Issue metadata
Sign in to add a comment
|
10.4% regression in thread_times.tough_scrolling_cases at 487045:487119 |
||||||||||||||||||||
Issue descriptionprevious a few results look exceptionally good, and within the range, results get back to the original level. but just in case.
,
Jul 19 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8973652118373700352
,
Jul 19 2017
=== Auto-CCing suspected CL author brucedawson@chromium.org === Hi brucedawson@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 : Bruce Dawson Commit : 8e6e8c57c1c30caf7e2756e95d5a59e90336b0bd Date : Mon Jul 17 16:39:20 2017 Subject: Revert "Test changing default Windows compiler to VS2017" Bisect Details Configuration: winx64intel_perf_bisect Benchmark : thread_times.tough_scrolling_cases Metric : thread_raster_cpu_time_per_frame/thread_raster_cpu_time_per_frame Change : 9.72% | 1.61741225972 -> 1.77455002786 Revision Result N chromium@487044 1.61741 +- 0.0229877 6 good chromium@487082 1.66309 +- 0.0136591 6 good chromium@487101 1.65282 +- 0.0174096 6 good chromium@487110 1.64763 +- 0.022662 6 good chromium@487111 1.78511 +- 0.0271584 6 bad <-- chromium@487112 1.78103 +- 0.0191965 6 bad chromium@487113 1.81637 +- 0.0249658 6 bad chromium@487115 1.81029 +- 0.014033 6 bad chromium@487119 1.77455 +- 0.0184288 6 bad To Run This Test src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests thread_times.tough_scrolling_cases More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8973652118373700352 For feedback, file a bug with component Speed>Bisection
,
Jul 19 2017
This bug means that VC++ 2017 gave a nice speed improvement on this benchmark which went away after the VC++ 2017 test was reverted. Therefore this isn't really a regression, it just means that we got a brief sample of a nice improvement. Closing as Wont Fix. |
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Jul 19 2017