Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9007057189871201312

=== Auto-CCing suspected CL author geofflang@chromium.org ===

Hi geofflang@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Clamp float32 depth data when uploading.
Author  : Geoff Lang
Commit description:
  
BUG=angleproject:1095

Change-Id: I4c272aef0f94733fc7b5297ddaa1fa2bc765fe62
Reviewed-on: https://chromium-review.googlesource.com/360029
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Jamie Madill <jmadill@chromium.org>
Reviewed-by: Geoff Lang <geofflang@chromium.org>
Commit-Queue: Geoff Lang <geofflang@chromium.org>
Commit  : 4107dda958cba1ceed0a58a2c0b5ff61f0bc33a5
Date    : Wed Jul 13 21:28:00 2016


===== TESTED REVISIONS =====
Revision                          Mean     Std Dev  N  Good?
chromium@405550                   29699.2  148.794  5  good
chromium@405576                   29729.2  37.225   5  good
chromium@405578                   29685.0  105.586  5  good
chromium@405579                   29628.8  26.9574  5  good
chromium@405579,angle@4107dda958  28128.8  40.9902  5  bad    <--
chromium@405579,angle@28ff4fd867  28100.6  68.2847  5  bad
chromium@405579,angle@b741c76144  27356.6  161.429  5  bad
chromium@405580                   26482.2  72.1644  5  bad
chromium@405584                   26505.2  224.079  5  bad
chromium@405591                   26528.6  137.616  5  bad
chromium@405602                   26489.8  83.8403  5  bad

Bisect job ran on: winx64nvidia_perf_bisect
Bug ID: 628654

Test Command: .\src\out\Release_x64\angle_perftests.exe --test-launcher-print-test-stdio=always --test-launcher-jobs=1
Test Metric: DrawCallPerf_d3d11_null/score
Relative Change: 10.81%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64nvidia_perf_bisect/builds/1724
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007057189871201312


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5814154829496320

| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!

geofflang, looks like your patch caused a regression. Could you take a look?

Jamie, could this be from the WPO changes?  The blamed CL should have no effect on this test, there are no depth float uploads.

Don't think so, that was a separate regression, and much larger, and was caught correctly by the perf bisect bot. I agree the suspect CL seems innocuous. Try to repro locally, using scripts/perf_test_runner.py before and after your CL with Chromium closed, and fire off another bisect job. If both of those are inconclusive it's very difficult to understand, but we can maybe ask a guru like Bruce to help.

Yes, the regression has started when I've landed my change to disable WPO for these builds, according to the dashboard we're back to the performance that we had on June 1st (before the CL that enabled WPO), so it's not really a regression, we're back to normal.

Alright then. Let's close this out.