On 9/2/2018 5:30 AM, Carl Eugen Hoyos wrote: > > >> Am 02.09.2018 um 01:18 schrieb James Almer <[email protected]>: >> >> Signed-off-by: James Almer <[email protected]> >> --- >> Unbenched, but if x86_32 is slow with it, then chances are so are arm >> and similar 32bit architectures. > > Please do not commit without benchmarks, I found no other architecture where > the new reader is slower.
I can't bench on anything but x86, which is why i sent this patch to get other people's opinions. You tried other 32 bit architectures like arm7 or PPC? fast_64 is a configure time constant used in a lot of speed critical modules to choose between using 32bit or 64bit ops, so seeing how this new bitstream reader uses a 64bit cache I'd expect it to be slower in such targets as well. _______________________________________________ ffmpeg-devel mailing list [email protected] http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
