[Webkit-unassigned] [Bug 155551] Pathological performance on first execution of a function called with mismatched argument count

[bugzilla-daemon at webkit.org]

https://bugs.webkit.org/show_bug.cgi?id=155551

--- Comment #9 from Oliver Hunt <oliver at apple.com> ---
Actually, i managing to trigger a bunch of performance cliffs. if we change f(j) to f(j,k) performance falls off a cliff:
function f(j) { for (var i = 0 ; i < 50000000; i++) j = (j ?  j * i : 1) ^ (i & j); }; var start = new Date; f(1); var end = new Date; print("1st: " + (end - start) + "ms");var start = new Date; f(1); var end = new Date; print("2nd: " + (end - start) + "ms")

1st: 375ms

vs.

function f(j,k) { for (var i = 0 ; i < 50000000; i++) j = (j ?  j * i : 1) ^ (i & j); }; var start = new Date; f(1); var end = new Date; print("1st: " + (end - start) + "ms"); 
1st: 1885ms


There is clearly some kind of perf cliff going on. At least for the first call specifically, and varying arty mismatches in general.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.webkit.org/pipermail/webkit-unassigned/attachments/20160316/90414bba/attachment-0001.html>