fdo-mirrors/cairo
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/cairo/cairo.git synced 2026-05-05 20:28:02 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

[perf] Print min_ticks in report

Browse source 
As the change and ranking is based on the min_ticks, and as this can
sometimes deviate wildly from median_ticks, include min_ticks in the
output.

In particular it helps to explain cases like:

xlib-rgba rectangles_similar-rgba-mag_source-512    10.13 88.41% ->   5.77 0.19%:  1.50x slowdown

which becomes

xlib-rgba rectangles_similar-rgba-mag_source-512    3.83 (10.13 88.41%) ->   5.75 (5.77 0.19%):  1.50x slowdown

(Considering the poor standard deviation on the initial measurement, this
is more likely a sampling error than a true regression.)
This commit is contained in:
Chris Wilson 2009-07-31 10:50:13 +01:00
parent ce8a8424aa
commit e283e53563
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
perf/cairo-perf-diff-files.c
View file

@ -142,11 +142,13 @@ test_diff_print_binary (test_diff_t *diff,
double max_change,
cairo_perf_report_options_t *options)
{
printf ("%5s-%-4s %26s-%-3d %6.2f %4.2f%% -> %6.2f %4.2f%%: %5.2fx ",
printf ("%5s-%-4s %26s-%-3d %6.2f (%.2f %4.2f%%) -> %6.2f (%.2f %4.2f%%): %5.2fx ",
diff->tests[0]->backend, diff->tests[0]->content,
diff->tests[0]->name, diff->tests[0]->size,
diff->tests[0]->stats.min_ticks / diff->tests[0]->stats.ticks_per_ms,
diff->tests[0]->stats.median_ticks / diff->tests[0]->stats.ticks_per_ms,
diff->tests[0]->stats.std_dev * 100,
diff->tests[1]->stats.min_ticks / diff->tests[1]->stats.ticks_per_ms,
diff->tests[1]->stats.median_ticks / diff->tests[1]->stats.ticks_per_ms,
diff->tests[1]->stats.std_dev * 100,
fabs (diff->change));