[Ffmpeg-devel] [PATCH] Snow mmx+sse2 asm optimizations

Luca Barbato lu_zero
Mon Mar 13 14:45:55 CET 2006

Michael Niedermayer wrote:
> hmm, maybe not, but if so thats a bug and should be fixed (= stride should
> be a multiple of 16)
> [...]

on the same tune, pred_block results are completely unaligned, there is
any possibility to align block * * ? that would boost
inner_add_yblock_$simd speed.



Luca Barbato

Gentoo/linux Gentoo/PPC

More information about the ffmpeg-devel mailing list