All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=795003

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=edbbaaa6e067e9139eea28b1f2e7fad973ab0e56dd33513eca13ad371a377fc1


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

android-webview-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8960213306656369680

=== Auto-CCing suspected CL author noel@chromium.org ===

Hi noel@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 : Noel Gordon
  Commit : 53edf03e13a1569f146f136c9e43bc6e476bf33e
  Date   : Wed Dec 13 03:51:05 2017
  Subject: Use default optimization on Android for zlib inflate chunk copy

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : blink_perf.image_decoder
  Metric       : decode-png/decode-png
  Change       : 8.00% | 160.40375 -> 173.234333333

Revision             Result                   N
chromium@523652      160.404 +- 2.24304       6      good
chromium@523666      160.703 +- 2.33103       6      good
chromium@523673      160.219 +- 1.94998       6      good
chromium@523677      160.212 +- 0.994386      6      good
chromium@523678      160.886 +- 2.51182       6      good
chromium@523679      172.493 +- 2.14993       6      bad       <--
chromium@523680      172.458 +- 1.75608       6      bad
chromium@523708      173.234 +- 2.16112       6      bad

Please refer to the following doc on diagnosing blink_perf regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/speed/benchmark_harnesses/blink_perf.md

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.image_decoder

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8960213306656369680


For feedback, file a bug with component Speed>Bisection

Subject: Use default optimization on Android for zlib inflate chunk copy

per https://bugs.chromium.org/p/chromium/issues/detail?id=772870#c17 the change removed -O3 optimization on Android for the zlib inflate chunk copy code to undo a perf regression on Android One bot [1].

[1] https://chromeperf.appspot.com/report?sid=c4dfef665436649947559a795146cef680e6a2ac1f0d5e531d36338ae0afbe79&start_rev=514313&end_rev=524033

The Android One bot recovered after this change, as you can see from the graphs, good.  But yes, the perf improv -O3 gave us on all our other Android bots, particularly the N5/5x bots, is lost.  /me sadface

Anyho, this regression is expected/intentional, WONTFIX, duping to  issue 772870 .