulas are combined, as possible.
- *
- * Full TopDown supports more levels to sub-divide each area: for example
- * BackendBound into computing bound and memory bound. For now we only
- * support Level 1 TopDown.
- */
-
-static double sanitize_val(double x)
-{
- if (x < 0 && x >= -0.02)
- return 0.0;
- return x;
-}
-
-static double td_total_slots(int map_idx, struct runtime_stat *st,
- struct runtime_stat_data *rsd)
-{
- return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, map_idx, rsd);
-}
-
-static double td_bad_spec(int map_idx, struct runtime_stat *st,
- struct runtime_stat_data *rsd)
-{
- double bad_spec = 0;
- double total_slots;
- double total;
-
- total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, map_idx, rsd) -
- runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, map_idx, rsd) +
- runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, map_idx, rsd);
-
- total_slots = td_total_slots(map_idx, st, rsd);
- if (total_slots)
- bad_spec = total / total_slots;
- return sanitize_val(bad_spec);
-}
-
-static double td_retiring(int map_idx, struct runtime_stat *st,
- struct runtime_stat_data *rsd)
-{
- double retiring = 0;
- double total_slots = td_total_slots(map_idx, st, rsd);
- double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
- map_idx, rsd);
-
- if (total_slots)
- retiring = ret_slots / total_slots;
- return retiring;
-}
-
-static double td_fe_bound(int map_idx, struct runtime_stat *st,
- struct runtime_stat_data *rsd)
-{
- double fe_bound = 0;
- double total_slots = td_total_slots(map_idx, st, rsd);
- double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
- map_idx, rsd);
-
- if (total_slots)
- fe_bound = fetch_bub / total_slots;
- return fe_bound;
-}
-
-static double td_be_bound(int map_idx, struct runtime_stat *st,
- struct runtime_stat_data *rsd)
-{
- double sum = (td_fe_bound(map_idx, st, rsd) +
- td_bad_spec(map_idx, st, rsd) +
- td_retiring(map_idx, st, rsd));
- if (sum == 0)
- return 0;
- return sanitize_val(1.0 - sum);
-}
-
-/*
- * Kernel reports metrics multiplied with slots. To get back
- * the ratios we need to recreate the sum.
- */
-
-static double td_metric_ratio(int map_idx, enum stat_type type,
- struct runtime_stat *stat,
- struct runtime_stat_data *rsd)
-{
- double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, map_idx, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, map_idx, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, map_idx, rsd) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, map_idx, rsd);
- double d = runtime_stat_avg(stat, type, map_idx, rsd);
-
- if (sum)
- return d / sum;
- return 0;
-}
-
-/*
- * ... but only if most of the values are actually available.
- * We allow two missing.
- */
-
-static bool full_td(int map_idx, struct runtime_stat *stat,
- struct runtime_stat_data *rsd)
-{
- int c = 0;
-
- if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, map_idx, rsd) > 0)
- c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, map_idx, rsd) > 0)
- c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, map_idx, rsd) > 0)
- c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, map_idx, rsd) > 0)
- c++;
- return c >= 2;
-}
-
static void print_smi_cost(struct perf_stat_config *config, int map_idx,
struct perf_stat_output_ctx *out,
struct runtime_stat *st,
@@ -885,7 +696,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
void *ctxp = out->ctx;
print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
- const char *color = NULL;
struct runtime_stat_data rsd = {
.ctx = evsel_context(evsel),
.cgrp = evsel->cgrp,
@@ -1044,162 +854,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
avg / (ratio * evsel->scale));
else
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(map_idx, st, &rsd);
-
- if (fe_bound > 0.2)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
- fe_bound * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(map_idx, st, &rsd);
-
- if (retiring > 0.7)
- color = PERF_COLOR_GREEN;
- print_metric(config, ctxp, color, "%8.1f%%", "retiring",
- retiring * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(map_idx, st, &rsd);
-
- if (bad_spec > 0.1)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
- bad_spec * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(map_idx, st, &rsd);
- const char *name = "backend bound";
- static int have_recovery_bubbles = -1;
-
- /* In case the CPU does not support topdown-recovery-bubbles */
- if (have_recovery_bubbles < 0)
- have_recovery_bubbles = pmu_have_event("cpu",
- "topdown-recovery-bubbles");
- if (!have_recovery_bubbles)
- name = "backend bound/bad spec";
-
- if (be_bound > 0.2)
- color = PERF_COLOR_RED;
- if (td_total_slots(map_idx, st, &rsd) > 0)
- print_metric(config, ctxp, color, "%8.1f%%", name,
- be_bound * 100.);
- else
- print_metric(config, ctxp, NULL, NULL, name, 0);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
- full_td(map_idx, st, &rsd)) {
- double retiring = td_metric_ratio(map_idx,
- STAT_TOPDOWN_RETIRING, st,
- &rsd);
- if (retiring > 0.7)
- color = PERF_COLOR_GREEN;
- print_metric(config, ctxp, color, "%8.1f%%", "Retiring",
- retiring * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
- full_td(map_idx, st, &rsd)) {
- double fe_bound = td_metric_ratio(map_idx,
- STAT_TOPDOWN_FE_BOUND, st,
- &rsd);
- if (fe_bound > 0.2)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound",
- fe_bound * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
- full_td(map_idx, st, &rsd)) {
- double be_bound = td_metric_ratio(map_idx,
- STAT_TOPDOWN_BE_BOUND, st,
- &rsd);
- if (be_bound > 0.2)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound",
- be_bound * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
- full_td(map_idx, st, &rsd)) {
- double bad_spec = td_metric_ratio(map_idx,
- STAT_TOPDOWN_BAD_SPEC, st,
- &rsd);
- if (bad_spec > 0.1)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation",
- bad_spec * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
- full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) {
- double retiring = td_metric_ratio(map_idx,
- STAT_TOPDOWN_RETIRING, st,
- &rsd);
- double heavy_ops = td_metric_ratio(map_idx,
- STAT_TOPDOWN_HEAVY_OPS, st,
- &rsd);
- double light_ops = retiring - heavy_ops;
-
- if (retiring > 0.7 && heavy_ops > 0.1)
- color = PERF_COLOR_GREEN;
- print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations",
- heavy_ops * 100.);
- if (retiring > 0.7 && light_ops > 0.6)
- color = PERF_COLOR_GREEN;
- else
- color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "Light Operations",
- light_ops * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
- full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) {
- double bad_spec = td_metric_ratio(map_idx,
- STAT_TOPDOWN_BAD_SPEC, st,
- &rsd);
- double br_mis = td_metric_ratio(map_idx,
- STAT_TOPDOWN_BR_MISPREDICT, st,
- &rsd);
- double m_clears = bad_spec - br_mis;
-
- if (bad_spec > 0.1 && br_mis > 0.05)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict",
- br_mis * 100.);
- if (bad_spec > 0.1 && m_clears > 0.05)
- color = PERF_COLOR_RED;
- else
- color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears",
- m_clears * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
- full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) {
- double fe_bound = td_metric_ratio(map_idx,
- STAT_TOPDOWN_FE_BOUND, st,
- &rsd);
- double fetch_lat = td_metric_ratio(map_idx,
- STAT_TOPDOWN_FETCH_LAT, st,
- &rsd);
- double fetch_bw = fe_bound - fetch_lat;
-
- if (fe_bound > 0.2 && fetch_lat > 0.15)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency",
- fetch_lat * 100.);
- if (fe_bound > 0.2 && fetch_bw > 0.1)
- color = PERF_COLOR_RED;
- else
- color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth",
- fetch_bw * 100.);
- } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
- full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) {
- double be_bound = td_metric_ratio(map_idx,
- STAT_TOPDOWN_BE_BOUND, st,
- &rsd);
- double mem_bound = td_metric_ratio(map_idx,
- STAT_TOPDOWN_MEM_BOUND, st,
- &rsd);
- double core_bound = be_bound - mem_bound;
-
- if (be_bound > 0.2 && mem_bound > 0.2)
- color = PERF_COLOR_RED;
- print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound",
- mem_bound * 100.);
- if (be_bound > 0.2 && core_bound > 0.1)
- color = PERF_COLOR_RED;
- else
- color = NULL;
- print_metric(config, ctxp, color, "%8.1f%%", "Core Bound",
- core_bound * 100.);
} else if (runtime_stat_n(st, STAT_NSECS, map_idx, &rsd) != 0) {
char unit = ' ';
char unit_buf[10] = "/sec";
@@ -91,19 +91,6 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
ID(TRANSACTION_START, cpu/tx-start/),
ID(ELISION_START, cpu/el-start/),
ID(CYCLES_IN_TX_CP, cpu/cycles-ct/),
- ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots),
- ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued),
- ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
- ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
- ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
- ID(TOPDOWN_RETIRING, topdown-retiring),
- ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
- ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
- ID(TOPDOWN_BE_BOUND, topdown-be-bound),
- ID(TOPDOWN_HEAVY_OPS, topdown-heavy-ops),
- ID(TOPDOWN_BR_MISPREDICT, topdown-br-mispredict),
- ID(TOPDOWN_FETCH_LAT, topdown-fetch-lat),
- ID(TOPDOWN_MEM_BOUND, topdown-mem-bound),
ID(SMI_NUM, msr/smi/),
ID(APERF, msr/aperf/),
};
@@ -25,19 +25,6 @@ enum perf_stat_evsel_id {
PERF_STAT_EVSEL_ID__TRANSACTION_START,
PERF_STAT_EVSEL_ID__ELISION_START,
PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
- PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS,
- PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED,
- PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
- PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
- PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
- PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING,
- PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC,
- PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND,
- PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND,
- PERF_STAT_EVSEL_ID__TOPDOWN_HEAVY_OPS,
- PERF_STAT_EVSEL_ID__TOPDOWN_BR_MISPREDICT,
- PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_LAT,
- PERF_STAT_EVSEL_ID__TOPDOWN_MEM_BOUND,
PERF_STAT_EVSEL_ID__SMI_NUM,
PERF_STAT_EVSEL_ID__APERF,
PERF_STAT_EVSEL_ID__MAX,
@@ -108,19 +95,6 @@ enum stat_type {
STAT_CYCLES_IN_TX,
STAT_TRANSACTION,
STAT_ELISION,
- STAT_TOPDOWN_TOTAL_SLOTS,
- STAT_TOPDOWN_SLOTS_ISSUED,
- STAT_TOPDOWN_SLOTS_RETIRED,
- STAT_TOPDOWN_FETCH_BUBBLES,
- STAT_TOPDOWN_RECOVERY_BUBBLES,
- STAT_TOPDOWN_RETIRING,
- STAT_TOPDOWN_BAD_SPEC,
- STAT_TOPDOWN_FE_BOUND,
- STAT_TOPDOWN_BE_BOUND,
- STAT_TOPDOWN_HEAVY_OPS,
- STAT_TOPDOWN_BR_MISPREDICT,
- STAT_TOPDOWN_FETCH_LAT,
- STAT_TOPDOWN_MEM_BOUND,
STAT_SMI_NUM,
STAT_APERF,
STAT_MAX
Now the events are computed from json metrics, the hard coded logic can be removed. Signed-off-by: Ian Rogers <irogers@google.com> --- tools/perf/util/stat-shadow.c | 346 ---------------------------------- tools/perf/util/stat.c | 13 -- tools/perf/util/stat.h | 26 --- 3 files changed, 385 deletions(-)