All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=751634

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=fb26e65ccb222bd11804fc6ab60b872e0f172b5fc44617c0b0a5499b6bb998c8


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

chromium-rel-win7-gpu-ati

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972368193255873792

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Hans Wennborg
  Commit : d2c91228a51bdf37ae3b2e501fb53c0528f1629c
  Date   : Fri Jul 28 20:11:05 2017
  Subject: win: Set is_clang=true by default

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : dromaeo.domcoreattr
  Metric       : dom/dom
  Change       : 6.89% | 907.624359206 -> 845.094015431

Revision             Result                  N
chromium@490485      907.624 +- 12.8487      6      good
chromium@490492      896.528 +- 20.9706      6      good
chromium@490493      897.373 +- 37.8693      6      good
chromium@490494      855.337 +- 13.3779      6      bad       <--
chromium@490495      844.632 +- 27.4524      6      bad
chromium@490498      856.403 +- 15.8076      6      bad
chromium@490510      846.415 +- 23.2784      6      bad
chromium@490535      851.423 +- 20.5755      6      bad
chromium@490585      845.094 +- 51.3412      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 dromaeo.domcoreattr

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972368193255873792


For feedback, file a bug with component Speed>Bisection

While they're both caused by the clang switch, the other bug is about media_perftests, and since it's pretty different I don't think we should dupe this against it.

Perf sheriff checking in: hans, any update?

We rolled back the Clang switch on Friday due to issues with debug info.

We might want to come back to this one when we switch it back on, but I'm not working on it at the moment, so let's wontfix for now.

We relanded the switch a while ago -- hans, should we reopen this, or no?

No. I don't remember any alerts about this from when we relanded, also the graph shows the benchmark doing great these days.