Commit Graph

3522 Commits

Author SHA1 Message Date
Michael Niedermayer
d37bb9d8c1 10l found by valgrind
Originally committed as revision 6099 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 15:24:13 +00:00
Michael Niedermayer
06e7fb82a4 remove duplicated parser, people who pass random gibblets of the bitstream into the decoder will have to pass it through a AVParser like for all other codecs too
remove silly internal buffering architecture (removes 1 memcpy() of the bitstream)
mp3on4 and mp3adu untested

Originally committed as revision 6098 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 12:19:05 +00:00
Michael Niedermayer
6e4703cac7 2nd try of skip_bits_long() for the ALT reader
1st try for the LIBMPEG2 reader
simplify init_get_bits()

Originally committed as revision 6097 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 11:50:23 +00:00
Michael Niedermayer
a42ec9f484 make A32 reader align its ptr during init no matter what missaligned mess is given to it
Originally committed as revision 6096 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 11:37:33 +00:00
Michael Niedermayer
3dddf21fcc 3rd try :)
Originally committed as revision 6095 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 11:26:54 +00:00
Michael Niedermayer
1491e21cdb 2nd try for a skip_bits_long() for the A32 reader
Originally committed as revision 6094 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 11:06:33 +00:00
Michael Niedermayer
5a7bd28335 move align_get_bits() to .h to avoid conflicts between different bitstream readers in different codecs
add a skip_bits_long() which can skip by any amount in any direction (several codecs contain half working hacks to do that)

Originally committed as revision 6093 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 10:26:14 +00:00
Michael Niedermayer
727c236a6b prevent bitstream reader to be overriden
Originally committed as revision 6092 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-26 09:34:02 +00:00
Michael Niedermayer
9bffa9e7af avoid branch
Originally committed as revision 6088 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 14:42:32 +00:00
Michael Niedermayer
14168ddb28 move variable declarations so that their scope is smaller
Originally committed as revision 6087 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 13:58:27 +00:00
Michael Niedermayer
bc2d2757bb move the +400 out of the innermost loop
Originally committed as revision 6086 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 13:46:56 +00:00
Michael Niedermayer
9b49f89cdf avoid reading exponent twice
Originally committed as revision 6085 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 13:36:27 +00:00
Michael Niedermayer
1f1d675b68 reduce size of vlc table, thats slightly faster here
Originally committed as revision 6084 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 12:26:34 +00:00
Michael Niedermayer
55017f35da try to avoid l3_unscale() by using a table
Originally committed as revision 6083 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 11:55:20 +00:00
Michael Niedermayer
f8347c4167 replace l3_unscale(1, exponents[pos]) by LUT
Originally committed as revision 6082 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 10:00:30 +00:00
Michael Niedermayer
7ca1ed0d9c maybe fixing the segfault on ARM
Originally committed as revision 6081 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-25 02:40:52 +00:00
Aurelien Jacobs
5902bdd8d4 cook shouldn't try to enforce the bitstream reader type
Originally committed as revision 6080 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 21:59:20 +00:00
Baptiste Coudurier
f31065f6e5 add codec id and tag for JPEG 2000
Originally committed as revision 6076 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 14:13:57 +00:00
Michael Niedermayer
92c5cb62b0 10l typo
Originally committed as revision 6074 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 12:35:53 +00:00
Michael Niedermayer
e90a72701e avoid a few if(x==0) checks in the inner loops
Originally committed as revision 6073 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 11:18:41 +00:00
Michael Niedermayer
25be48eb48 fix non ALT bitstream reader
Originally committed as revision 6070 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 09:24:50 +00:00
Michael Niedermayer
6430ce0f72 optimize reorder_block() though this function seems to be executed too rarely for this to make much difference
Originally committed as revision 6068 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 08:40:09 +00:00
Michael Niedermayer
a753e55bb5 simplify
Originally committed as revision 6067 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-24 08:39:07 +00:00
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
c7aa36964e simplify
Originally committed as revision 6058 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-23 23:40:03 +00:00
Aurelien Jacobs
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
Baptiste Coudurier
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
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
5ab1972b53 indent preprocessor directives
Originally committed as revision 6047 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-22 11:16:47 +00:00
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
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
Michael Niedermayer
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
Benjamin Larsson
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
Michael Niedermayer
ed567d9c41 cosmetics
Originally committed as revision 6032 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 23:12:10 +00:00
Michael Niedermayer
67eca72dc0 SWAP
Originally committed as revision 6030 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-19 20:55:02 +00:00
Michael Niedermayer
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
Luca Abeni
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
Benjamin Larsson
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
Loren Merritt
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
Loren Merritt
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
Diego Biurrun
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
Michael Niedermayer
cf5aed5bad simplify
Originally committed as revision 6020 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-08-18 10:43:23 +00:00
Steve L'Homme
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
Diego Biurrun
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