a08a502eda
dont copy the whole GetBitContext around
...
Originally committed as revision 6062 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 06:57:32 +00:00
3328ec6331
faster handling of zero coeffs in the low freq decode
...
Originally committed as revision 6061 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 01:12:26 +00:00
3c693e7743
optimizing high freq decode
...
Originally committed as revision 6060 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 01:01:39 +00:00
daf4cd9ac3
use memset() instead of slow c loops
...
Originally committed as revision 6059 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 00:03:51 +00:00
c7aa36964e
simplify
...
Originally committed as revision 6058 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-23 23:40:03 +00:00
acba32385b
fix arm asm compilation in mpegaudiodec
...
Originally committed as revision 6057 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-23 23:39:27 +00:00
b3701f5cc0
Alignment of the LT window, segfault fix patch by Baptiste Coudurier.
...
Originally committed as revision 6051 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 16:23:56 +00:00
69fd15f871
MUL* for ARM code based on a patch by Siarhei Siamashka
...
untested
Originally committed as revision 6050 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 13:25:09 +00:00
f617adedc8
replace MULL with asm too, no significnat speedup but its probably better to not take any chances, some versions of gcc will almost certainly mess it up too if they can
...
Originally committed as revision 6049 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 12:07:02 +00:00
47a0cd7408
replacing MULH by asm for x86
...
about 30% faster imdct36()
Originally committed as revision 6048 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 11:51:09 +00:00
5ab1972b53
indent preprocessor directives
...
Originally committed as revision 6047 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 11:16:47 +00:00
355903f5a8
make high precission synth filter 3 times faster on x86
...
Originally committed as revision 6046 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 11:11:04 +00:00
0bd2483a75
replace MULL by MULH + shift in dct32() (code is very slightly faster, and the compiler should be able to optimize the shift away on 64bit archs)
...
Originally committed as revision 6045 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 06:24:59 +00:00
eb6447766d
replace a few MULL by MULH
...
Originally committed as revision 6039 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-21 12:12:43 +00:00
120aad7fe9
reorder butterflies to reduce memory load/store
...
Originally committed as revision 6037 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-20 22:18:26 +00:00
6c496518e8
Added codec id for QCELP.
...
Originally committed as revision 6036 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-20 19:08:05 +00:00
ed567d9c41
cosmetics
...
Originally committed as revision 6032 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 23:12:10 +00:00
67eca72dc0
SWAP
...
Originally committed as revision 6030 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 20:55:02 +00:00
0eb6817d98
audio format conversion
...
untested and unused
Originally committed as revision 6029 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 20:22:57 +00:00
a37e9e8606
Allow swscale emulation header to be included by C++ programs
...
Originally committed as revision 6027 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 15:14:44 +00:00
9aee40d967
SIMD vector optimizations. 3% faster overall decoding.
...
Originally committed as revision 6026 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 08:46:52 +00:00
652c59b967
use ff_fft_calc_3dn2 instead of sse on a K8.
...
1.5% faster vorbis.
Originally committed as revision 6024 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 02:42:20 +00:00
1e4ecf26f5
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
2006-08-18 23:53:49 +00:00
f4bd289a04
Explicitly include fastmemcpy.h from libvo/.
...
Originally committed as revision 6021 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-18 13:38:24 +00:00
cf5aed5bad
simplify
...
Originally committed as revision 6020 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-18 10:43:23 +00:00
0b23d689d8
Add YV12 support, patch by Steve Lhomme % steve P lhomme A free P fr %
...
Original thread:
Date: Aug 17, 2006 5:45 PM
Subject: Re: [Ffmpeg-devel] [PATCH] AVISynth support
Originally committed as revision 6018 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-18 07:55:08 +00:00
7981555d89
Move all internal -I parameters to the front of CFLAGS to avoid using external
...
header files that happen to have the same name as internal ones.
Originally committed as revision 6016 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-17 16:32:08 +00:00
2287c100b2
cleanup
...
Originally committed as revision 6007 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-17 08:08:28 +00:00
3829a62eae
insufficient alignment
...
Originally committed as revision 6006 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-17 07:49:22 +00:00
cb243ea220
10l, thanks to Emanuele Giaquinta <exg@gentoo.org> for testing and finding the issue
...
Originally committed as revision 6002 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-15 20:36:05 +00:00
696e1bb36e
Compile fix (for GCC<3.3) when encoders are disabled
...
Original thread:
Date: Aug 10, 2006 10:45 AM
Subject: [Ffmpeg-devel] [PATCH] fix compilation when Snow ENcoder is disabled
Originally committed as revision 6000 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-15 14:59:27 +00:00
241807f32d
altivec float optimizations
...
Originally committed as revision 5999 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-14 22:55:11 +00:00
94c8fbdcad
fix codec timebase and timestamps
...
Originally committed as revision 5998 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-14 18:17:14 +00:00
0f812f5291
fix h261 parsing bug
...
Originally committed as revision 5997 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-14 17:58:30 +00:00
6bb9e49249
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
2006-08-13 10:10:06 +00:00
b5f7e6eb95
Clean up:make dsputil subfile names consistent
...
Originally committed as revision 5993 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-13 08:26:43 +00:00
4454dc1b6f
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:
Date: Aug 11, 2006 8:00 AM
Subject: Re: [Ffmpeg-devel] Mac OS X Intel last part: balign directives
Originally committed as revision 5990 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-12 16:37:31 +00:00
8226ecaa6c
Fix CHECK_BIDIR macro so it works with Intel's Compiler
...
Patch by Marco Manfredini mldb A gmx P net
Originally committed as revision 5989 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-12 16:31:17 +00:00
069720565c
vorbis simd tweaks
...
Originally committed as revision 5983 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-11 18:19:37 +00:00
6b53e173cf
Disable B-frames decoding until I return and finish their proper decoding.
...
Originally committed as revision 5980 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-11 04:41:30 +00:00
876031a74e
keep in sync with dsputil, makes --disable-decoder=vorbis build
...
Originally committed as revision 5979 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-11 02:56:32 +00:00
0e0adae0ba
vorbis cosmetics: mdct0,mdct1 => mdct[2]
...
Originally committed as revision 5978 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 21:57:30 +00:00
88db1a15c5
misc tweaks in vorbis_residue_decode().
...
4% faster vorbis.
Originally committed as revision 5977 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 21:55:31 +00:00
1f1aa1d955
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
2006-08-10 20:24:58 +00:00
eb4825b5d4
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
2006-08-10 19:06:25 +00:00
60ae06e77e
r5954 broke fft on cpus with 3dnow but without mm3dnow.h
...
Originally committed as revision 5974 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 18:49:47 +00:00
ffad4ed154
Fix x86 SIMD asm and pic, patch from Martin von Gagern <Martin.vGagern@gmx.net>
...
Originally committed as revision 5973 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 16:05:29 +00:00
347be47226
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
2006-08-10 15:26:18 +00:00
0fc256f3d9
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
Originally committed as revision 5971 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 11:29:57 +00:00
fc48b6fe74
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.
Patch by John Dalgliesh % johnd AH defyne P org %
Original thread:
Date: Aug 10, 2006 8:16 AM
Subject: [Ffmpeg-devel] Mac OS X Intel part 3: binary integer constants
Originally committed as revision 5970 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-10 09:06:06 +00:00
Michael Niedermayer
Aurelien Jacobs
Baptiste Coudurier
Benjamin Larsson
Luca Abeni
Loren Merritt
Diego Biurrun
Steve L'Homme
Luca Barbato
Guillaume Poirier
Marco Manfredini
John Dalgliesh
Kostya Shishkov