FFmpeg/libavcodec/x86
James Almer aa1f38015c x86/synth_filter: improve FMA version
Replace mulps+subps with fnmaddps, resulting in two less instructions inside the
inner loops.
About 1% faster FMA3 performance.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-03-17 21:04:15 +01:00
..
ac3dsp_init.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
ac3dsp.asm Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
cabac.h Merge commit '3741aa37c2a0d0717faff74a5c4cc357d16f6d1d' 2014-03-05 21:33:44 +01:00
cavsdsp.c Merge remote-tracking branch 'qatar/master' 2013-12-05 11:55:41 +01:00
constants.c
constants.h Add missing external declarations. 2014-03-17 00:48:09 +01:00
dca.h Merge commit 'b23bc95920e2f10b9621857e829c45b064f356c0' 2014-02-19 15:44:48 +01:00
dcadsp_init.c Merge commit '3bfdee00cd92ff07c364d4901c4aefda32780756' 2014-03-06 14:10:27 +01:00
dcadsp.asm x86/synth_filter: improve FMA version 2014-03-17 21:04:15 +01:00
dct32.asm
dct_init.c
deinterlace.asm Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
dirac_dwt.c
dirac_dwt.h
diracdsp_mmx.c
diracdsp_mmx.h
diracdsp_yasm.asm
dnxhdenc.c
dsputil_init.c Merge commit 'db3f61a04f1f66746660f921bb2780ddf1141f3b' 2014-03-14 01:25:57 +01:00
dsputil_mmx.c Merge commit '38675229a879aa5258a8c71891fc8cbf74cf139f' 2014-03-14 01:01:37 +01:00
dsputil_qns_template.c
dsputil_x86.c
dsputil_x86.h Merge commit '4cb4680c1087a2cd13d4b0c9167a2eb3147f99d8' 2014-03-14 01:25:19 +01:00
dsputil.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
dsputilenc_mmx.c Merge commit 'a36947c167d7278b891453083b57dc56b7a7f5c5' 2014-03-14 01:09:57 +01:00
dsputilenc.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
dwt_yasm.asm
fdct.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
fft_init.c
fft.asm
fft.h
flacdsp_init.c x86/fladsp: add missing check to ff_flacdsp_init_x86() 2014-02-16 12:06:04 +01:00
flacdsp.asm x86: Move XOP emulation to x86util 2014-02-24 08:30:19 +01:00
fmtconvert_init.c
fmtconvert.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
fpel_mmx.c
fpel.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h263_loopfilter.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h263dsp_init.c Merge commit '0338c396987c82b41d322630ea9712fe5f9561d6' 2013-11-08 17:42:56 +01:00
h264_chromamc_10bit.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_chromamc.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_deblock_10bit.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_deblock.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_i386.h
h264_idct_10bit.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_idct.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_intrapred_10bit.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_intrapred_init.c Merge commit 'a03a642d5ceb5f2f7c6ebbf56ff365dfbcdb65eb' 2014-01-06 16:51:23 +01:00
h264_intrapred.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_qpel_8bit.asm
h264_qpel_10bit.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_qpel.c
h264_weight_10bit.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264_weight.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
h264chroma_init.c
h264dsp_init.c Merge commit 'a03a642d5ceb5f2f7c6ebbf56ff365dfbcdb65eb' 2014-01-06 16:51:23 +01:00
hpeldsp_init.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
hpeldsp_mmx.c
hpeldsp_rnd_template.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
hpeldsp.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
idct_mmx_xvid.c
idct_sse2_xvid.c avcodec/x86/idct_sse2_xvid: move offsets out of MANGLE() 2014-03-17 04:19:59 +01:00
idct_xvid.h
imdct36.asm x86/imdct36: use sse3 instructions in the last BUTTERF step when possible 2014-02-27 23:28:15 +01:00
lossless_videodsp_init.c avcodec/x86/lossless_videodsp: disable median optimizations for 16bps 2014-01-23 01:51:24 +01:00
lossless_videodsp.asm avcodec/x86/lossless_videodsp: fix w type 2014-02-15 06:41:38 +01:00
lpc.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
Makefile tta/x86: add ff_ttafilter_process_dec_{ssse3, sse4} 2014-02-17 13:51:19 +01:00
mathops.h
mlpdsp.c
motion_est.c Merge commit 'f8bbebecfd7ea3dceb7c96f931beca33f80a3490' 2014-03-14 01:20:43 +01:00
mpeg4qpel.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
mpegaudiodsp.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
mpegvideo.c Merge commit 'dfc50ac85e9d68a771b556297b7c411650206f3b' 2013-12-20 23:44:31 +01:00
mpegvideoenc_template.c Fixed 64bit conformance with mvzbl. 2014-03-17 00:13:50 +01:00
mpegvideoenc.c Merge commit 'dfc50ac85e9d68a771b556297b7c411650206f3b' 2013-12-20 23:44:31 +01:00
pngdsp_init.c
pngdsp.asm
proresdsp_init.c Merge commit 'b23650491fbd579a4365f42bd42575afb7b53f7e' 2014-02-28 17:13:00 +01:00
proresdsp.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
qpel.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
rnd_mmx.c
rnd_template.c Merge commit '831a1180785a786272cdcefb71566a770bfb879e' 2014-03-13 23:59:56 +01:00
rv34dsp_init.c Merge commit 'b0be1ae792ac8bbfb0fc7b9b9cb39eaf0feb489b' 2014-01-09 20:24:15 +01:00
rv34dsp.asm
rv40dsp_init.c
rv40dsp.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
sbrdsp_init.c
sbrdsp.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
simple_idct.c Merge commit '17608f6ee3d2088cdb8d1e704276d8b34f01160d' 2014-03-13 23:41:17 +01:00
snowdsp.c
ttadsp_init.c tta/x86: add ff_ttafilter_process_dec_{ssse3, sse4} 2014-02-17 13:51:19 +01:00
ttadsp.asm tta/x86: add ff_ttafilter_process_dec_{ssse3, sse4} 2014-02-17 13:51:19 +01:00
v210-init.c
v210.asm
vc1dsp_init.c x86: avcodec: Add a bunch of missing #includes for av_cold 2014-01-09 15:09:07 +01:00
vc1dsp_mmx.c
vc1dsp.asm
vc1dsp.h
videodsp_init.c Merge commit '51daafb02eaf96e0743a37ce95a7f5d02c1fa3c2' 2014-01-31 14:30:30 +01:00
videodsp.asm x86: videodsp: Fix a bug in a %if statement where we used '%%' instead of '&&'. 2014-01-30 15:33:23 +01:00
vorbisdsp_init.c
vorbisdsp.asm
vp3dsp_init.c
vp3dsp.asm
vp6dsp_init.c Merge commit 'b0be1ae792ac8bbfb0fc7b9b9cb39eaf0feb489b' 2014-01-09 20:24:15 +01:00
vp6dsp.asm
vp8dsp_init.c avcodec/vp8dsp: add VP7 idct and loop filter 2014-02-15 02:15:35 +01:00
vp8dsp_loopfilter.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
vp8dsp.asm Merge commit '55519926ef855c671d084ccc151056de9e3d3a77' 2014-03-14 00:01:30 +01:00
vp9dsp_init.c vp9/x86: intra prediction SIMD. 2014-02-17 13:39:00 +01:00
vp9intrapred.asm vp9/x86: set correct number of registers used in intra pred asm 2014-02-18 17:20:14 +01:00
vp9itxfm.asm vp9/x86: use explicit register for relative stack references. 2014-01-24 19:25:25 -05:00
vp9lpf.asm x86/vp9lpf: simplify 2nd transpose in 44/48/88/84. 2014-02-08 11:10:23 +01:00
vp9mc.asm vp9/x86: rename ff_avg[48]_sse to ff_avg[48]_mmxext 2014-01-18 17:08:25 +01:00
vp56_arith.h
w64xmmtest.c