[MPlayer-dev-eng] [PATCH]: af_resample SIMD optimization(MMX/SSE2/3DNOW!/SSE/SSE3)

[Zhou Zongyi]

I tested them on Athlon XP. SSE3 seems a bit faster than SSE. Perhaps lddqu is faster than movups?

> Hi,
> 
> 2009/3/12 Zhou Zongyi <zhouzongyi at pset.suntec.net>:
>> Hi all,
>>
>> This patch implements SIMD optimized FIR filter in resample.
>>
>> Since SSE3 is used, you should apply SSE3 detection patch before applying this one:
>>
>> http://lists.mplayerhq.hu/pipermail/mplayer-dev-eng/2009-January/059824.html
> 
> Have u ever benchmarked the performance of SSE against SSE3? Most of
> the time haddps is too slow to use.
> 
> -- 
> Zuxy
> Beauty is truth,
> While truth is beauty.
> PGP KeyID: E8555ED6