36d6b545a1
CMOV-ify vp56 arithcoder
...
This incantation causes gcc 4.3 to generate cmov on x86, a vastly better option
than a completely unpredictable branch.
Hopefully this carries over to newer versions and other CPUs with conditionals.
~5 cycles saved per call on a Core i7.
Originally committed as revision 23921 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 23:18:47 +00:00
2e6ed48d6e
Optimize vp56 arithmetic decoder
...
Negate "bits" to eliminate a negate in cache refilling.
Originally committed as revision 23920 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 23:15:25 +00:00
cf60d669a6
Add more int packing macros, name them consistently
...
Originally committed as revision 23916 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 22:33:38 +00:00
bce3bd1ced
renormalize VP5/6/7/8 range coder without loop
...
Originally committed as revision 23915 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 22:05:29 +00:00
0db2d3cf1d
Do not skip one of three bits zero padding.
...
Patch by Daniel Kristjansson, danielk cuymedia net
Originally committed as revision 23914 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 21:46:03 +00:00
809b7a99b2
Add missed file dct32.c
...
Originally committed as revision 23913 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 21:45:51 +00:00
06d01188e9
More mp{1,2,3} 32-point DCT transform to our common DCT framework.
...
Should allow for future SIMD optimizations.
Originally committed as revision 23912 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 20:11:27 +00:00
1782460b38
Improve av_resample() documentation
...
Originally committed as revision 23906 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 20:09:37 +00:00
49bd8e4b84
Fix grammar errors in documentation
...
Originally committed as revision 23904 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 15:38:06 +00:00
df92772c55
apedec: add flush function
...
Originally committed as revision 23900 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 09:33:59 +00:00
85b76ce990
Fix "initialization from incompatible pointer type" warning in rv34.
...
Patch by Eli Friedman (at gmail).
Originally committed as revision 23897 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 06:50:44 +00:00
25fe863062
Silense one warning:
...
"passing argument 1 of ‘av_memcpy_backptr’ from incompatible pointer type"
Patch by Eli Friedman, eli D friedman A gmail
Originally committed as revision 23895 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 01:57:05 +00:00
99267eb702
Fix strict-aliasing violations in MPV_motion_internal.
...
Patch by Eli Friedman, eli D friedman A gmail
Originally committed as revision 23894 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-30 01:47:42 +00:00
dd8e127a4d
rv40: make rv40_adaptive_loop_filter() always_inline
...
This function is called from the rv40_[hv]_loop_filter() wrappers
with some arguments constant, so it really needs to be inlined.
3% faster overall on Cortex-A8.
Originally committed as revision 23893 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 22:41:22 +00:00
82a8d0f114
Use add instead of lshift in mmxext vp8 idct
...
Originally committed as revision 23891 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 17:23:17 +00:00
565344e7e4
Remove unused macros (duplicates from the now-LGPL x86util.asm).
...
Originally committed as revision 23890 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 17:04:29 +00:00
cbb39648c1
Add CRC check to the ALS decoder.
...
Originally committed as revision 23889 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 16:56:28 +00:00
a4edc5a9df
ARM: add mov32 macro
...
Originally committed as revision 23888 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 14:48:45 +00:00
480cb7edd3
ARM: (mostly) whitespace cosmetics
...
Originally committed as revision 23887 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 14:48:41 +00:00
2dd2f71692
MMX idct_add for VP8.
...
Originally committed as revision 23886 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 14:43:11 +00:00
29e719377f
Add missing mm_support call toff_h264_pred_init_x86.
...
I'm not sure if this is supposed to be here, but it can't hurt.
Originally committed as revision 23885 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 12:28:06 +00:00
982fac7357
Altivec VP8 MC functions
...
Originally committed as revision 23884 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 06:42:17 +00:00
7bf4e9d7f7
Altivec: Add helper function to load from a constant misalignment
...
Originally committed as revision 23883 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 06:42:12 +00:00
a3ef994cea
vorbis: cosmetics, remove trailing comma for values that will never have
...
anything added
Originally committed as revision 23882 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 06:42:08 +00:00
95275094a5
Faster C VP8 normal inner loop filter
...
Originally committed as revision 23881 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 04:34:04 +00:00
9942b6a1b0
Use crop table in C implementations of VP8 DSP functions.
...
Much faster VP8 C DSP functions; ~5-10% faster overall with asm off.
Originally committed as revision 23880 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 03:34:24 +00:00
004cda8e79
Add mmxext version of VP8 DC Hadamard transform
...
Originally committed as revision 23878 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 01:41:59 +00:00
37355fe823
Make x86util.asm LGPL so we can use it in LGPL asm
...
Strip out most x264-specific stuff (not used anywhere in ffmpeg).
Originally committed as revision 23877 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 00:40:12 +00:00
bc14f04b2f
MMXEXT version of vp8 4x4 vertical pred
...
Originally committed as revision 23876 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-29 00:23:52 +00:00
fb9927ad7d
Add mmx/mmxext/ssse3 4x4 TM intra pred functions for vp8
...
Originally committed as revision 23875 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 23:53:07 +00:00
8b746bb473
Add missing comment header for predict_4x4_dc_mmxext
...
Originally committed as revision 23874 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 23:37:24 +00:00
270a85d259
Fix some intra pred MMX functions that used MMXEXT instructions
...
Also add predict_4x4_dc MMXEXT function for vp8/h264.
Originally committed as revision 23873 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 23:35:17 +00:00
a912da761d
Fix VP8 bilinear mc on x86_64
...
Originally committed as revision 23872 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 22:13:14 +00:00
4e42debc8d
aacenc: Start the lookahead pointer 1/4 of the way into the first short window.
...
Short windows are of length 256 and begin at sample 448.
Originally committed as revision 23871 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:50:57 +00:00
75ef689884
aacenc: Fix window decision logic.
...
This keeps the encoder from switching away from an wight short sequence
prematurely when attacks are detected two frames in a row. It also allows for
the legal and useful LONG_STOP_SEQUENCE to LONG_START_SEQUENCE transition.
Originally committed as revision 23870 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:49:26 +00:00
804d489c4a
aacenc: Fill in the estimated codebook for the final computed scalefactor in the TLS.
...
Originally committed as revision 23869 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:42:57 +00:00
7ca4a72f47
10l: Revert r23867. It didn't make any sense.
...
Originally committed as revision 23868 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:40:38 +00:00
9a3fe1ae6e
Make ff_psy_preprocess_end() act like av_freep().
...
Originally committed as revision 23867 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:36:19 +00:00
072c0d605f
aacenc: Properly pad extradata.
...
This fixes a valgrind error when encoding to ADTS.
Originally committed as revision 23866 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:34:57 +00:00
50f70541d3
Change MMXEXT to MMX2, MMXEXT is deprecated
...
Originally committed as revision 23865 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 21:12:00 +00:00
0fecad09fe
Add x86 asm functions for VP8 put_pixels
...
Originally committed as revision 23858 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 19:14:40 +00:00
a173aa8940
Add MMX, SSE2, SSSE3 asm for VP8 bilinear MC
...
Originally committed as revision 23857 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 18:56:24 +00:00
7ed06b2be8
Simplify MV parsing, removes laying out 2 or 4 (16x8/8x8/8x16) MVs over all
...
16 subblocks (since we no longer need that), which should also lead to a
minor speedup.
Originally committed as revision 23854 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 16:04:14 +00:00
7c4dcf8165
Optimize split MC, so we don't always do 4x4 blocks of 4x4pixels each, but
...
we apply them as 16x8/8x16/8x8 subblocks where possible. Since this allows
us to use width=8/16 instead of width=4 MC functions, we can now take more
advantage of SSE2/SSSE3 optimizations, leading to a total speedup for splitMV
filter of about 10%.
Originally committed as revision 23853 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 13:50:55 +00:00
eca9e4035a
Set rv34 (0,0) subpel mc functions to the optimised h264 ones
...
Originally committed as revision 23845 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 10:56:16 +00:00
1f65b67c46
Fix x86 build with h264dsp disabled
...
Originally committed as revision 23844 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 10:02:15 +00:00
186d02150e
Use lookup table to avoid division in mp2 decoder
...
Originally committed as revision 23840 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-28 04:55:36 +00:00
a64fadf62b
Fix linking if MMX is disabled.
...
Originally committed as revision 23839 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-27 23:25:04 +00:00
7447204d2d
vaapi: add missing #include "h263.h"
...
Originally committed as revision 23833 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-27 20:18:28 +00:00
0b37cccaab
ra288: convert VLAs to fixed size
...
Originally committed as revision 23832 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-06-27 19:30:31 +00:00
Jason Garrett-Glaser
Måns Rullgård
Stefan Gehrer
Daniel Kristjansson
Vitor Sessak
Eli Friedman
Ronald S. Bultje
Thilo Borgmann
David Conrad
Alex Converse
Baptiste Coudurier
Stefano Sabatini