On 01/05/16 03:26, Christophe Gisquet wrote:
> And last but not least, although you've optimized it, Golomb parsing
> actually shows the shortcomings of the new code. I have tried porting
> code making heavy use of it, and there's a major slowdown (15%) there.
I'm quite sure get_{ue,se}_golomb are faster with that set and all the
codecs in Libav are as fast or faster. Check Alexandra's tree, maybe she
ported it in a different way, all the Libav codebase is as fast or
faster after the change (I ran some perf stat myself).
lu
_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel
