Vitor Sessak <[email protected]> writes: > On 04/01/2011 09:20 PM, Luca Barbato wrote: >> On 04/01/2011 07:12 PM, Vitor Sessak wrote: >>> Hi, >>> >>> The following patches add an AVX (an intel x86 extension) FFT >>> implementation. Since I do not have a Sandybridge myself, I have no idea >>> of its performance. Benchmarks (for ex., using fft-test -s) are thus >>> very welcome. Also welcome are suggestions for optimizing it further, in >>> particular the 8 point FFT (in the T8_AVX macro), which is not much >>> faster than the SSE version. >> >>> --- >>> libavcodec/x86/fft.c | 9 +- >>> libavcodec/x86/fft.h | 1 + >>> libavcodec/x86/fft_mmx.asm | 320 >>> ++++++++++++++++++++++++++++++++++++++++++-- >>> libavcodec/x86/fft_sse.c | 12 ++ >>> libavcodec/x86/x86inc.asm | 17 +++ >>> libavutil/mem.c | 16 +-- >> >> Might be nicer have an fft_avx.asm file, beside that I don't have an avx >> system. > > It uses several macros from fft_mmx.asm...
Those could be moved to a shared file. -- Måns Rullgård [email protected] _______________________________________________ libav-devel mailing list [email protected] https://lists.libav.org/mailman/listinfo/libav-devel
