FFmpeg/libavutil/x86
Lynne 27cffd16aa
x86/tx_float: replace fft_sr_avx with fft_sr_fma3
When the SLOW_GATHER flag was added to the AVX2 version, this
made FMA3-features not enabled on Zen CPUs.
As FMA3 adds 6-7% across all platforms that support it, in
the interest of saving space, this commit removes the AVX
version and replaces it with an FMA3 version.
The only CPUs affected are Sandy Bridge and Bulldozer, which
have AVX support, but no FMA3 support.
In the future, if there's a demand for it, a version of the
function duplicated for AVX can be added.
2022-05-21 02:11:50 +02:00
..
asm.h asm: FF_-prefix internal macros used in inline assembly 2016-06-27 17:21:18 +02:00
bswap.h libavutil: x86: Include stdlib.h before using _byteswap_ulong 2020-01-23 18:30:26 +02:00
cpu.c avutil/cpu: add AVX512 Icelake flag 2022-03-10 16:45:48 -03:00
cpu.h avutil/cpu: add AVX512 Icelake flag 2022-03-10 16:45:48 -03:00
cpuid.asm libavutil: include assembly with full path from source root 2022-02-08 10:42:26 +01:00
emms.asm libavutil: include assembly with full path from source root 2022-02-08 10:42:26 +01:00
emms.h avutil/x86/emms: Don't unnecessarily include lavu/cpu.h 2022-02-21 12:37:51 +01:00
fixed_dsp_init.c x86/fixed_dsp: add ff_butterflies_fixed_sse2 2016-01-16 21:09:38 -03:00
fixed_dsp.asm libavutil: include assembly with full path from source root 2022-02-08 10:42:26 +01:00
float_dsp_init.c x86/float_dsp: add ff_vector_dmul_{sse2,avx} 2018-09-14 12:54:42 -03:00
float_dsp.asm libavutil: include assembly with full path from source root 2022-02-08 10:42:26 +01:00
imgutils_init.c Remove unnecessary libavutil/(avutil|common|internal).h inclusions 2022-02-24 12:56:49 +01:00
imgutils.asm Merge commit '6be7944ee2ec2f045e6eb9a93237e992c8b20ac4' 2017-03-23 18:05:27 -03:00
intmath.h x86/intmath: add VEX encoded versions of av_clipf() and av_clipd() 2021-11-19 11:21:03 -03:00
intreadwrite.h
lls_init.c Include attributes.h directly 2021-04-19 14:34:10 +02:00
lls.asm libavutil: include assembly with full path from source root 2022-02-08 10:42:26 +01:00
Makefile x86/tx_float: do not build tx_float_init.c if x86 assembly is disabled 2022-01-27 02:17:46 +01:00
pixelutils_init.c x86/pixelutils: don't use the AVX2 functions on CPUs known to be slow with them 2018-07-31 22:14:53 -03:00
pixelutils.asm libavutil: include assembly with full path from source root 2022-02-08 10:42:26 +01:00
pixelutils.h
timer.h
tx_float_init.c x86/tx_float: replace fft_sr_avx with fft_sr_fma3 2022-05-21 02:11:50 +02:00
tx_float.asm x86/tx_float: replace fft_sr_avx with fft_sr_fma3 2022-05-21 02:11:50 +02:00
w64xmmtest.h all: Add missing header guards 2016-01-28 19:49:48 -08:00
x86inc.asm avutil/cpu: add AVX512 Icelake flag 2022-03-10 16:45:48 -03:00
x86util.asm avutil/x86util : add macro for loading a 128 bits constants in an xmm or in each part of an ymm in order to simplify avx2 asm func 2017-12-02 18:25:15 +01:00