All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=708545

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgvNyMpwoM


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

android-webview-nexus6

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8983144997956258320

=== Auto-CCing suspected CL author ivica.bogosavljevic@imgtec.com ===

Hi ivica.bogosavljevic@imgtec.com, 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 : ivica.bogosavljevic
  Commit : 74b8ef6cea108d55d479afe16ffa2b0e7bf90074
  Date   : Tue Apr 04 09:18:56 2017
  Subject: MIPS: Fix `[builtins] Reland of Port TypedArrayInitialize to CodeStubAssembler.`

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:v8:effective_size_avg/load_games/load_games_lazors
  Change       : 0.99% | 2285224.0 -> 2307924.0

Revision                           Result                  N
chromium@461684                    2285224 +- 0.0          6      good
chromium@461691                    2285224 +- 0.0          6      good
chromium@461695                    2285224 +- 0.0          6      good
chromium@461695,v8@68c14892cb      2285224 +- 0.0          6      good
chromium@461695,v8@45e3c56d40      2285224 +- 0.0          6      good
chromium@461695,v8@74b8ef6cea      2305151 +- 15190.2      6      bad       <--
chromium@461695,v8@ce06d1f232      2307957 +- 182.574      6      bad
chromium@461696                    2307924 +- 0.0          6      bad
chromium@461697                    2307924 +- 0.0          6      bad
chromium@461698                    2307924 +- 0.0          6      bad
chromium@461712                    2307924 +- 0.0          6      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.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 --story-filter=load.games.lazors system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8983144997956258320

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5685244914565120


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

What steps should I take from hereon: the patch was needed in order to fix a crash. I could add some special conditions in order to lower the impact of it, but I cannot disable it completely.

That's pretty much it - revisit the CL to see if the memory increase was expected and if there is anything that can be done to minimize the jump, then close it after you have it mitigated as much as makes sense.

 Issue 709056  has been merged into this issue.

The following revision refers to this bug:
  https://chromium.googlesource.com/v8/v8.git/+/d9691952c1825ca9c8f73db5f63f842da9226cd8

commit d9691952c1825ca9c8f73db5f63f842da9226cd8
Author: ivica.bogosavljevic <ivica.bogosavljevic@imgtec.com>
Date: Sat Apr 08 22:15:38 2017

[builtins] Speed up TypedArrayInitialize in CodeStubAssembler

On those architectures that do support unaligned memory access
there is no need to emit heap alignment code in TypedArrayInitialize.

BUG= chromium:708545 

Review-Url: https://codereview.chromium.org/2802003003
Cr-Commit-Position: refs/heads/master@{#44501}

[modify] https://crrev.com/d9691952c1825ca9c8f73db5f63f842da9226cd8/src/builtins/builtins-typedarray-gen.cc
[modify] https://crrev.com/d9691952c1825ca9c8f73db5f63f842da9226cd8/src/compiler/code-assembler.cc
[modify] https://crrev.com/d9691952c1825ca9c8f73db5f63f842da9226cd8/src/compiler/code-assembler.h

So I uploaded the patch that disables the fix where it is not needed. Can I now close this issue?