[Ffmpeg-devel] MMX/MMX2 and SSE optimizations for H.264 decoding

[Romain Dolbeau]

Loren Merritt wrote:

> we have:
> put_h264_qpel_16_mc*_altivec
> put_h264_chroma_mc8_altivec
> 
> we do not have equivalents of:
> put_h264_qpel_8_mc*_mmx2
> put_h264_qpel_4_mc*_mmx2
> h264_*_loop_filter_*_mmx2
> ff_h264_idct_add_mmx2

The additional question is, are we going to be bitten by
Amdahl's Law ? i.e. are these important enought during
the decoding process to justify optimizing them ?

-- 
Romain Dolbeau
<romain at dolbeau.org>