[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 #8 from Gabor Loki <loki at webkit.org>  2011-02-22 08:42:56 PST ---
> May I suggest to add benchmarks (even if only Qt benchmarks) to see how does that fly?

Where to add benchmarks? If you send me some pointers I will happily measure the effect of this patch, but I have to mention that in general the benchmarks mainly give an overall insight about the performance. So, if you really would like to measure the effect of this kind of parallelization, you should create a basic svg with turbulence filter. For example: you can use the Source/WebCore/manual-tests/svg-filter-animation.svg as a simple benchmark after all non-related filters are removed from the SVG.


> I would really prefer something more like TBB, because you have a lot more control over the way things are parallelized.

Good idea, but I feel this could be another patch where we will introduce TBB for another threading model of the WebKit's threading interface.

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