On Thu, Oct 06, 2011 at 01:38:32PM +0000, Ronald S. Bultje wrote:
> Hi,
> 
> 2011/10/3 Måns Rullgård <[email protected]>:
> > "Ronald S. Bultje" <[email protected]> writes:
> >> 2011/10/3 Måns Rullgård <[email protected]>:
> >>> This seem to speed up ~1.6x for each doubling of the cores.  That's
> >>> certainly better.  Good enough?  Decoding intra frames is in theory
> >>> infinitely parallelisable, so what's holding it back?
> >>
> >> It's slice threads, not frame threads. I.e. parts of the frame parsing
> >> aren't done in parallel, and all non-prores{dec,dsp}.c stuff is also
> >> not parallel.
> >
> > In that case it's fine.
> 
> Anyone else? I'd like this committed.

commit then
_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel

Reply via email to