Statistics
| Branch: | Revision:

ffmpeg / libavcodec / x86 @ bf6fa732

Name Size Revision Age Author Comment
Makefile 3.4 KB dda3f0ef about 10 years Justin Ruggles Add x86-optimized versions of exponent_min(). ...
ac3dsp.asm 3.84 KB 1f004fc5 about 10 years Justin Ruggles ac3dsp: Change punpckhqdq to movhlps in ac3_max...
ac3dsp_mmx.c 2.2 KB fbb6b49d about 10 years Justin Ruggles ac3enc: Add x86-optimized function to speed up ...
cavsdsp_mmx.c 19.2 KB c6c98d08 over 10 years Stefano Sabatini Move mm_support() from libavcodec to libavutil,...
dct32_sse.c 11.5 KB 153ca56b over 10 years Ramiro Polla xmm_clobbers: list xmm registers first in clobb...
deinterlace.asm 2.48 KB 1761272b over 10 years avcoder Use SECTION .text for yasm code. Patch by avco...
dnxhd_mmx.c 2.15 KB 4f9d25dd over 10 years Ramiro Polla dnxhd_mmx: prefer xmm registers below xmm6 when...
dsputil_mmx.c 117 KB bf6fa732 about 10 years Ronald S. Bultje dsputil_mmx.c: remove ff_vector128. Remove ff_...
dsputil_mmx.h 7.86 KB 12802ec0 about 10 years Ronald S. Bultje dsputil: move VC1-specific stuff into VC1DSPCon...
dsputil_mmx_avg_template.c 40.8 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
dsputil_mmx_qns_template.c 3.76 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
dsputil_mmx_rnd_template.c 22.9 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
dsputil_yasm.asm 23.9 KB 17cf7c68 about 10 years Ronald S. Bultje Fix ff_emu_edge_core_sse() on Win64. Fix emu_e...
dsputilenc_mmx.c 35 KB 56f8952b about 10 years Justin Ruggles Move lpc_compute_autocorr() from DSPContext to ...
dsputilenc_yasm.asm 9.52 KB ada65af9 over 10 years Ronald S. Bultje Don't access upper 32 bits of a 32-bit int on 6...
fdct_mmx.c 17.8 KB e2d13c58 over 10 years Ramiro Polla cosmetics: split long line Originally committe...
fft.c 1.89 KB e6b1ed69 about 10 years Loren Merritt FFT: factor a shuffle out of the inner loop and...
fft.h 1.58 KB 4dcc4f8e over 10 years Vitor Sessak SSE optimized 32-point DCT Originally committe...
fft_3dn.c 898 Bytes a6493a8f about 12 years Diego Biurrun Rename libavcodec/i386/ --> libavcodec/x86/. It...
fft_3dn2.c 5.1 KB cb4f1246 over 10 years Alex Converse imdct/x86: Use "s->mdct_size" instead of "1 << ...
fft_mmx.asm 14.9 KB e6b1ed69 about 10 years Loren Merritt FFT: factor a shuffle out of the inner loop and...
fft_sse.c 2.93 KB 770c410f about 10 years Alex Converse Fix ff_imdct_calc_sse() on gcc-4.6 Gcc 4.6 onl...
fmtconvert.asm 2.57 KB c73d99e6 about 10 years Justin Ruggles Separate format conversion DSP functions from D...
fmtconvert_mmx.c 9.68 KB c73d99e6 about 10 years Justin Ruggles Separate format conversion DSP functions from D...
h264_chromamc.asm 17.4 KB 8d147f1f about 10 years Ronald S. Bultje For rounding in chroma MC SSSE3, use 16-byte pw...
h264_deblock.asm 22.4 KB 2c166c3a over 10 years Ronald S. Bultje Port latest x264 deblock asm (before they moved...
h264_i386.h 6.08 KB ba87f080 almost 11 years Diego Biurrun Remove explicit filename from Doxygen @file com...
h264_idct.asm 24.6 KB 19fb234e about 10 years Jason Garrett-Glaser H.264: split luma dc idct out and implement MMX...
h264_intrapred.asm 70.5 KB 80944df7 about 10 years Mans Rullgard x86: fix overflow in h264 8x8 planar prediction...
h264_intrapred_init.c 13 KB 536e9b2f about 10 years Daniel Kang Port pred8x8l_down_left_mmxext (H.264 intra pre...
h264_qpel_mmx.c 53.2 KB 153ca56b over 10 years Ramiro Polla xmm_clobbers: list xmm registers first in clobb...
h264_weight.asm 8.33 KB b1c32fb5 over 10 years Reimar Döffinger Use "d" suffix for general-purpose registers us...
h264dsp_mmx.c 17.2 KB 19fb234e about 10 years Jason Garrett-Glaser H.264: split luma dc idct out and implement MMX...
idct_mmx.c 23.7 KB 740dfe70 over 10 years Vitor Sessak Fix compilation in x86_64. I broke it with r245...
idct_mmx_xvid.c 23.4 KB c26e58e3 almost 11 years Måns Rullgård Add some missing #includes Originally committe...
idct_sse2_xvid.c 15.3 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
idct_xvid.h 1.2 KB ba87f080 almost 11 years Diego Biurrun Remove explicit filename from Doxygen @file com...
lpc_mmx.c 6.11 KB 1c189fc5 about 10 years Justin Ruggles cosmetics related to LPC changes. Signed-off-b...
mathops.h 2.68 KB 22cb6fb6 almost 11 years Michael Niedermayer Adding missing () to mathops.h. Originally com...
mlpdsp.c 6.21 KB 989b7181 over 11 years Ramiro Polla Use fewer macros in x86-optimized mlpdsp. Fixes...
motion_est_mmx.c 16 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
mpegaudiodec_mmx.c 5 KB c6c98d08 over 10 years Stefano Sabatini Move mm_support() from libavcodec to libavutil,...
mpegvideo_mmx.c 28 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
mpegvideo_mmx_template.c 17.4 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
simple_idct_mmx.c 71.1 KB ef4a6514 about 10 years Mans Rullgard Replace ASMALIGN() with .p2align This macro ha...
snowdsp_mmx.c 39.4 KB 9276bddd over 10 years İsmail Dönmez snowdsp: Explicitly state the operand sizes Fi...
vc1dsp_mmx.c 35.8 KB 12802ec0 about 10 years Ronald S. Bultje dsputil: move VC1-specific stuff into VC1DSPCon...
vc1dsp_yasm.asm 7.8 KB b1c32fb5 over 10 years Reimar Döffinger Use "d" suffix for general-purpose registers us...
vp3dsp.asm 20.7 KB b1c32fb5 over 10 years Reimar Döffinger Use "d" suffix for general-purpose registers us...
vp56_arith.h 1.71 KB 05c04cdf over 10 years Jason Garrett-Glaser VP5/6/8: ~7% faster arithmetic decoding Grab fr...
vp56dsp.asm 4.86 KB 4eca52ed over 10 years Ronald S. Bultje Fix typos when converting inline asm to yasm, f...
vp56dsp_init.c 1.73 KB c6c98d08 over 10 years Stefano Sabatini Move mm_support() from libavcodec to libavutil,...
vp8dsp-init.c 19 KB c6c98d08 over 10 years Stefano Sabatini Move mm_support() from libavcodec to libavutil,...
vp8dsp.asm 78.4 KB b1c32fb5 over 10 years Reimar Döffinger Use "d" suffix for general-purpose registers us...
x86inc.asm 16.4 KB 532e7697 over 10 years Loren Merritt sync yasm macros from x264 Originally committe...
x86util.asm 9.29 KB dda3f0ef about 10 years Justin Ruggles Add x86-optimized versions of exponent_min(). ...

Latest revisions

# Date Author Comment
bf6fa732 02/19/2011 03:51 PM Ronald S. Bultje

dsputil_mmx.c: remove ff_vector128.

Remove ff_vector128, it is identical to ff_pb_80.
12802ec0 02/17/2011 10:35 PM Ronald S. Bultje

dsputil: move VC1-specific stuff into VC1DSPContext.
1f004fc5 02/16/2011 07:08 PM Justin Ruggles

ac3dsp: Change punpckhqdq to movhlps in ac3_max_msb_abs_int16().

Signed-off-by: Ronald S. Bultje <>
fbb6b49d 02/13/2011 09:49 PM Justin Ruggles

ac3enc: Add x86-optimized function to speed up log2_tab().

AC3DSPContext.ac3_max_msb_abs_int16() finds the maximum MSB of the absolute
value of each element in an array of int16_t.

Signed-off-by: Ronald S. Bultje <>
e6b1ed69 02/13/2011 02:36 PM Loren Merritt

FFT: factor a shuffle out of the inner loop and merge it into fft_permute.

6% faster SSE FFT on Conroe, 2.5% on Penryn.

Signed-off-by: Janne Grunau <>
dda3f0ef 02/10/2011 08:32 PM Justin Ruggles

Add x86-optimized versions of exponent_min().

Signed-off-by: Ronald S. Bultje <>
17cf7c68 02/08/2011 11:25 PM Ronald S. Bultje

Fix ff_emu_edge_core_sse() on Win64.

Fix emu_edge_v_extend_15 to be <128 bytes on Win64, by being more strict
on the size of registers and which registers are being used for operations
where multiple are available. This fixes segfaults in emulated_edge()...
c73d99e6 02/02/2011 02:44 AM Justin Ruggles

Separate format conversion DSP functions from DSPContext.

This will be beneficial for use with the audio conversion API without
requiring it to depend on all of dsputil.

Signed-off-by: Mans Rullgard <>
770c410f 02/02/2011 02:40 AM Alex Converse

Fix ff_imdct_calc_sse() on gcc-4.6

Gcc 4.6 only preserves the first value when using an array with an "m"
constraint.

Signed-off-by: Mans Rullgard <>
81f2a3f4 02/01/2011 01:55 AM Ronald S. Bultje

Implement a SIMD version of emulated_edge_mc() for x86.

From ~550 cycles (C version) to 170 (SSE/x86-64), 206 (MMX/x86-32)
and 196 (SSE2/x86-32) cycles.

View revisions

Also available in: Atom