aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/h264.c
Commit message (Collapse)AuthorAgeFilesLines
* export refsMichael Niedermayer2008-12-241-0/+2
| | | | Originally committed as revision 16306 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Optimize pred_pskip_motion()Michael Niedermayer2008-12-241-2/+2
| | | | | | 7 cpu cycles faster on pentium dual. Originally committed as revision 16304 to svn://svn.ffmpeg.org/ffmpeg/trunk
* IndentMichael Niedermayer2008-12-231-19/+19
| | | | Originally committed as revision 16302 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Integrate get_te0_golomb() calls into the code, this allows some checksMichael Niedermayer2008-12-231-4/+29
| | | | | | | | to be avoided and the function is pretty small. 3% speedup, though this is probably due to changed inlining and not directly this change. Originally committed as revision 16301 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Use get_ue_golomb_31() where possible, almost all are just in headersMichael Niedermayer2008-12-231-15/+15
| | | | | | though. Originally committed as revision 16300 to svn://svn.ffmpeg.org/ffmpeg/trunk
* indentMichael Niedermayer2008-12-231-21/+21
| | | | Originally committed as revision 16296 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Use the new VLC table for the first non trailing coeff too.Michael Niedermayer2008-12-231-5/+18
| | | | | | | Sadly only 5 cycles faster here on pentium dual. So maybe the complexity is not worth it and this should be reverted ... Originally committed as revision 16295 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Optimize esc removal code.Michael Niedermayer2008-12-231-4/+11
| | | | Originally committed as revision 16294 to svn://svn.ffmpeg.org/ffmpeg/trunk
* IndentMichael Niedermayer2008-12-231-8/+8
| | | | Originally committed as revision 16292 to svn://svn.ffmpeg.org/ffmpeg/trunk
* unified CAVLC level decoding LUT.Michael Niedermayer2008-12-231-4/+45
| | | | | | Quite a bit faster (HPCVMOLQ_BRCM_B.264 was 3% faster here) Originally committed as revision 16291 to svn://svn.ffmpeg.org/ffmpeg/trunk
* 100l, I broke H.264 again, forgot one hunk.Michael Niedermayer2008-12-231-0/+1
| | | | | | Thanks to FATE for finding it. Originally committed as revision 16285 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Optimize 0 0 0-3 search, 45% faster on pentium dual.Michael Niedermayer2008-12-231-0/+17
| | | | Originally committed as revision 16284 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify decode_cabac_mb_ref() a little bit, 2 cpu cycles faster onMichael Niedermayer2008-12-221-4/+1
| | | | | | pentium dual. Originally committed as revision 16279 to svn://svn.ffmpeg.org/ffmpeg/trunk
* IndentMichael Niedermayer2008-12-221-7/+7
| | | | Originally committed as revision 16278 to svn://svn.ffmpeg.org/ffmpeg/trunk
* inline decode_cabac_mb_type for I & P frames, 9 cycles faster on pentium dual.Michael Niedermayer2008-12-221-22/+13
| | | | Originally committed as revision 16277 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Negate 2 more variables, 1 cpu cycle faster on pentium dual.Michael Niedermayer2008-12-221-5/+5
| | | | Originally committed as revision 16276 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify if/else, no speed changeMichael Niedermayer2008-12-221-5/+1
| | | | Originally committed as revision 16275 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Negate a few variables, this simplifies the code and makes it 5 cycles fasterMichael Niedermayer2008-12-221-15/+15
| | | | | | on pentium dual. Originally committed as revision 16274 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify ifs(), 8 cpu cycles faster on pentium dualMichael Niedermayer2008-12-221-12/+4
| | | | Originally committed as revision 16273 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify if(), 3 cpu cycles faster in pentium dual.Michael Niedermayer2008-12-221-4/+2
| | | | Originally committed as revision 16272 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Rename libavcodec/i386/ --> libavcodec/x86/.Diego Biurrun2008-12-221-1/+1
| | | | | | | It contains optimizations that are not specific to i386 and libavutil uses this naming scheme already. Originally committed as revision 16270 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove a bunch of unused variables.Diego Biurrun2008-12-221-5/+0
| | | | Originally committed as revision 16263 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove useless code.Michael Niedermayer2008-12-211-4/+2
| | | | Originally committed as revision 16253 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Only execute clear_blocks() when needed.Michael Niedermayer2008-12-211-4/+3
| | | | | | +0.3% speedup for both aladin & cathedral. Originally committed as revision 16252 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Optimize get_dct8x8_allowed().Michael Niedermayer2008-12-201-7/+4
| | | | | | 30 cpu cycles faster on pentium dual. Originally committed as revision 16248 to svn://svn.ffmpeg.org/ffmpeg/trunk
* H.264 loopfilter speed tweaksJason Garrett-Glaser2008-12-191-10/+18
| | | | Originally committed as revision 16240 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix decoding with the plain C idcts ofMichael Niedermayer2008-12-191-0/+2
| | | | | | | | FRExt/HPCAMOLQ_BRCM_B FRExt/HPCAQ2LQ_BRCM_B FRExt/HPCVMOLQ_BRCM_B Originally committed as revision 16236 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Replace /2 by >>1 in decode_cabac_mb_dqp()Michael Niedermayer2008-12-191-2/+2
| | | | | | 3 cpu cycles speed up on pentium dual. Originally committed as revision 16233 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify ctx update in decode_cabac_mb_dqp().Michael Niedermayer2008-12-191-4/+1
| | | | | | no speed change Originally committed as revision 16232 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify ctx calculation in decode_cabac_mb_dqp()Michael Niedermayer2008-12-191-4/+1
| | | | | | no speed change Originally committed as revision 16231 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Clear FF_INPUT_BUFFER_PADDING_SIZE bytes at the end of NALs in rbsp_buffer.Alexander Strange2008-12-191-1/+3
| | | | | | | Fixes valgrind uninitialized value warnings at the end of decoding H.264 frames. Originally committed as revision 16230 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Move filter_luma_intra into dsputil for later addition of asm.Jason Garrett-Glaser2008-12-191-91/+2
| | | | Originally committed as revision 16228 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify chroma AC in CABAC residual decoding.Jason Garrett-Glaser2008-12-191-19/+8
| | | | Originally committed as revision 16227 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Optimize ctx calculation in decode_cabac_mb_mvd(), code by dark shikari.Michael Niedermayer2008-12-191-8/+2
| | | | | | | The case for 16x16 blocks becomes 10 cpu cycles faster on pentium dual, i could not find a speed difference in the case of subblocks though. Originally committed as revision 16226 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove unacceptable NULL pointer hack from mc code.Michael Niedermayer2008-12-181-3/+0
| | | | Originally committed as revision 16225 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Check ref values in CABAC H.264 for validity.Michael Niedermayer2008-12-181-7/+34
| | | | Originally committed as revision 16224 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Move idct_(dc)add closer to where it is needed.Michael Niedermayer2008-12-181-3/+3
| | | | Originally committed as revision 16223 to svn://svn.ffmpeg.org/ffmpeg/trunk
* indentMichael Niedermayer2008-12-181-36/+36
| | | | Originally committed as revision 16222 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Reorder ifs in chroma hl_decode_mb to avoid a duplicate transform_bypassMichael Niedermayer2008-12-181-7/+11
| | | | | | | check. 14 cpu cycles speedup on Pentium Dual Originally committed as revision 16221 to svn://svn.ffmpeg.org/ffmpeg/trunk
* s/h->cbp_table[mb_xy]/h->cbp/Michael Niedermayer2008-12-181-4/+4
| | | | Originally committed as revision 16220 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Faster CAVLC decoding of trailing_ones. Based on a patch by dark shikari.Michael Niedermayer2008-12-181-3/+5
| | | | | | decode_residual is about 3.3% faster. Originally committed as revision 16219 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Replace i by trailing_ones, part of a patch by dark shikari.Jason Garrett-Glaser2008-12-181-4/+3
| | | | | | | No speed change meassureable with START/STOP_TIMER, but this is needed for future optimizations. Originally committed as revision 16218 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove if() surrounding decode_cabac_mb_type() that can never be true.Michael Niedermayer2008-12-181-4/+2
| | | | Originally committed as revision 16217 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove unreachable else clause, found by dark shikari.Michael Niedermayer2008-12-181-4/+2
| | | | Originally committed as revision 16216 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove useless IS_8x8DCT check i forgot, spotted by dark shikari.Michael Niedermayer2008-12-181-1/+1
| | | | Originally committed as revision 16215 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Do not calculate idct_dc_add/idct_add when the variables are unused.Michael Niedermayer2008-12-181-13/+18
| | | | Originally committed as revision 16210 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove redundant nnz variable.Michael Niedermayer2008-12-181-2/+1
| | | | Originally committed as revision 16209 to svn://svn.ffmpeg.org/ffmpeg/trunk
* indentMichael Niedermayer2008-12-181-11/+11
| | | | Originally committed as revision 16208 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Use the new idct functions (except chroma as it was slower in benchmarks)Michael Niedermayer2008-12-181-7/+14
| | | | | | | | | | cathedral +0.5% speed aladin +0.6% speed [note aladin has been cat-ed 10 times to reduce the influence of init time] Speedup also verified via START/STOP_TIMER (difference was very significant for the changed parts) Originally committed as revision 16207 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Skip non intra luma code when there is no coded luma.Michael Niedermayer2008-12-181-1/+1
| | | | | | 0.7% speedup for the cathedral sample. Originally committed as revision 16203 to svn://svn.ffmpeg.org/ffmpeg/trunk
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-06 16:37:44 +0000