All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=787812

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=8642ebc9ba2be82b4512411484a0e2b2805ad55297f53ae4283e9b3840a7643d


Bot(s) for this bug's original alert(s):

chromium-rel-win7-gpu-intel

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8962218861246589616

=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : rasterize_and_record_micro.top_25
  Metric       : record_time/file___static_top_25_youtube.html
  Change       : 1.15% | 0.131 -> 0.1325

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/a06cdd8debb95c60fb9dc5cd531b9be7d8d215b1..c7f24fba3104b579b1fadde313ece93f6dc334b9


Revision             Result                     N
chromium@516239      0.131 +- 0.00959166        14       good
chromium@516251      0.13081 +- 0.00807701      21       good
chromium@516258      0.130429 +- 0.0036645      14       good
chromium@516264      0.1305 +- 0.00273861       14       good
chromium@516265      ---                        ---      build failure
chromium@516266      0.132571 +- 0.0103648      14       bad
chromium@516293      0.1325 +- 0.00644205       14       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 --story-filter=file...static.top.25.youtube.html rasterize_and_record_micro.top_25

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8962218861246589616


For feedback, file a bug with component Speed>Bisection

Hi Sylvain,
I think this regression might be caused by this CL:
https://chromium.googlesource.com/chromium/src/+/f5d2d957af78d8f9cc025e7301d12409d2f48cad
There are only two in the range and the other one only re-enables some tests. Does that seem possible to you?

Given that the regression is on desktop and my CL only affect mobile version of Chrome (iOS specifically), there is 0% chance that my CL is causing the regression.

Ignore: ref moved.