xenia-project/FFmpeg
1
0
Fork 0
mirror of https://github.com/xenia-project/FFmpeg.git synced 2024-11-29 06:20:29 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
5a97469a4f
FFmpeg/libavcodec/x86
History
Christophe Gisquet 5a97469a4f x86: sbrdsp: Implement SSE2 qmf_deint_bfly 
Sandybridge: 47 cycles

Having a loop counter is a 7 cycle gain.
Unrolling is another 7 cycle gain.
Working in reverse scan is another 6 cycles.

Signed-off-by: Diego Biurrun <diego@biurrun.de>
2013-05-03 18:23:14 +02:00
..
ac3dsp_init.c x86: ac3dsp: Remove 3dnow version of ff_ac3_extract_exponents 2013-04-26 21:06:52 +02:00
ac3dsp.asm x86: ac3dsp: Remove 3dnow version of ff_ac3_extract_exponents 2013-04-26 21:06:52 +02:00
cabac.h
cavsdsp.c x86: dsputil: Move cavs and vc1-specific functions where they belong 2013-05-02 11:45:37 +02:00
constants.c dsputil: Make dsputil selectable 2013-04-10 11:04:05 +03:00
dct32.asm build: Drop AVX assembly ifdefs 2012-11-11 20:43:28 +01:00
deinterlace.asm x86: yasm: Use complete source path for macro helper %includes 2012-10-31 00:37:42 +01:00
dnxhdenc.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
dsputil_mmx.c x86: dsputil: Move cavs and vc1-specific functions where they belong 2013-05-02 11:45:37 +02:00
dsputil_mmx.h x86: dsputil: Move cavs and vc1-specific functions where they belong 2013-05-02 11:45:37 +02:00
dsputil_qns_template.c
dsputil.asm x86: qpel: Move fullpel and l2 functions to a separate file 2013-04-08 12:38:33 +03:00
dsputilenc_mmx.c x86: Move some conditional code around to avoid unused variable warnings 2013-04-22 17:50:02 +02:00
dsputilenc.asm Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
fdct.c dsputil: Move fdct function declarations to dct.h 2013-02-09 00:08:28 +01:00
fft_init.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
fft.asm build: Drop AVX assembly ifdefs 2012-11-11 20:43:28 +01:00
fft.h
fmtconvert_init.c Move misplaced file author information where it belongs 2013-04-11 02:42:11 +02:00
fmtconvert.asm x86: SPLATD: port to cpuflags 2012-11-18 18:34:05 +01:00
fpel_mmx.c x86: dsputil: Move avg_pixels16_mmx() out of rnd_template.c 2013-05-02 11:45:37 +02:00
fpel.asm x86: hpeldsp: Move half-pel assembly from dsputil to hpeldsp 2013-04-19 23:18:53 +03:00
h263_loopfilter.asm x86: dsputil: Fix h263 loop filter link error in some configurations 2013-02-18 17:09:00 +01:00
h264_chromamc_10bit.asm x86: mmx2 ---> mmxext in asm constructs 2012-11-14 00:58:51 +01:00
h264_chromamc.asm dsputil: Make dsputil selectable 2013-04-10 11:04:05 +03:00
h264_deblock_10bit.asm x86: mmx2 ---> mmxext in asm constructs 2012-11-14 00:58:51 +01:00
h264_deblock.asm dsputil: Make dsputil selectable 2013-04-10 11:04:05 +03:00
h264_i386.h
h264_idct_10bit.asm h264: Integrate clear_blocks calls with IDCT 2013-04-10 11:03:06 +03:00
h264_idct.asm h264: Integrate clear_blocks calls with IDCT 2013-04-10 11:03:06 +03:00
h264_intrapred_10bit.asm x86: mmx2 ---> mmxext in asm constructs 2012-11-14 00:58:51 +01:00
h264_intrapred_init.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
h264_intrapred.asm x86: h264_intrapred: Fix C function names in comments 2012-11-18 18:34:05 +01:00
h264_qpel_8bit.asm Revert "Move H264/QPEL specific asm from dsputil.asm to h264_qpel_*.asm." 2013-02-28 21:50:02 +01:00
h264_qpel_10bit.asm x86: h264_qpel_10bit: drop unused parameter from MC10/MC20/MC30 macros 2012-11-10 14:49:09 +01:00
h264_qpel.c x86: Drop unnecessary ff_ name prefixes from static functions 2013-04-30 16:02:03 +02:00
h264_weight_10bit.asm x86: h264_weight_10bit: port to cpuflags 2012-11-13 19:07:09 +01:00
h264_weight.asm x86: h264_weight: port to cpuflags 2012-11-27 21:10:38 +01:00
h264chroma_init.c h264chroma: Remove duplicate 9/10 bit functions 2013-02-19 22:33:19 +02:00
h264dsp_init.c x86: Drop unnecessary ff_ name prefixes from static functions 2013-04-30 16:02:03 +02:00
hpeldsp_avg_template.c x86: Drop unnecessary ff_ name prefixes from static functions 2013-04-30 16:02:03 +02:00
hpeldsp_init.c x86: dsputil: Move avg_pixels16_mmx() out of rnd_template.c 2013-05-02 11:45:37 +02:00
hpeldsp_rnd_template.c x86: Rename dsputil_rnd_template.c to rnd_template.c 2013-04-25 23:03:09 +03:00
hpeldsp.asm x86: qpel: Move fullpel and l2 functions to a separate file 2013-04-08 12:38:33 +03:00
idct_mmx_xvid.c Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
idct_sse2_xvid.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
idct_xvid.h Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
imdct36.asm x86: include x86inc.asm in x86util.asm 2012-10-31 00:37:42 +01:00
lpc.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
Makefile x86: Move duplicated put_pixels{8|16}_mmx functions into their own file 2013-05-02 11:16:45 +02:00
mathops.h
mlpdsp.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
motion_est.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
mpeg4qpel.asm x86: mpeg4qpel: Make movsxifnidn do the right thing 2013-02-11 20:17:15 +01:00
mpegaudiodsp.c mpegaudiosp: More consistent names for ppc/x86 optimization files 2013-04-30 12:19:43 +02:00
mpegvideo.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
mpegvideoenc_template.c Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
mpegvideoenc.c x86: Move some conditional code around to avoid unused variable warnings 2013-04-22 17:50:02 +02:00
pngdsp_init.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
pngdsp.asm x86: mmx2 ---> mmxext in asm constructs 2012-11-14 00:58:51 +01:00
proresdsp_init.c Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
proresdsp.asm Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
qpel.asm x86: hpeldsp: Move half-pel assembly from dsputil to hpeldsp 2013-04-19 23:18:53 +03:00
rnd_template.c x86: dsputil: Move avg_pixels16_mmx() out of rnd_template.c 2013-05-02 11:45:37 +02:00
rv34dsp_init.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
rv34dsp.asm Drop DCTELEM typedef 2013-01-22 18:32:56 -08:00
rv40dsp_init.c dsputil: convert remaining functions to use ptrdiff_t strides 2013-03-12 18:26:42 +01:00
rv40dsp.asm x86: mmx2 ---> mmxext in asm constructs 2012-11-14 00:58:51 +01:00
sbrdsp_init.c x86: sbrdsp: Implement SSE2 qmf_deint_bfly 2013-05-03 18:23:14 +02:00
sbrdsp.asm x86: sbrdsp: Implement SSE2 qmf_deint_bfly 2013-05-03 18:23:14 +02:00
simple_idct.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
vc1dsp_init.c dsputil: convert remaining functions to use ptrdiff_t strides 2013-03-12 18:26:42 +01:00
vc1dsp_mmx.c x86: dsputil: Move cavs and vc1-specific functions where they belong 2013-05-02 11:45:37 +02:00
vc1dsp.asm x86: PABSW: port to cpuflags 2012-11-05 14:51:10 +01:00
vc1dsp.h x86: vc1: call ff_vc1dsp_init_x86() under if (ARCH_X86) 2012-10-08 11:54:05 +02:00
videodsp_init.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
videodsp.asm cosmetics: Remove unnecessary extern keywords from function declarations 2013-03-27 14:21:45 +01:00
vorbisdsp_init.c Add av_cold attributes to arch-specific init functions 2013-02-05 17:01:05 +01:00
vorbisdsp.asm vorbisdsp: convert x86 simd functions from inline asm to yasm. 2013-01-22 18:02:24 -08:00
vp3dsp_init.c vp3: Use full transpose for all IDCTs 2013-04-15 12:32:05 +03:00
vp3dsp.asm vp3: Use full transpose for all IDCTs 2013-04-15 12:32:05 +03:00
vp8dsp_init.c cosmetics: Remove unnecessary extern keywords from function declarations 2013-03-27 14:21:45 +01:00
vp8dsp.asm dsputil: Make dsputil selectable 2013-04-10 11:04:05 +03:00
vp56_arith.h
vp56dsp_init.c Remove unnecessary dsputil.h #includes 2013-02-26 00:51:34 +01:00
vp56dsp.asm x86: yasm: Use complete source path for macro helper %includes 2012-10-31 00:37:42 +01:00
w64xmmtest.c x86: Remove win64 xmm clobbering wrappers for the now removed avcodec_encode_video function 2013-03-23 23:37:27 +02:00