Statistics
| Branch: | Revision:

ffmpeg / libavcodec / i386 @ e98750c3

Name Size Revision Age Author Comment
cavsdsp_mmx.c 19.8 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
cpuid.c 3.55 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
dsputil_h264_template_mmx.c 10.7 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
dsputil_h264_template_ssse3.c 7.01 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
dsputil_mmx.c 104 KB e98750c3 over 13 years Michael Niedermayer float_to_int16_sse2() 20% faster than sse Orig...
dsputil_mmx.h 4.2 KB 1835cda6 over 13 years Victor Pollex Make LOAD4/STORE4 macros more generic. Patch by...
dsputil_mmx_avg.h 37.4 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
dsputil_mmx_qns.h 3.89 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
dsputil_mmx_rnd.h 22.8 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
dsputilenc_mmx.c 41.5 KB 1835cda6 over 13 years Victor Pollex Make LOAD4/STORE4 macros more generic. Patch by...
fdct_mmx.c 15.9 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
fft_3dn.c 4.26 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
fft_3dn2.c 6.97 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
fft_sse.c 11.5 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
flacdsp_mmx.c 5.61 KB 74fd9022 over 13 years Alexander Strange Realign newlines. Originally committed as revi...
h264_i386.h 6.18 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
h264dsp_mmx.c 84.1 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
idct_mmx.c 22.1 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
idct_mmx_xvid.c 23.4 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
idct_sse2_xvid.c 15 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
idct_xvid.h 1.17 KB f73a6393 almost 14 years Alexander Strange Add a new xvid-style IDCT using SSE2. Original...
mathops.h 1.45 KB 5b21bdab over 14 years Diego Biurrun Add FFMPEG_ prefix to all multiple inclusion gu...
mmx.h 13.6 KB c88c253d almost 14 years Diego Biurrun cosmetics: __asm__ __volatile__ --> asm volatil...
motion_est_mmx.c 15.6 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
mpegvideo_mmx.c 27.4 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
mpegvideo_mmx_template.c 17.1 KB 40d0e665 over 13 years Ramiro Polla Do not misuse long as the size of a register in...
simple_idct_mmx.c 71 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
snowdsp_mmx.c 38.6 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
vc1dsp_mmx.c 23.3 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
vp3dsp_mmx.c 11.7 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
vp3dsp_mmx.h 1.19 KB a12b44d7 over 13 years Diego Biurrun Add missing required header directly. Original...
vp3dsp_sse2.c 35.6 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...
vp3dsp_sse2.h 1.15 KB 245976da over 13 years Diego Biurrun Use full path for #includes from another direct...

Latest revisions

# Date Author Comment
e98750c3 07/09/2008 07:21 AM Michael Niedermayer

float_to_int16_sse2()
20% faster than sse

Originally committed as revision 14138 to svn://svn.ffmpeg.org/ffmpeg/trunk

1835cda6 07/08/2008 09:24 AM Victor Pollex

Make LOAD4/STORE4 macros more generic.
Patch by Victor Pollex victor pollex web de
Original thread: [PATCH] mmx implementation of vc-1 inverse transformations
Date: 06/21/2008 03:37 PM

Originally committed as revision 14108 to svn://svn.ffmpeg.org/ffmpeg/trunk

35ee72b1 07/07/2008 09:25 PM Michael Niedermayer

1 c-asm loop less and 1x unroll of float_to_int16_sse()
25% faster

Originally committed as revision 14104 to svn://svn.ffmpeg.org/ffmpeg/trunk

560fa9bf 07/07/2008 09:04 PM Michael Niedermayer

Fix x86-64

Originally committed as revision 14103 to svn://svn.ffmpeg.org/ffmpeg/trunk

63b737d4 07/07/2008 08:46 PM Michael Niedermayer

dont use C-asm loops and unroll once float_to_int16_3dnow()
30% faster

Originally committed as revision 14102 to svn://svn.ffmpeg.org/ffmpeg/trunk

74fd9022 06/28/2008 06:30 PM Alexander Strange

Realign newlines.

Originally committed as revision 14023 to svn://svn.ffmpeg.org/ffmpeg/trunk

00969e1c 06/28/2008 06:27 PM Alexander Strange

Use MANGLE instead of memory operands to read globals.
(fixes out of registers with apple gcc 4.2)

Originally committed as revision 14022 to svn://svn.ffmpeg.org/ffmpeg/trunk

00eebe3d 06/22/2008 07:05 AM Reimar Döffinger

Fix add_bytes_mmx and add_bytes_l2_mmx for w < 16

Originally committed as revision 13877 to svn://svn.ffmpeg.org/ffmpeg/trunk

0bd134ab 05/17/2008 02:36 PM Michael Niedermayer

Simplify vsad16_mmx2().

Originally committed as revision 13193 to svn://svn.ffmpeg.org/ffmpeg/trunk

6bf6a930 05/17/2008 02:35 PM Michael Niedermayer

Simplify vsad16_mmx().

Originally committed as revision 13191 to svn://svn.ffmpeg.org/ffmpeg/trunk

View revisions

Also available in: Atom