[Webkit-unassigned] [Bug 274043] REGRESSION (277125 at main): 10% performance regression in Web Assembly

[bugzilla-daemon at webkit.org]

https://bugs.webkit.org/show_bug.cgi?id=274043

--- Comment #6 from Marcus Plutowski <marcus_plutowski at apple.com> ---
I got a hold of an M1 MacBook and was able to reproduce a solid 8% performance drop across the listed commit, with about the same performance baseline as you described -- I'll start doing some differential testing to see where this could be coming from.

It is odd that I wasn't able to reproduce this on my M3. To make sure I'm doing this the exact same way you are: I know you were first looking at the Safari Technology Preview at first, but thereafter how exactly did you measure performance for a specific hash? Details on A) how you built, B) what you ran (MiniBrowser? something else?) would help a lot.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.webkit.org/pipermail/webkit-unassigned/attachments/20240522/63c9d849/attachment.htm>