| Age | Commit message (Expand) | Author |
|---|
| 2006-10-19 | optimize sign decoding code in decode_residual() | Michael Niedermayer |
| 2006-10-18 | Kill a warning with MSVC | Jindřich Makovička |
| 2006-10-18 | x86 asm version of the decode significance loop (not 8x8) of decode_residual(... | Michael Niedermayer |
| 2006-10-17 | cosmetic (%%eax->%0) | Michael Niedermayer |
| 2006-10-17 | Fix crash with illegal instruction, cmov is available on 686 and later only. | Diego Biurrun |
| 2006-10-17 | Expand some #endif comments. | Diego Biurrun |
| 2006-10-16 | fix !CMOV_IS_FAST case (iam not really happy with the fix but i didnt come up... | Michael Niedermayer |
| 2006-10-16 | 10l | Michael Niedermayer |
| 2006-10-16 | this code will not work with PIC as it needs 7 registers and gcc doesnt suppo... | Michael Niedermayer |
| 2006-10-16 | shift CABACContext.range right, this reduces the number of shifts needed in g... | Michael Niedermayer |
| 2006-10-13 | dehack *ps_state indexing in the branchless decoder | Michael Niedermayer |
| 2006-10-13 | add "memory" to the clobber list we change memory so we need it, this also fi... | Michael Niedermayer |
| 2006-10-12 | prevent "mb level" get_cabac() calls from being inlined (3% faster decode_mb_... | Michael Niedermayer |
| 2006-10-12 | adds some useful comments after some of the #else, #elseif, | Guillaume Poirier |
| 2006-10-12 | Rename ABS macro to FFABS. | Diego Biurrun |
| 2006-10-11 | slightly faster on P3 slightly slower on athlon and probably faster on P4 | Michael Niedermayer |
| 2006-10-11 | moving lps state transition code a little up in the branched asm code (1% fas... | Michael Niedermayer |
| 2006-10-11 | write cabac low and range variables as early as possible to prevent stalls fr... | Michael Niedermayer |
| 2006-10-11 | use ecx instead of cl (no speed change on P3 but might avoid partial register... | Michael Niedermayer |
| 2006-10-11 | make state transition tables global as they are constant and the code is slig... | Michael Niedermayer |
| 2006-10-11 | 10l | Michael Niedermayer |
| 2006-10-11 | make lps_range a global table its constant anyway (saves 1 addition for acces... | Michael Niedermayer |
| 2006-10-11 | enable CMOV_IS_FAST as its faster or equal speed on every cpu (duron, athlon,... | Michael Niedermayer |
| 2006-10-10 | BRANCHLESS_CABAD --> BRANCHLESS_CABAC_DECODER | Diego Biurrun |
| 2006-10-10 | moving another bit&1 out, this is as fast as with it in there, but it makes m... | Michael Niedermayer |
| 2006-10-10 | move the &1 out of the asm so gcc can optimize it away in inlined cases (yes ... | Michael Niedermayer |
| 2006-10-10 | replace a few and/sub/... by cmov | Michael Niedermayer |
| 2006-10-10 | reading 8bit mem into a 8bit register needs 2 uops on P4, 8bit->32bit with ze... | Michael Niedermayer |
| 2006-10-10 | on the P4 inc needs twice as much time a add | Michael Niedermayer |
| 2006-10-10 | 10l | Michael Niedermayer |
| 2006-10-10 | reverse remainder of the failed attempt to optimize *state=c->mps_state[s] | Michael Niedermayer |
| 2006-10-10 | x86 branchless cabac decoder | Michael Niedermayer |
| 2006-10-10 | optimize branchless C CABAC decoder | Michael Niedermayer |
| 2006-10-09 | move outcommented START/STOP_TIMER to a hopefully better place for benchmarki... | Michael Niedermayer |
| 2006-10-09 | drop failed attempt to optimize *state= c->mps_state[s]; | Michael Niedermayer |
| 2006-10-09 | 10l bugfix for some disabled code | Michael Niedermayer |
| 2006-10-09 | first try of a handwritten get_cabac() for x86, this is 10-20% faster on P3 d... | Michael Niedermayer |
| 2006-10-09 | remove bytestream_end checks, seems to work fine without them and the bitstre... | Michael Niedermayer |
| 2006-10-09 | decrease ff_h264_norm_shift[] size | Michael Niedermayer |
| 2006-10-09 | cleanup | Michael Niedermayer |
| 2006-10-08 | branchless renormalization (1% faster get_cabac) old branchless renormalizati... | Michael Niedermayer |
| 2006-10-08 | 5% faster get_cabac() | Michael Niedermayer |
| 2006-10-08 | disable benchmarking code | Michael Niedermayer |
| 2006-10-08 | renorm_cabac_decoder_once START/STOP_TIMER scores for athlon | Michael Niedermayer |
| 2006-10-07 | refill cabac variables in 16bit steps, 3% faster get_cabac() | Michael Niedermayer |
| 2006-10-07 | Change license headers to say 'FFmpeg' instead of 'this program/this library' | Diego Biurrun |
| 2006-10-07 | () 10l | Michael Niedermayer |
| 2006-10-07 | several x86 renorm_cabac_decoder_once optimizations | Michael Niedermayer |
| 2006-10-04 | don't try to inline cabac functions. gcc ignored the hint anyway, and forcing... | Loren Merritt |
| 2006-08-27 | tweak cabac. 0.5% faster h264. | Loren Merritt |
