All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=798292

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=af0cd1c9f33dbe7b35641c09ba4b26d2cd076695855e9ca6dbff18e62908eb43


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

android-nexus5X
android-one
chromium-rel-mac11
chromium-rel-mac12-mini-8gb

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/14c83b1d040000

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/14c83b1d040000

<b>[PE] Invalidate <use> instances even when mutating from the parser</b>
By fs@opera.com · Mon Dec 18 16:48:54 2017
chromium @ a8014bf1bc9b0c1c4b709702f404a84c5cc948cd

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

The 'weather' cases are the same as  issue 797067  (this content is affected by the bug fixed by the above commit, so can rightfully require more time.)

The 'googleimagesearch' / android-one case has a disjoint regression range so probably requires a new bisect.

s/has a disjoint regression range/regression range does not contain the above commit/

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8958428601598859920

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

Suspected Commit
  Author : Mike Klein
  Commit : 37155d476cd727329d985b75ecedbefe380a0f23
  Date   : Mon Dec 18 18:48:42 2017
  Subject: Rework out-of-gamut handling in SkRasterPipeline

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : rasterize_and_record_micro.top_25
  Metric       : rasterize_time/file___static_top_25_googleimagesearch.html
  Change       : 1.86% | 221.395166667 -> 225.524

Revision                             Result                   N
chromium@524741                      221.395 +- 0.763727      6      good
chromium@524771                      221.699 +- 1.51493       6      good
chromium@524786                      221.092 +- 0.516486      6      good
chromium@524788                      221.076 +- 0.657622      6      good
chromium@524788,skia@5b92ce1b24      221.198 +- 0.703855      6      good
chromium@524788,skia@37155d476c      225.697 +- 0.616859      6      bad       <--
chromium@524788,skia@28f89389f0      225.875 +- 0.450522      6      bad
chromium@524789                      225.893 +- 0.744444      6      bad
chromium@524790                      225.841 +- 0.70725       6      bad
chromium@524793                      225.831 +- 0.670784      6      bad
chromium@524800                      225.891 +- 0.830943      6      bad
chromium@524859                      225.524 +- 1.00268       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=file...static.top.25.googleimagesearch.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/8958428601598859920


For feedback, file a bug with component Speed>Bisection