All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=883780

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=d5ccb30c5a38ac6b617601ff57d689da77fec146c31f878168bd00aa2b37f65b


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

mac-10_12_laptop_low_end-perf

rasterize_and_record_micro.top_25 - Benchmark documentation link:
  None

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/1239ebb5640000

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/1239ebb5640000

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/15cff379640000

Trying bisect slightly after

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/15cff379640000

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/1714408d640000

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/1714408d640000

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/1442b7a5640000

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/1442b7a5640000

clamp after color pipeline when dst is normalized by mtklein@google.com
https://skia.googlesource.com/skia/+/fc9624cb840ca089620a2f9e519bcc1260468712
4.659 → 4.718 (+0.0597)

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

Benchmark documentation link:
  None

This ought to have been fixed by https://chromium-review.googlesource.com/c/chromium/src/+/1213446 rolling "add clamp_gamut".

I think I see that on the perf chart as https://chromeperf.appspot.com/group_report?rev=589795.  Not really sure how to link to that point on the chart.