Re: [libav-devel] [PATCH] lavr: replace the SSE version of ff_conv_fltp_to_flt_6ch() with SSE4 and AVX

2012-05-09 Thread Justin Ruggles
On 05/09/2012 01:14 PM, Vitor Sessak wrote: > On 05/09/2012 03:49 PM, Justin Ruggles wrote: >> The current SSE version is slower than the MMX version on Athlon64 and >> Sandy >> Bridge, but the SSE4 and AVX versions are faster on Sandy Bridge. >> --- >> libavresample/x86/audio_convert.asm|

Re: [libav-devel] [PATCH] lavr: replace the SSE version of ff_conv_fltp_to_flt_6ch() with SSE4 and AVX

2012-05-09 Thread Vitor Sessak
On 05/09/2012 03:49 PM, Justin Ruggles wrote: The current SSE version is slower than the MMX version on Athlon64 and Sandy Bridge, but the SSE4 and AVX versions are faster on Sandy Bridge. --- libavresample/x86/audio_convert.asm| 30 -- libavresample/x86/audio

[libav-devel] [PATCH] lavr: replace the SSE version of ff_conv_fltp_to_flt_6ch() with SSE4 and AVX

2012-05-09 Thread Justin Ruggles
The current SSE version is slower than the MMX version on Athlon64 and Sandy Bridge, but the SSE4 and AVX versions are faster on Sandy Bridge. --- libavresample/x86/audio_convert.asm| 30 -- libavresample/x86/audio_convert_init.c | 13 + libavutil/x8