diff options
| author | Lawrence Crowl <crowl@google.com> | 2012-11-07 00:36:04 +0000 |
|---|---|---|
| committer | Lawrence Crowl <crowl@gcc.gnu.org> | 2012-11-07 00:36:04 +0000 |
| commit | bff0e5295af23c7947f7b4804a72e86aeca0ce56 (patch) | |
| tree | 8ab0c916dd01a2cfac2710a91391bbc30eaeb98e /gcc/tree-ssa-loop-ch.c | |
| parent | 8f7a6877dbcd89fd253fd7a6e9ffdb2c7949063e (diff) | |
| download | gcc-bff0e5295af23c7947f7b4804a72e86aeca0ce56.zip gcc-bff0e5295af23c7947f7b4804a72e86aeca0ce56.tar.gz gcc-bff0e5295af23c7947f7b4804a72e86aeca0ce56.tar.bz2 | |
Add a contrib script for comparing the performance of two sets of
compiler runs.
Usage documentation is in the script.
The script produces output of the form:
$ compare_two_ftime_report_sets "Log0/*perf" "Log3/*perf"
Arithmetic sample for timevar log files
"Log0/*perf"
and selecting lines containing "TOTAL" with desired confidence 95 is
trial count is 4, mean is 443.022 (95% confidence in 440.234 to 445.811),
std.deviation is 1.75264, std.error is 0.876322
Arithmetic sample for timevar log files
"Log3/*perf"
and selecting lines containing "TOTAL" with desired confidence 95 is
trial count is 4, mean is 441.302 (95% confidence in 436.671 to 445.934),
std.deviation is 2.91098, std.error is 1.45549
The first sample appears to be 0.39% larger,
with 60% confidence of being larger.
To reach 95% confidence, you need roughly 14 trials,
assuming the standard deviation is stable, which is iffy.
Tested on x86_64 builds.
Index: contrib/ChangeLog
2012-11-05 Lawrence Crowl <crowl@google.com>
* compare_two_ftime_report_sets: New.
From-SVN: r193277
Diffstat (limited to 'gcc/tree-ssa-loop-ch.c')
0 files changed, 0 insertions, 0 deletions