All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=648902

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICguf3bpgoM


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

chromium-rel-win7-gpu-ati

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9000920989755016320

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@418871  319.079  10.4331  18  good
chromium@418934  320.763  9.10368  18  bad

Bisect job ran on: winx64ati_perf_bisect
Bug ID: 648902

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: putImageData/putImageData
Relative Change: 6.48%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1568
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9000920989755016320


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6664456984068096

| 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 Tests>AutoBisect.  Thank you!

kicked another bisect with a wider range

https://chromeperf.appspot.com/buildbucket_job_status/9000474346997120192

CC: perfbot sheriff since bisect wasn't reported at all.

Copy and paste results manually from https://chromeperf.appspot.com/group_report?bug_id=648902
	
2016-09-21 11:27:54 
===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@418871  319.079  10.4331  18  good
chromium@418934  320.763  9.10368  18  bad

Bisect job ran on: winx64ati_perf_bisect
Bug ID: 648902

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: putImageData/putImageData
Relative Change: 6.48%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1568
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9000920989755016320


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6664456984068096

| 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 Tests>AutoBisect.  Thank you!

Oops, the result of #6 wasn't for the second bisect of #5.
But, according to the link of #5,

Status of the bisect job 9000474346997120192: COMPLETED, SUCCESS

  Master: master.tryserver.chromium.perf
  Builder: winx64ati_perf_bisect
  Test: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
  Metric: putImageData/putImageData
  Good revision: 418798
  Bad revision: 419073
  Job created on (UTC): Mon Sep 26 07:43:22 2016
  Job completed on(UTC): Mon Sep 26 09:49:15 2016
  Buildbot link: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1571

And builtbot result says "The metric values for the initial \"good\" and \"bad\" revisions do not represent a clear regression."

https://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1571/steps/Post%20bisect%20results/logs/stdio

The "Post bisect results" step for the buildbot was green, but wasn't reported actually.

sullivan@, may I assign you to this?

Ive filed https://github.com/catapult-project/catapult/issues/2870 about the bisect update issue.

Perf sheriff ping

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8998329423724513088

Trying another bisect job to check whether https://github.com/catapult-project/catapult/issues/2870 is a consistent problem or a transient problem.

Meanwhile, this looks it's it's probably not a real regression:
 - one bot
 - no ref build
 - graph is noisy
 - bisect didn't reproduce

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@418871  325.302  10.2803  18  good
chromium@418934  328.191  8.52536  18  bad

Bisect job ran on: winx64ati_perf_bisect
Bug ID: 648902

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.canvas
Test Metric: putImageData/putImageData
Relative Change: 1.53%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64ati_perf_bisect/builds/1621
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8998329423724513088


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5797281956102144

| 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 Tests>AutoBisect.  Thank you!

I think we can close this, the graph recovered afterwards and it's so noisy we'd never bisect it.