On Tue, 24 Oct 2017 at 00:56 Carl Eugen Hoyos <ceffm...@gmail.com> wrote:
> 2017-10-24 1:43 GMT+02:00 Niki Bowe <nbowe-at-google....@ffmpeg.org>: > > On Thu, Oct 19, 2017 at 3:39 PM, Carl Eugen Hoyos <ceffm...@gmail.com> > > wrote: > > >> Does the patch have a measurable speed impact? > >> > > Is there a standard set of benchmarks I can run? > > > > For typical videos the speed impact is small, due to NALU fitting in > cache, > > but for videos with many large NALUs there can be some slowdown. > > (5% overall slowdown would make every patch unacceptable > but I doubt this is the case.) > > Use the TIMER makros from libavutil/timer.h, put them around all > calls to ff_h2645_extract_rbsp(). > Related to https://trac.ffmpeg.org/ticket/6789, we see huge memory allocations in this code so if this patch fixes, it should be committed irrespective of any speed loss. Kieran _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
