Carl Worth 2fa0228d63 Two big improvements to bring the std. deviation down to where we want it. ... 1. Remove all the alarm/signal code, which just isn't doing what we want for some reason. Instead, for now we'll simply run for a fixed number of iterations, (perhaps we can tune that per test later). 2. Before computing mean and stdandard deviation of runs, sort them all and discard the top and bottom 20% of the values. Now the standard deviation for the paint test is generally 2% or less.		2006-08-31 17:43:40 -07:00
..
.gitignore	perf: Don't measure meta-surface-backed surface types.	2006-08-31 08:53:58 -07:00
cairo-perf-timer-posix.c	perf: Switch from alarm to setitimer for more fine-grained control of timers	2006-08-31 14:08:43 -07:00
cairo-perf-timer-win32.c	perf: Switch from alarm to setitimer for more fine-grained control of timers	2006-08-31 14:08:43 -07:00
cairo-perf-timer.h	perf: Switch from alarm to setitimer for more fine-grained control of timers	2006-08-31 14:08:43 -07:00
cairo-perf.c	Two big improvements to bring the std. deviation down to where we want it.	2006-08-31 17:43:40 -07:00
cairo-perf.h	Two big improvements to bring the std. deviation down to where we want it.	2006-08-31 17:43:40 -07:00
Makefile.am	perf: Rename timer-alarm files to cairo-perf-timer	2006-08-31 11:38:23 -07:00
paint.c	Two big improvements to bring the std. deviation down to where we want it.	2006-08-31 17:43:40 -07:00