summaryrefslogtreecommitdiff
path: root/libavcodec
Commit message (Collapse)AuthorAge
* cosmetic: improve comment breaking at 80 colsAurelien Jacobs2010-07-01
| | | | Originally committed as revision 23938 to svn://svn.ffmpeg.org/ffmpeg/trunk
* fix dependencies of vp5 and vp6 decoders after r23915Aurelien Jacobs2010-07-01
| | | | | | they now also depends on cabac.o for ff_h264_norm_shift Originally committed as revision 23937 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Maybe fix threaded mpeg*video encodingMåns Rullgård2010-07-01
| | | | | | | This allocates per-thread copies of some MpegEncContext.ac_val which is used concurrently from the encoding threads. Originally committed as revision 23933 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix h264/vp8 intra pred on Athlon XPJason Garrett-Glaser2010-07-01
| | | | | | Whose idea was it to have a CPU that didn't SIGILL on an invalid instruction? Originally committed as revision 23927 to svn://svn.ffmpeg.org/ffmpeg/trunk
* mpegaudioenc: Remove write-only variables from the context.Rafaël Carré2010-07-01
| | | | | | Patch by Rafaël Carré (rafael <dot> carre <at> gmail). Originally committed as revision 23926 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Eliminate another redundant instruction in vp56/8 arithcoderJason Garrett-Glaser2010-06-30
| | | | | | | | | | | | | Necessary because of this GCC bug: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=44474 To do this, convert some, but not all (!) of the variables in VP56RangeCoder into local variables. If we convert c->high into a local variable, gcc gets the stupids and refuses to use a conditional move for the unpredictable main branch. TODO: dispense with this bullshit and write an asm version. Originally committed as revision 23924 to svn://svn.ffmpeg.org/ffmpeg/trunk
* CMOV-ify vp56 arithcoderJason Garrett-Glaser2010-06-30
| | | | | | | | | 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
* Optimize vp56 arithmetic decoderJason Garrett-Glaser2010-06-30
| | | | | | Negate "bits" to eliminate a negate in cache refilling. Originally committed as revision 23920 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add more int packing macros, name them consistentlyMåns Rullgård2010-06-30
| | | | Originally committed as revision 23916 to svn://svn.ffmpeg.org/ffmpeg/trunk
* renormalize VP5/6/7/8 range coder without loopStefan Gehrer2010-06-30
| | | | Originally committed as revision 23915 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Do not skip one of three bits zero padding.Daniel Kristjansson2010-06-30
| | | | | | Patch by Daniel Kristjansson, danielk cuymedia net Originally committed as revision 23914 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add missed file dct32.cMåns Rullgård2010-06-30
| | | | Originally committed as revision 23913 to svn://svn.ffmpeg.org/ffmpeg/trunk
* More mp{1,2,3} 32-point DCT transform to our common DCT framework.Vitor Sessak2010-06-30
| | | | | | Should allow for future SIMD optimizations. Originally committed as revision 23912 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Improve av_resample() documentationMåns Rullgård2010-06-30
| | | | Originally committed as revision 23906 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix grammar errors in documentationMåns Rullgård2010-06-30
| | | | Originally committed as revision 23904 to svn://svn.ffmpeg.org/ffmpeg/trunk
* apedec: add flush functionMåns Rullgård2010-06-30
| | | | Originally committed as revision 23900 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix "initialization from incompatible pointer type" warning in rv34.Eli Friedman2010-06-30
| | | | | | Patch by Eli Friedman (at gmail). Originally committed as revision 23897 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Silense one warning:Eli Friedman2010-06-30
| | | | | | | | "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
* Fix strict-aliasing violations in MPV_motion_internal.Eli Friedman2010-06-30
| | | | | | Patch by Eli Friedman, eli D friedman A gmail Originally committed as revision 23894 to svn://svn.ffmpeg.org/ffmpeg/trunk
* rv40: make rv40_adaptive_loop_filter() always_inlineMåns Rullgård2010-06-29
| | | | | | | | | 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
* Use add instead of lshift in mmxext vp8 idctJason Garrett-Glaser2010-06-29
| | | | Originally committed as revision 23891 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove unused macros (duplicates from the now-LGPL x86util.asm).Ronald S. Bultje2010-06-29
| | | | Originally committed as revision 23890 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add CRC check to the ALS decoder.Thilo Borgmann2010-06-29
| | | | Originally committed as revision 23889 to svn://svn.ffmpeg.org/ffmpeg/trunk
* ARM: add mov32 macroMåns Rullgård2010-06-29
| | | | Originally committed as revision 23888 to svn://svn.ffmpeg.org/ffmpeg/trunk
* ARM: (mostly) whitespace cosmeticsMåns Rullgård2010-06-29
| | | | Originally committed as revision 23887 to svn://svn.ffmpeg.org/ffmpeg/trunk
* MMX idct_add for VP8.Ronald S. Bultje2010-06-29
| | | | Originally committed as revision 23886 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add missing mm_support call toff_h264_pred_init_x86.Jason Garrett-Glaser2010-06-29
| | | | | | 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
* Altivec VP8 MC functionsDavid Conrad2010-06-29
| | | | Originally committed as revision 23884 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Altivec: Add helper function to load from a constant misalignmentDavid Conrad2010-06-29
| | | | Originally committed as revision 23883 to svn://svn.ffmpeg.org/ffmpeg/trunk
* vorbis: cosmetics, remove trailing comma for values that will never haveDavid Conrad2010-06-29
| | | | | | anything added Originally committed as revision 23882 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Faster C VP8 normal inner loop filterJason Garrett-Glaser2010-06-29
| | | | Originally committed as revision 23881 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Use crop table in C implementations of VP8 DSP functions.Jason Garrett-Glaser2010-06-29
| | | | | | 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
* Add mmxext version of VP8 DC Hadamard transformJason Garrett-Glaser2010-06-29
| | | | Originally committed as revision 23878 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Make x86util.asm LGPL so we can use it in LGPL asmJason Garrett-Glaser2010-06-29
| | | | | | Strip out most x264-specific stuff (not used anywhere in ffmpeg). Originally committed as revision 23877 to svn://svn.ffmpeg.org/ffmpeg/trunk
* MMXEXT version of vp8 4x4 vertical predJason Garrett-Glaser2010-06-29
| | | | Originally committed as revision 23876 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add mmx/mmxext/ssse3 4x4 TM intra pred functions for vp8Jason Garrett-Glaser2010-06-28
| | | | Originally committed as revision 23875 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add missing comment header for predict_4x4_dc_mmxextJason Garrett-Glaser2010-06-28
| | | | Originally committed as revision 23874 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix some intra pred MMX functions that used MMXEXT instructionsJason Garrett-Glaser2010-06-28
| | | | | | Also add predict_4x4_dc MMXEXT function for vp8/h264. Originally committed as revision 23873 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix VP8 bilinear mc on x86_64Jason Garrett-Glaser2010-06-28
| | | | Originally committed as revision 23872 to svn://svn.ffmpeg.org/ffmpeg/trunk
* aacenc: Start the lookahead pointer 1/4 of the way into the first short window.Alex Converse2010-06-28
| | | | | | Short windows are of length 256 and begin at sample 448. Originally committed as revision 23871 to svn://svn.ffmpeg.org/ffmpeg/trunk
* aacenc: Fix window decision logic.Alex Converse2010-06-28
| | | | | | | | 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
* aacenc: Fill in the estimated codebook for the final computed scalefactor in ↵Alex Converse2010-06-28
| | | | | | the TLS. Originally committed as revision 23869 to svn://svn.ffmpeg.org/ffmpeg/trunk
* 10l: Revert r23867. It didn't make any sense.Alex Converse2010-06-28
| | | | Originally committed as revision 23868 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Make ff_psy_preprocess_end() act like av_freep().Alex Converse2010-06-28
| | | | Originally committed as revision 23867 to svn://svn.ffmpeg.org/ffmpeg/trunk
* aacenc: Properly pad extradata.Alex Converse2010-06-28
| | | | | | This fixes a valgrind error when encoding to ADTS. Originally committed as revision 23866 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Change MMXEXT to MMX2, MMXEXT is deprecatedBaptiste Coudurier2010-06-28
| | | | Originally committed as revision 23865 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add x86 asm functions for VP8 put_pixelsJason Garrett-Glaser2010-06-28
| | | | Originally committed as revision 23858 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add MMX, SSE2, SSSE3 asm for VP8 bilinear MCJason Garrett-Glaser2010-06-28
| | | | Originally committed as revision 23857 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify MV parsing, removes laying out 2 or 4 (16x8/8x8/8x16) MVs over allRonald S. Bultje2010-06-28
| | | | | | | 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
* Optimize split MC, so we don't always do 4x4 blocks of 4x4pixels each, butRonald S. Bultje2010-06-28
| | | | | | | | | 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
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-29 19:09:56 +0000