Issue metadata
Sign in to add a comment
|
32.7% regression in angle_perftests at 466134:466250 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Apr 24 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981424303130860912
,
Apr 24 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981424296955664064
,
Apr 25 2017
=== Auto-CCing suspected CL author jmadill@chromium.org === Hi jmadill@chromium.org, the bisect results pointed to your CL, please take a look at the results. === BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Jamie Madill Commit : 6de518589879b6b5802587bdca74bbb4f614a7f6 Date : Wed Apr 19 21:50:10 2017 Subject: Optimize angle::BitSetIterator. Bisect Details Configuration: winx64nvidia_perf_bisect Benchmark : angle_perftests Metric : Uniforms_gl_matrix_repeating/score Change : 35.52% | 10800.5 -> 6963.83333333 Revision Result N chromium@466133 10800.5 +- 2677.71 12 good chromium@466137 10766.7 +- 2165.75 12 good chromium@466138 10769.3 +- 3022.67 12 good chromium@466138,angle@a0e0aebbf2 10965.0 +- 1899.65 12 good chromium@466138,angle@6de5185898 7124.67 +- 1492.06 12 bad <-- chromium@466138,angle@8162926b2b 7186.5 +- 1244.06 12 bad chromium@466139 6943.83 +- 1938.18 12 bad chromium@466140 7297.33 +- 1295.43 12 bad chromium@466148 7251.67 +- 716.002 12 bad chromium@466163 6971.0 +- 1729.98 12 bad chromium@466192 7406.0 +- 178.65 12 bad chromium@466250 6963.83 +- 1816.95 12 bad To Run This Test .\src\out\Release_x64\angle_perftests.exe --test-launcher-print-test-stdio=always --test-launcher-jobs=1 Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8981424296955664064 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=4710656449708032 | 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 Speed>Bisection. Thank you!
,
Apr 25 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Jamie Madill Commit : 6de518589879b6b5802587bdca74bbb4f614a7f6 Date : Wed Apr 19 21:50:10 2017 Subject: Optimize angle::BitSetIterator. Bisect Details Configuration: winx64nvidia_perf_bisect Benchmark : angle_perftests Metric : Uniforms_gl_matrix_repeating/score Change : 33.99% | 11311.1666667 -> 7466.33333333 Revision Result N chromium@466133 11311.2 +- 1687.6 12 good chromium@466137 11022.0 +- 1898.08 12 good chromium@466138 11143.8 +- 1755.01 12 good chromium@466138,angle@a0e0aebbf2 10820.8 +- 2034.26 12 good chromium@466138,angle@6de5185898 7292.17 +- 1493.37 12 bad <-- chromium@466138,angle@8162926b2b 7596.5 +- 1289.5 12 bad chromium@466139 7418.0 +- 1022.64 12 bad chromium@466140 7430.5 +- 1142.45 12 bad chromium@466148 7026.67 +- 1741.31 12 bad chromium@466163 7178.0 +- 1554.5 12 bad chromium@466192 7311.17 +- 1488.05 12 bad chromium@466250 7466.33 +- 1453.19 12 bad To Run This Test .\src\out\Release_x64\angle_perftests.exe --test-launcher-print-test-stdio=always --test-launcher-jobs=1 Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8981424303130860912 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=6587192891146240 | 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 Speed>Bisection. Thank you!
,
Apr 25 2017
,
Apr 25 2017
,
Apr 25 2017
I can't repro this. It's kinda bad that such a large regression on the bots isn't detectable locally. Note: I am on Windows 10, with a different GPU, and different driver version. |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by jmad...@chromium.org
, Apr 24 2017