All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=677449

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg7__F8AsM


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

chromium-rel-win7-gpu-nvidia

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8991947792349887664

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


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N    Good?
chromium@440450  8.94336  23.9999  14   good
chromium@440503  8.32743  17.4729  14   good
chromium@440529  8.33611  14.5514  9    good
chromium@440542  7.25593  17.5193  14   good
chromium@440543  ---      ---      ---  build failure
---              ---      ---      ---  too many build failures to list
chromium@440554  ---      ---      ---  build failure
chromium@440555  14.4386  29.6513  14   bad

Bisect job ran on: winx64nvidia_perf_bisect
Bug ID: 677449

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Wordpress smoothness.top_25_smooth
Test Metric: first_gesture_scroll_update_latency/Wordpress
Relative Change: 97.55%

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64nvidia_perf_bisect/builds/1986
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8991947792349887664


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5832496262938624

| 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!

+vmiura: Bisect reproduces, but can't narrow the revision range because Chrome doesn't build. We only saw this regression on one bot, and it recovered. Anything more we should do here?

This seems to have fully recovered.  I don't think it's worth doing more investigation.