[Webkit-unassigned] [Bug 43903] Speeding up SVG filters with multicore (SMP) support

[bugzilla-daemon at webkit.org]

https://bugs.webkit.org/show_bug.cgi?id=43903





--- Comment #25 from Balazs Kelemen <kbalazs at webkit.org>  2011-03-02 04:40:51 PST ---
(In reply to comment #21)
> > Benjamin, do you have any idea what is happening here? Why did the environment produce this strange numbers?
> 
> Nope, I have no idea what is going on here. The deviation is just insane, it is usually around 1%.
> 

Not belongs strictly to this bug (should we create another?) but
I have also tried those tests (the gitorious version) and the deviation
was not acceptable. I guess the trunk version also suffering from this
in wall-time mode. I do not think this is only a problem with SVG related
pages but it is caused by the event based approach of our benchmark framework.
The really good thing in this framework is that one can measure
the performance of specific subsystems like layouting or painting
but we cannot use it to validate optimizations as long as we cannot make it
producing stable results.

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