Hi,
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. I can do frame threads also but it would have a latency.
It will probably scale somewhat better.
Ronald
_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel
