Statistics
| Branch: | Revision:

ffmpeg / libavcodec / i386 @ bda2203d

# Date Author Comment
bda2203d 11/03/2006 11:07 AM Michael Niedermayer

preempt possible overflow

Originally committed as revision 6881 to svn://svn.ffmpeg.org/ffmpeg/trunk

5a1553de 11/03/2006 09:59 AM Michael Niedermayer

1 instruction less

Originally committed as revision 6880 to svn://svn.ffmpeg.org/ffmpeg/trunk

e9f1885c 11/03/2006 02:03 AM Michael Niedermayer

optimize H264_DEBLOCK_P0_Q0
2.5% faster filter_mb_fast() on P3

Originally committed as revision 6877 to svn://svn.ffmpeg.org/ffmpeg/trunk

7c428ea6 10/14/2006 05:04 PM Diego Biurrun

Put libmpeg2 IDCT functions under CONFIG_GPL, fixes link failure
with --disable-opts.

Originally committed as revision 6691 to svn://svn.ffmpeg.org/ffmpeg/trunk

c26abfa5 10/11/2006 11:17 PM Diego Biurrun

Rename ABS macro to FFABS.

Originally committed as revision 6666 to svn://svn.ffmpeg.org/ffmpeg/trunk

b78e7197 10/07/2006 03:30 PM Diego Biurrun

Change license headers to say 'FFmpeg' instead of 'this program/this library'
and fix GPL/LGPL version mismatches.

Originally committed as revision 6577 to svn://svn.ffmpeg.org/ffmpeg/trunk

ade6e7f3 10/07/2006 11:30 AM Diego Biurrun

Compilation fix, printf gets redefined to please_use_av_log.

Originally committed as revision 6574 to svn://svn.ffmpeg.org/ffmpeg/trunk

0eb59ddb 10/05/2006 12:23 AM Diego Biurrun

Switch idct_mmx_xvid.c from GPL to LGPL as permitted by the
author, Peter Ross (pross xvid org).

Originally committed as revision 6557 to svn://svn.ffmpeg.org/ffmpeg/trunk

2833fc46 10/01/2006 09:25 PM Loren Merritt

approximate qpel functions: sacrifice some quality for some decoding speed. enabled on B-frames with -lavdopts fast.

Originally committed as revision 6412 to svn://svn.ffmpeg.org/ffmpeg/trunk

62bb489b 09/27/2006 07:54 PM Måns Rullgård

add some #ifdef CONFIG_ENCODERS/DECODERS

Originally committed as revision 6356 to svn://svn.ffmpeg.org/ffmpeg/trunk

a4eb118a 09/21/2006 05:43 PM Loren Merritt

cosmetics (indentation)

Originally committed as revision 6313 to svn://svn.ffmpeg.org/ffmpeg/trunk

f469094c 09/21/2006 05:42 PM Loren Merritt

tweak ff_imdct_calc_3dn2

Originally committed as revision 6312 to svn://svn.ffmpeg.org/ffmpeg/trunk

ebbafcb4 09/21/2006 04:37 PM Loren Merritt

sse implementation of imdct.
patch mostly by Zuxy Meng (zuxy dot meng at gmail dot com)

Originally committed as revision 6311 to svn://svn.ffmpeg.org/ffmpeg/trunk

99aed7c8 09/19/2006 10:22 PM Luca Barbato

New single instruction math operation header

Originally committed as revision 6291 to svn://svn.ffmpeg.org/ffmpeg/trunk

2a2311be 09/14/2006 10:13 PM Aurelien Jacobs

disable vp3 mmx idct for theora files to avoid artifacts
(see theora-a4_v6-k250-s0_2.ogg)

Originally committed as revision 6253 to svn://svn.ffmpeg.org/ffmpeg/trunk

7f889a76 09/14/2006 12:38 AM Diego Biurrun

Remove the LGPL exception clause as discussed on ffmpeg-devel
and move the dependent code under CONFIG_GPL.

Originally committed as revision 6248 to svn://svn.ffmpeg.org/ffmpeg/trunk

1dac8fea 09/12/2006 08:58 PM Aurelien Jacobs

Enables back the mmx/sse optimized version of the vp3 idct.
It generates different md5sum than the reference C implementation,
but no visual difference, so enabled only when bitexact is not set.

Originally committed as revision 6241 to svn://svn.ffmpeg.org/ffmpeg/trunk

04d7f601 09/10/2006 02:02 PM Diego Biurrun

Add official LGPL license headers to the files that were missing them.

Originally committed as revision 6219 to svn://svn.ffmpeg.org/ffmpeg/trunk

0e176c3e 09/02/2006 11:10 PM Måns Rullgård

remove redundant declarations

Originally committed as revision 6153 to svn://svn.ffmpeg.org/ffmpeg/trunk

3e20143e 08/28/2006 09:33 AM Loren Merritt

mmx implementation of deblocking strength decision.
2-3% faster h264.

Originally committed as revision 6113 to svn://svn.ffmpeg.org/ffmpeg/trunk

1e4ecf26 08/18/2006 11:53 PM Loren Merritt

ff_fft_calc_3dn/3dn2/sse: convert intrinsics to inline asm.
2.5% faster fft, 0.5% faster vorbis.

Originally committed as revision 6023 to svn://svn.ffmpeg.org/ffmpeg/trunk

cf5aed5b 08/18/2006 10:43 AM Michael Niedermayer

simplify

Originally committed as revision 6020 to svn://svn.ffmpeg.org/ffmpeg/trunk

3829a62e 08/17/2006 07:49 AM Michael Niedermayer

insufficient alignment

Originally committed as revision 6006 to svn://svn.ffmpeg.org/ffmpeg/trunk

6bb9e492 08/13/2006 10:10 AM Marco Manfredini

Fix building with --disable-opts but MMX enabled.
patch by Marco Manfredini mldb at gmx dot net

Originally committed as revision 5994 to svn://svn.ffmpeg.org/ffmpeg/trunk

4454dc1b 08/12/2006 04:37 PM John Dalgliesh

Support for MacIntel, last part: balign directives
Determines whether .align's arg is power-of-two or not, then defines ASMALIGN appropriately in config.h. Changes all .baligns to ASMALIGNs.
Patch by John Dalgliesh % johnd AH defyne P org %
Original thread:...

06972056 08/11/2006 06:19 PM Loren Merritt

vorbis simd tweaks

Originally committed as revision 5983 to svn://svn.ffmpeg.org/ffmpeg/trunk

1f1aa1d9 08/10/2006 08:24 PM Michael Niedermayer

convert vector_fmul_reverse_sse2 and vector_fmul_add_add_sse2 to sse
please complain if they are slower on sse2 cpus ...

Originally committed as revision 5976 to svn://svn.ffmpeg.org/ffmpeg/trunk

eb4825b5 08/10/2006 07:06 PM Loren Merritt

sse and 3dnow implementations of float->int conversion and mdct windowing.
15% faster vorbis.

Originally committed as revision 5975 to svn://svn.ffmpeg.org/ffmpeg/trunk

ffad4ed1 08/10/2006 04:05 PM Luca Barbato

Fix x86 SIMD asm and pic, patch from Martin von Gagern <>

Originally committed as revision 5973 to svn://svn.ffmpeg.org/ffmpeg/trunk

347be472 08/10/2006 03:26 PM John Dalgliesh

Support for MacIntel, take xx: '/nop' illegal for old versions of GAS
Patch by John Dalgliesh % johnd AH defyne P org %
Original thread:
Date: Aug 8, 2006 8:12 PM
Subject: Re: [Ffmpeg-devel] [PATCH] '/nop' illegal for old versions of GAS

Originally committed as revision 5972 to svn://svn.ffmpeg.org/ffmpeg/trunk

0fc256f3 08/10/2006 11:29 AM John Dalgliesh

Add support for Mac OS X Intel part 2: Assembler macros in fdct_mmx.c
convert gas macros to ccp macros
Patch by John Dalgliesh % johnd AH defyne P org %
Original thread:
Date: Aug 10, 2006 5:39 AM
Subject: Re: [Ffmpeg-devel] Mac OS X Intel part 2: Assembler macros in fdct_mmx.c...

fc48b6fe 08/10/2006 09:06 AM John Dalgliesh

Support for Mac OS X Intel, part 3: binary integer constants:
Apple's assembler only understands the same integer constants as C does: hex, decimal, octal. It doesn't understand binary integer constants (0b...) so this patch replaces binary integer constants with hex ones....

ee5df927 08/09/2006 06:37 AM Loren Merritt

emms -> femms

Originally committed as revision 5965 to svn://svn.ffmpeg.org/ffmpeg/trunk

2494bdd9 08/09/2006 06:33 AM Loren Merritt

gcc 2.95 and 3.4.x on x86 32bit without fomit-frame-pointer can't even find 5 registers for asm input.
0.5% slower vorbis.

Originally committed as revision 5964 to svn://svn.ffmpeg.org/ffmpeg/trunk

1b87c402 08/08/2006 09:47 PM Loren Merritt

slightly faster ff_imdct_calc_3dn2() on amd64. (gcc added a bunch of useless movsxd)

Originally committed as revision 5962 to svn://svn.ffmpeg.org/ffmpeg/trunk

21bb884f 08/08/2006 12:03 PM Michael Niedermayer

change vorbis_inverse_coupling_sse2() so it works on sse1 cpus

Originally committed as revision 5957 to svn://svn.ffmpeg.org/ffmpeg/trunk

bcfa3e58 08/08/2006 04:01 AM Loren Merritt

3dnow2 implementation of imdct.
6% faster vorbis and wma.

Originally committed as revision 5954 to svn://svn.ffmpeg.org/ffmpeg/trunk

cd035a60 08/03/2006 07:09 AM Loren Merritt

10l, vorbis_inverse_coupling_sse() was really 3dnow

Originally committed as revision 5903 to svn://svn.ffmpeg.org/ffmpeg/trunk

2dac4acf 08/03/2006 03:18 AM Loren Merritt

sse & sse2 implementations of vorbis channel coupling.
9% faster vorbis (on a K8).

Originally committed as revision 5898 to svn://svn.ffmpeg.org/ffmpeg/trunk

595e7bd9 07/29/2006 08:45 AM Stefan Gehrer

some MMX optimizations for the CAVS decoder

Originally committed as revision 5846 to svn://svn.ffmpeg.org/ffmpeg/trunk

5ced7b80 07/19/2006 09:49 AM Michael Niedermayer

disable the vp3 mmx and sse2 idcts, their output doesnt match the c idct (tested with -f crc) and the theora spec does not allow different idcts not to mention the difference is quite vissible ...

Originally committed as revision 5788 to svn://svn.ffmpeg.org/ffmpeg/trunk

98d417cb 07/05/2006 07:31 PM Måns Rullgård

#define SBUTTERFLY outside CONFIG_ENCODERS

Originally committed as revision 5628 to svn://svn.ffmpeg.org/ffmpeg/trunk

9c39071d 07/03/2006 10:52 AM Luca Abeni

Move REG_* macros from libavcodec/i386/mmx.h to libavutil/x86_cpu.h

Originally committed as revision 5595 to svn://svn.ffmpeg.org/ffmpeg/trunk

3f8674a9 07/02/2006 10:01 PM Måns Rullgård

remove redundant macro definitions

Originally committed as revision 5589 to svn://svn.ffmpeg.org/ffmpeg/trunk

8fb0d073 07/02/2006 09:53 PM Måns Rullgård

kill warning

Originally committed as revision 5588 to svn://svn.ffmpeg.org/ffmpeg/trunk

e27b6e62 04/28/2006 05:03 PM Michael Niedermayer

missmatch control for mpeg2 intra dequantization if bitexact=1

Originally committed as revision 5328 to svn://svn.ffmpeg.org/ffmpeg/trunk

392f6da8 04/28/2006 07:46 AM Zuxy Meng

Remove unused and unsupported Cyrix's "Extended MMX",
Add SSE3 support.
Patch by Zuxy Meng < zuxy POIS meng AH gmail POIS com >
Original thread:
04/26/06 13:13:
[Ffmpeg-devel] [PATCH] Bug fix, SSE3 support in i386/cputest.c and dsputil.h

Originally committed as revision 5326 to svn://svn.ffmpeg.org/ffmpeg/trunk

f42635f5 04/18/2006 03:48 AM Wolfram Gloger

gcc-2.95 compile fix, patch by Wolfram Gloger <wmglo A dent PIS med PIS uni-muenchen PIS de>

Originally committed as revision 5298 to svn://svn.ffmpeg.org/ffmpeg/trunk

75ca1a5f 04/05/2006 04:13 AM Loren Merritt

gmc_mmx tweaks

Originally committed as revision 5269 to svn://svn.ffmpeg.org/ffmpeg/trunk

703c8195 04/04/2006 09:23 AM Loren Merritt

mmx implementation of 3-point GMC. (5x faster than C)

Originally committed as revision 5265 to svn://svn.ffmpeg.org/ffmpeg/trunk

22b48b85 03/27/2006 12:51 PM Luca Barbato

altivec support for snow

Originally committed as revision 5228 to svn://svn.ffmpeg.org/ffmpeg/trunk

5e8b787a 03/25/2006 08:41 AM Loren Merritt

simplified and slightly faster h264_chroma_mc8_mmx

Originally committed as revision 5214 to svn://svn.ffmpeg.org/ffmpeg/trunk

513fbd8e 03/23/2006 08:16 PM Loren Merritt

prefetch pixels for future motion compensation. 2-5% faster h264.

Originally committed as revision 5203 to svn://svn.ffmpeg.org/ffmpeg/trunk

5e6a5c4d 03/22/2006 10:08 PM Loren Merritt

10l

Originally committed as revision 5201 to svn://svn.ffmpeg.org/ffmpeg/trunk

fdd30579 03/22/2006 10:05 PM Loren Merritt

added mmx implementation of h264_chroma_mc2

Originally committed as revision 5200 to svn://svn.ffmpeg.org/ffmpeg/trunk

e8600e5e 03/22/2006 12:08 PM Robert Edele

add MMX and SSE versions of ff_snow_inner_add_yblock
Patch by Robert Edele < yartrebo AH earthlink POIS net >
Original Thread:
Date: Mar 22, 2006 3:24 AM
Subject: [Ffmpeg-devel] [PATCH] snow mmx + sse2 part 5

Originally committed as revision 5197 to svn://svn.ffmpeg.org/ffmpeg/trunk

2c9a0285 03/21/2006 09:51 PM Robert Edele

snow mmx+sse2 optimizations, part 4

Patch by Robert Edele, yartrebo <<at>> earthlink <<dot>> net

Originally committed as revision 5191 to svn://svn.ffmpeg.org/ffmpeg/trunk

4567b4bd 03/20/2006 10:27 PM Robert Edele

Add the mmx and sse2 implementations of ff_snow_vertical_compose().
Patch by Robert Edele < yartrebo AH earthlink POIS net >
Original thread:
Date: Mar 20, 2006 5:54 PM
Subject: [Ffmpeg-devel] [PATCH] snow mmx + sse2 part 3

Originally committed as revision 5185 to svn://svn.ffmpeg.org/ffmpeg/trunk

059715a4 03/16/2006 07:18 PM Robert Edele

First part of a series of speed-enchancing patches.
This one sets up a snow.h and makes snow use the dsputil function pointer
framework to access the three functions that will be implemented in asm
in the other parts of the patchset.
Patch by Robert Edele < yartrebo AH earthlink POIS net>...

82eb4b0f 03/08/2006 04:13 AM Zuxy Meng

3DNow! & Extended 3DNow! versions of FFT

Patch by Zuxy Meng, zuxy <<dot>> meng >>at<< gmail <<dot>> com
Minor non-functional diff-related fixes by me.

Originally committed as revision 5125 to svn://svn.ffmpeg.org/ffmpeg/trunk

548a1c8a 03/07/2006 10:45 PM Loren Merritt

h264_idct8_add_mmx

Originally committed as revision 5123 to svn://svn.ffmpeg.org/ffmpeg/trunk

6da971f1 03/07/2006 10:33 PM Loren Merritt

h264_idct_add only needs mmx1

Originally committed as revision 5122 to svn://svn.ffmpeg.org/ffmpeg/trunk

2ffb22d2 03/05/2006 08:25 PM Zuxy Meng

use xorps instead of mulps to toggle the sign of a float, as suggested by Software Optimization Guide for AMD64 Processors.
Patch by Zuxy Meng < zuxy POIS meng AH gmail POIS com > OKed by Michael
Original thread:
Date: Mar 5, 2006 8:15 PM
Subject: [Ffmpeg-devel] [PATCH] Little optimization to fft_sse.c...

d84f7c61 03/05/2006 07:02 PM Loren Merritt

gcc2.95 workaround

Originally committed as revision 5111 to svn://svn.ffmpeg.org/ffmpeg/trunk

7a5b2fa8 03/04/2006 07:56 PM Loren Merritt

remove some useless instructions

Originally committed as revision 5109 to svn://svn.ffmpeg.org/ffmpeg/trunk

6a8eb0f4 03/02/2006 08:21 AM Loren Merritt

4% faster h264_qpel_mc

Originally committed as revision 5094 to svn://svn.ffmpeg.org/ffmpeg/trunk

ef9d1d15 02/10/2006 06:55 AM Loren Merritt

h264: special case dc-only idct. ~1% faster overall

Originally committed as revision 4971 to svn://svn.ffmpeg.org/ffmpeg/trunk

4e295993 02/09/2006 02:43 AM Loren Merritt

10l in 1.12

Originally committed as revision 4965 to svn://svn.ffmpeg.org/ffmpeg/trunk

6ee66973 02/07/2006 04:10 PM Loren Merritt

10l (x86_64)

Originally committed as revision 4952 to svn://svn.ffmpeg.org/ffmpeg/trunk

e545f375 02/07/2006 10:52 AM Loren Merritt

18% faster put_h264_qpel16_mc132_mmx2

Originally committed as revision 4951 to svn://svn.ffmpeg.org/ffmpeg/trunk

c03ce51d 02/07/2006 07:35 AM Loren Merritt

11% faster put_h264_qpel16_v_lowpass_mmx2

Originally committed as revision 4950 to svn://svn.ffmpeg.org/ffmpeg/trunk

0331f092 02/07/2006 06:25 AM Loren Merritt

15% faster put_h264_qpel16_hv_lowpass_mmx2

Originally committed as revision 4949 to svn://svn.ffmpeg.org/ffmpeg/trunk

68b51e58 02/05/2006 01:35 PM Steve L'Homme

MSVC-compatible _align8/_align16 declaration
patch by Steve Lhomme, steve .dot. lhomme .at. free .dot. fr

Originally committed as revision 4942 to svn://svn.ffmpeg.org/ffmpeg/trunk

5509bffa 01/12/2006 10:43 PM Diego Biurrun

Update licensing information: The FSF changed postal address.

Originally committed as revision 4842 to svn://svn.ffmpeg.org/ffmpeg/trunk

e8b56208 01/09/2006 03:38 AM Loren Merritt

tweak h264_biweight

Originally committed as revision 4835 to svn://svn.ffmpeg.org/ffmpeg/trunk

cec93959 12/30/2005 11:47 PM Loren Merritt

fix some potential arithmetic overflows in pred_direct_motion() and
ff_h264_weight_WxH_mmx2().

Originally committed as revision 4795 to svn://svn.ffmpeg.org/ffmpeg/trunk

bb270c08 12/22/2005 01:10 AM Diego Biurrun

COSMETICS: tabs --> spaces, some prettyprinting

Originally committed as revision 4764 to svn://svn.ffmpeg.org/ffmpeg/trunk

115329f1 12/17/2005 06:14 PM Diego Biurrun

COSMETICS: Remove all trailing whitespace.

Originally committed as revision 4749 to svn://svn.ffmpeg.org/ffmpeg/trunk

f6d1338c 12/10/2005 10:53 PM Guillaume Poirier

Add the rest of missing Reg_* macros to support both AMD-64 style regs and IA32 regs.
Not used yet, but should be once the SIMD code to accelerate Snow decoding is merged.

Originally committed as revision 4731 to svn://svn.ffmpeg.org/ffmpeg/trunk

ea15df80 11/12/2005 05:23 AM Loren Merritt

use sse16_sse2() in nsse

Originally committed as revision 4688 to svn://svn.ffmpeg.org/ffmpeg/trunk

a6624e21 10/27/2005 06:45 AM Loren Merritt

faster h264_chroma_mc8_mmx, added h264_chroma_mc4_mmx.
2-4% overall speedup.

Originally committed as revision 4666 to svn://svn.ffmpeg.org/ffmpeg/trunk

b926572a 10/09/2005 11:38 PM Loren Merritt

h264 mmx weighted prediction. up to 3% overall speedup.

Originally committed as revision 4630 to svn://svn.ffmpeg.org/ffmpeg/trunk

5693c083 09/30/2005 02:31 AM Loren Merritt

sse2 16x16 sum squared diff (306=>268 cycles on a K8)
faster 8x8 mmx ssd (77=>70 cycles)

Originally committed as revision 4623 to svn://svn.ffmpeg.org/ffmpeg/trunk

12e96681 09/21/2005 09:17 PM Michael Niedermayer

replace a few mov + psrlq with pshufw, there are more cases which could benefit from this but they would require us to duplicate some functions ...
the trick is from various places (my own code in libpostproc, a patch on the x264 list, ...)

Originally committed as revision 4608 to svn://svn.ffmpeg.org/ffmpeg/trunk

cd7af76d 09/10/2005 07:30 PM Reimar Döffinger

Fix compile without CONFIG_GPL, misplaced #endif caused a missing }.

Originally committed as revision 4575 to svn://svn.ffmpeg.org/ffmpeg/trunk

9f211bc6 09/10/2005 07:03 PM Michael Niedermayer

remove unused table entries
change non portable table access

Originally committed as revision 4574 to svn://svn.ffmpeg.org/ffmpeg/trunk

84740d59 09/10/2005 05:01 PM Michael Niedermayer

xvids mmx&mmx2 idcts
needed to decode xvid without some minor artefacts
under #ifdef CONFIG_GPL of course

Originally committed as revision 4572 to svn://svn.ffmpeg.org/ffmpeg/trunk

79396ac6 09/06/2005 09:25 PM Måns Rullgård

Kill some compiler warnings. Compiled code verified identical after changes.

Originally committed as revision 4567 to svn://svn.ffmpeg.org/ffmpeg/trunk

d3a9f798 09/03/2005 09:17 AM Michael Niedermayer

simplify (d&a) and (d&~a) calculation, hint by skal

Originally committed as revision 4552 to svn://svn.ffmpeg.org/ffmpeg/trunk

b5b65df7 09/02/2005 09:13 PM Michael Niedermayer

add consts (this was in my local tree, dunno where it came from, probably forgoten from some const patch)

Originally committed as revision 4551 to svn://svn.ffmpeg.org/ffmpeg/trunk

bf4e3bd2 08/14/2005 03:42 PM Måns Rullgård

kill a bunch of compiler warnings

Originally committed as revision 4522 to svn://svn.ffmpeg.org/ffmpeg/trunk

c11c2bc2 08/01/2005 08:07 PM Alexander Strasser

libavutil: Utility code from libavcodec moved to a separate library.

Originally committed as revision 4489 to svn://svn.ffmpeg.org/ffmpeg/trunk

d2bb7db1 06/02/2005 08:45 PM Loren Merritt

sort H.264 mmx dsp functions into their own file

Originally committed as revision 4338 to svn://svn.ffmpeg.org/ffmpeg/trunk

c26ae41d 06/01/2005 09:19 PM Michael Niedermayer

adding a few const

Originally committed as revision 4337 to svn://svn.ffmpeg.org/ffmpeg/trunk

435b0720 06/01/2005 06:04 PM Michael Niedermayer

100l for myself (breaking amd64)

Originally committed as revision 4336 to svn://svn.ffmpeg.org/ffmpeg/trunk

6510f43c 06/01/2005 11:56 AM Michael Niedermayer

merge a few asm blocks so gcc cant unoptimize it (658->631 dezicycles on duron)

Originally committed as revision 4334 to svn://svn.ffmpeg.org/ffmpeg/trunk

987ae784 06/01/2005 11:36 AM Michael Niedermayer

get rid of 2 movq (680 -> 658 dezicycles on duron)

Originally committed as revision 4333 to svn://svn.ffmpeg.org/ffmpeg/trunk

e4b36d44 06/01/2005 08:43 AM Michael Niedermayer

avoid one transpose (730->680 dezicycles on duron)

Originally committed as revision 4332 to svn://svn.ffmpeg.org/ffmpeg/trunk

85bbfcd4 06/01/2005 04:51 AM Loren Merritt

10l (symbol mangling)

Originally committed as revision 4331 to svn://svn.ffmpeg.org/ffmpeg/trunk

1f3dbc09 06/01/2005 01:18 AM Michael Niedermayer

add rounding bias before the horizontal idct (765->730 dezicyles on duron)

Originally committed as revision 4330 to svn://svn.ffmpeg.org/ffmpeg/trunk