| Message ID | 20180808145945.26159-2-chris@chris-wilson.co.uk (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [i-g-t,1/2] igt/perf_pmu: Aim for a fixed number of iterations for calibrating accuracy | expand |
On 08/08/2018 15:59, Chris Wilson wrote: > Normalize the variance to stddev, and remove some redundant steps in > computing the time from itself. > > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> > --- > tests/perf_pmu.c | 22 +++++++++++++--------- > 1 file changed, 13 insertions(+), 9 deletions(-) > > diff --git a/tests/perf_pmu.c b/tests/perf_pmu.c > index 5a26d5272..4e8da3d94 100644 > --- a/tests/perf_pmu.c > +++ b/tests/perf_pmu.c > @@ -1577,8 +1577,8 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, > /* 1st pass is calibration, second pass is the test. */ > for (int pass = 0; pass < ARRAY_SIZE(timeout); pass++) { > unsigned int target_idle_us = idle_us; > - uint64_t busy_ns = 0, idle_ns = 0; > struct timespec start = { }; > + uint64_t busy_ns = 0; > unsigned long pass_ns = 0; > double avg = 0.0, var = 0.0; > unsigned int n = 0; > @@ -1589,6 +1589,7 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, > unsigned long loop_ns, loop_busy; > struct timespec _ts = { }; > double err, tmp; > + uint64_t now; > > /* PWM idle sleep. */ > _ts.tv_nsec = target_idle_us * 1000; > @@ -1605,14 +1606,13 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, > igt_spin_batch_end(spin); > > /* Time accounting. */ > - loop_ns = igt_nsec_elapsed(&start); > - loop_busy = loop_ns - loop_busy; > - loop_ns -= pass_ns; > + now = igt_nsec_elapsed(&start); > + loop_busy = now - loop_busy; > + loop_ns = now - pass_ns; > + pass_ns = now; > > busy_ns += loop_busy; > total_busy_ns += loop_busy; > - idle_ns += loop_ns - loop_busy; > - pass_ns += loop_ns; > total_ns += loop_ns; Looks okay, but ugh... just made me lose ten minutes reconstructing before and after for no real benefit. :I > > /* Re-calibrate. */ > @@ -1628,10 +1628,14 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, > var += (err - avg) * (err - tmp); > } while (pass_ns < timeout[pass]); > > + pass_ns = igt_nsec_elapsed(&start); > expected = (double)busy_ns / pass_ns; > - igt_info("%u: busy %"PRIu64"us, idle %"PRIu64"us -> %.2f%% (target: %lu%%; average=%.2f, variance=%f)\n", > - pass, busy_ns / 1000, idle_ns / 1000, > - 100 * expected, target_busy_pct, avg, var / n); > + > + igt_info("%u: busy %"PRIu64"us, idle %"PRIu64"us -> %.2f%% (target: %lu%%; average=%.2f±%.3f%%)\n", > + pass, busy_ns / 1000, (pass_ns - busy_ns) / 1000, > + 100 * expected, target_busy_pct, > + avg, sqrt(var / n)); > + > write(link[1], &expected, sizeof(expected)); > } > > Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Regards, Tvrtko
diff --git a/tests/perf_pmu.c b/tests/perf_pmu.c index 5a26d5272..4e8da3d94 100644 --- a/tests/perf_pmu.c +++ b/tests/perf_pmu.c @@ -1577,8 +1577,8 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, /* 1st pass is calibration, second pass is the test. */ for (int pass = 0; pass < ARRAY_SIZE(timeout); pass++) { unsigned int target_idle_us = idle_us; - uint64_t busy_ns = 0, idle_ns = 0; struct timespec start = { }; + uint64_t busy_ns = 0; unsigned long pass_ns = 0; double avg = 0.0, var = 0.0; unsigned int n = 0; @@ -1589,6 +1589,7 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, unsigned long loop_ns, loop_busy; struct timespec _ts = { }; double err, tmp; + uint64_t now; /* PWM idle sleep. */ _ts.tv_nsec = target_idle_us * 1000; @@ -1605,14 +1606,13 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, igt_spin_batch_end(spin); /* Time accounting. */ - loop_ns = igt_nsec_elapsed(&start); - loop_busy = loop_ns - loop_busy; - loop_ns -= pass_ns; + now = igt_nsec_elapsed(&start); + loop_busy = now - loop_busy; + loop_ns = now - pass_ns; + pass_ns = now; busy_ns += loop_busy; total_busy_ns += loop_busy; - idle_ns += loop_ns - loop_busy; - pass_ns += loop_ns; total_ns += loop_ns; /* Re-calibrate. */ @@ -1628,10 +1628,14 @@ accuracy(int gem_fd, const struct intel_execution_engine2 *e, var += (err - avg) * (err - tmp); } while (pass_ns < timeout[pass]); + pass_ns = igt_nsec_elapsed(&start); expected = (double)busy_ns / pass_ns; - igt_info("%u: busy %"PRIu64"us, idle %"PRIu64"us -> %.2f%% (target: %lu%%; average=%.2f, variance=%f)\n", - pass, busy_ns / 1000, idle_ns / 1000, - 100 * expected, target_busy_pct, avg, var / n); + + igt_info("%u: busy %"PRIu64"us, idle %"PRIu64"us -> %.2f%% (target: %lu%%; average=%.2f±%.3f%%)\n", + pass, busy_ns / 1000, (pass_ns - busy_ns) / 1000, + 100 * expected, target_busy_pct, + avg, sqrt(var / n)); + write(link[1], &expected, sizeof(expected)); }
Normalize the variance to stddev, and remove some redundant steps in computing the time from itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> --- tests/perf_pmu.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-)