All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=814054

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=60e4de492626a4d8ab7a5d4ce8a4dd5622be3317bddad4fdf4a7093aaf008bc4


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

chromium-rel-mac11-air
chromium-rel-mac11-pro
chromium-rel-win7-gpu-ati
chromium-rel-win7-gpu-intel
chromium-rel-win7-x64-dual

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/12e2a9b7840000

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/12e2a9b7840000

[turbofan] Masking/poisoning in codegen (optimized code, x64) by mvstanton@chromium.org
https://chromium.googlesource.com/v8/v8/+/8f489e73b23f764801a35abaaf10772406fd4209

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

Mike, was this regression expected?

Not expected. My CL added infrastructure for branch poisoning, but it had an issue that even when the flag for it was off, we'd do some of that work. I've duped it to 814053, and closed that bug as fixed, since Jarin@ made a repair CL that turns off the infrastructure when --branch-load-poisoning isn't specified.