#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
+#include "util/color.h"
#include "util/header.h"
#include "util/cpumap.h"
#include "util/thread.h"
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES },
- { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES },
- { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES },
};
struct stats runtime_nsecs_stats[MAX_NR_CPUS];
struct stats runtime_cycles_stats[MAX_NR_CPUS];
+struct stats runtime_stalled_cycles_stats[MAX_NR_CPUS];
struct stats runtime_branches_stats[MAX_NR_CPUS];
+struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
+struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
struct stats walltime_nsecs_stats;
static int create_perf_stat_counter(struct perf_evsel *evsel)
return 0;
}
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
+{
+ if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+ update_stats(&runtime_nsecs_stats[0], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+ update_stats(&runtime_cycles_stats[0], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES))
+ update_stats(&runtime_stalled_cycles_stats[0], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+ update_stats(&runtime_branches_stats[0], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+ update_stats(&runtime_cacherefs_stats[0], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+ update_stats(&runtime_l1_dcache_stats[0], count[0]);
+}
+
/*
* Read out the results of a single counter:
* aggregate counts across CPUs in system-wide mode
/*
* Save the full runtime - to allow normalization during printout:
*/
- if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
- update_stats(&runtime_nsecs_stats[0], count[0]);
- if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[0], count[0]);
- if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[0], count[0]);
+ update_shadow_stats(counter, count);
return 0;
}
count = counter->counts->cpu[cpu].values;
- if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
- update_stats(&runtime_nsecs_stats[cpu], count[0]);
- if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[cpu], count[0]);
- if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[cpu], count[0]);
+ update_shadow_stats(counter, count);
}
return 0;
return WEXITSTATUS(status);
}
+static void print_noise_pct(double total, double avg)
+{
+ double pct = 0.0;
+
+ if (avg)
+ pct = 100.0*total/avg;
+
+ fprintf(stderr, " ( +-%6.2f%% )", pct);
+}
+
static void print_noise(struct perf_evsel *evsel, double avg)
{
struct perf_stat *ps;
return;
ps = evsel->priv;
- fprintf(stderr, " ( +- %7.3f%% )",
- 100 * stddev_stats(&ps->res_stats[0]) / avg);
+ print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
}
static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
return;
if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
- fprintf(stderr, " # %10.3f CPUs ",
- avg / avg_stats(&walltime_nsecs_stats));
+ fprintf(stderr, " # %8.3f CPUs utilized ", avg / avg_stats(&walltime_nsecs_stats));
+}
+
+static void print_stalled_cycles(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+
+ total = avg_stats(&runtime_cycles_stats[cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = PERF_COLOR_NORMAL;
+ if (ratio > 75.0)
+ color = PERF_COLOR_RED;
+ else if (ratio > 50.0)
+ color = PERF_COLOR_MAGENTA;
+ else if (ratio > 25.0)
+ color = PERF_COLOR_YELLOW;
+
+ fprintf(stderr, " # ");
+ color_fprintf(stderr, color, "%5.2f%%", ratio);
+ fprintf(stderr, " of all cycles are idle ");
+}
+
+static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+
+ total = avg_stats(&runtime_branches_stats[cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = PERF_COLOR_NORMAL;
+ if (ratio > 20.0)
+ color = PERF_COLOR_RED;
+ else if (ratio > 10.0)
+ color = PERF_COLOR_MAGENTA;
+ else if (ratio > 5.0)
+ color = PERF_COLOR_YELLOW;
+
+ fprintf(stderr, " # ");
+ color_fprintf(stderr, color, "%5.2f%%", ratio);
+ fprintf(stderr, " of all branches ");
+}
+
+static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+
+ total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = PERF_COLOR_NORMAL;
+ if (ratio > 20.0)
+ color = PERF_COLOR_RED;
+ else if (ratio > 10.0)
+ color = PERF_COLOR_MAGENTA;
+ else if (ratio > 5.0)
+ color = PERF_COLOR_YELLOW;
+
+ fprintf(stderr, " # ");
+ color_fprintf(stderr, color, "%5.2f%%", ratio);
+ fprintf(stderr, " of all L1-dcache hits ");
}
static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
if (total)
ratio = avg / total;
- fprintf(stderr, " # %10.3f IPC ", ratio);
+ fprintf(stderr, " # %4.2f insns per cycle", ratio);
+
+ total = avg_stats(&runtime_stalled_cycles_stats[cpu]);
+
+ if (total && avg) {
+ ratio = total / avg;
+ fprintf(stderr, "\n # %4.2f stalled cycles per insn", ratio);
+ }
+
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
runtime_branches_stats[cpu].n != 0) {
- total = avg_stats(&runtime_branches_stats[cpu]);
+ print_branch_misses(cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_branches_stats[cpu].n != 0) {
+ print_l1_dcache_misses(cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+ runtime_cacherefs_stats[cpu].n != 0) {
+ total = avg_stats(&runtime_cacherefs_stats[cpu]);
if (total)
ratio = avg * 100 / total;
- fprintf(stderr, " # %10.3f %% ", ratio);
+ fprintf(stderr, " # %8.3f %% of all cache refs ", ratio);
+
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES)) {
+ print_stalled_cycles(cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+ total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+ if (total)
+ ratio = 1.0 * avg / total;
+ fprintf(stderr, " # %8.3f GHz ", ratio);
} else if (runtime_nsecs_stats[cpu].n != 0) {
total = avg_stats(&runtime_nsecs_stats[cpu]);
if (total)
ratio = 1000.0 * avg / total;
- fprintf(stderr, " # %10.3f M/sec", ratio);
+ fprintf(stderr, " # %8.3f M/sec ", ratio);
+ } else {
+ fprintf(stderr, " ");
}
}
fprintf(stderr, " %18.9f seconds time elapsed",
avg_stats(&walltime_nsecs_stats)/1e9);
if (run_count > 1) {
- fprintf(stderr, " ( +- %7.3f%% )",
- 100*stddev_stats(&walltime_nsecs_stats) /
- avg_stats(&walltime_nsecs_stats));
+ print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+ avg_stats(&walltime_nsecs_stats));
}
fprintf(stderr, "\n\n");
}
projects / ~andy / linux / blobdiff