[Webkit-unassigned] [Bug 77950] SSE optimization for vsvesq and vmaxmgv

[bugzilla-daemon at webkit.org]

https://bugs.webkit.org/show_bug.cgi?id=77950





--- Comment #14 from Raymond Toy <rtoy at chromium.org>  2012-02-27 09:21:17 PST ---
(In reply to comment #10)
> (From update of attachment 128369 [details])
> View in context: https://bugs.webkit.org/attachment.cgi?id=128369&action=review
> 
> >> Source/WebCore/platform/audio/VectorMath.cpp:500
> >> +            source = _mm_and_ps(source, mMask);
> > 
> > You mentioned that the performance with and_ps is less than the previous version with min_ps.  Is this because and_ps is slower or maybe because of some pipelining isues?  I'm just curious as to why this is slower.
> 
> It`s not slower with and_ps, my expression may not be clear so sorry for misleading you. I mean the performance between using and_ps and min_ps is not too much different, so I think the performance data is no needed to be updated.

Ok.  No need to change anything then.  I'm glad the performance didn't change.

-- 
Configure bugmail: https://bugs.webkit.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.