Ronald S. Bultje <rsbultje <at> gmail.com> writes: > What kind of speedup are you seeing
His patch provides a 10% - 30% speedup for most libswscale input functions, but not for rgb24->yuv with gcc 5. > and how did you measure that, He measured it with some performance tool and with -benchmark and with START/STOP_TIMER(). > and why doesn't START/STOP_TIMER show these speedups? It does show the same results as the performance tool afaict. Carl Eugen _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
