3912 Commits (8c9d49f266b41895f2b500c196b97d089be271c4)

Author SHA1 Message Date
Michael Niedermayer 1d7c111856 10l 18 years ago
Michael Niedermayer faff3a7ad0 this code will not work with PIC as it needs 7 registers and gcc doesnt support that in PIC 18 years ago
Michael Niedermayer f24a515931 shift CABACContext.range right, this reduces the number of shifts needed in get_cabac() and is slightly faster on P3 (and should be much faster on P4 as the P4 except the more recent variants lacks an integer shifter and so shifts have ~10 times longer latency then simple operations like adds) 18 years ago
Ramiro Polla aa770811a3 Have xvid encoder wrapper honnor -vtag option 18 years ago
Diego Biurrun 14f29f795d Revert putting EXTRALIBS in common.mak, linking fails on MinGW. 18 years ago
Kostya Shishkov a8789714ba Ignore blocks with no samples and flags (but usually with MD5 sum) 18 years ago
Diego Biurrun 7c428ea681 Put libmpeg2 IDCT functions under CONFIG_GPL, fixes link failure 18 years ago
Steve L'Homme 8aaed74c4b Remove empty structures, 18 years ago
Kostya Shishkov ab9ce19170 Make PNG produce correct 8-bit pictures 18 years ago
Kostya Shishkov 4ec0beaa59 Move block size check to decoder 18 years ago
Michael Niedermayer b566bd65e2 simplify escape decoding 18 years ago
Diego Biurrun a88fc5c040 Remove intrinsics checks, they are no longer used. 18 years ago
Michael Niedermayer 68a205edef dehack *ps_state indexing in the branchless decoder 18 years ago
Kostya Shishkov a991b1fecb TIFF decoder 18 years ago
Michael Niedermayer 12ff5b0f3b add "memory" to the clobber list we change memory so we need it, this also fixes some problems with gcc svn 18 years ago
Michael Niedermayer 5ed0d67da5 -1 is a valid return value in ratecontrol_1pass() -> 100l for takis 18 years ago
Dominik Mierzejewski 61b769871f Fixes: 18 years ago
Michael Niedermayer de1013e1ca 10l int vs uint8_t 18 years ago
Michael Niedermayer 851ded8918 prevent "mb level" get_cabac() calls from being inlined (3% faster decode_mb_cabac() on P3) 18 years ago
Michael Niedermayer 1f6049f515 int->uint8_t for 2 tables 18 years ago
Baptiste Coudurier 29f86228a0 support for Tiertex .seq files demuxing/video decoding, by Gregory Montoir %cyx A users P sourceforge P net% 18 years ago
Gregory Montoir 7da4d4cdec fix SHOW_SBITS for ALT_BITSTREAM_READER_LE, patch by Gregory Montoir %cyx A users P sourceforge P net% 18 years ago
Diego Biurrun cb690cadaf Rename internal.h --> xvid_internal.h, it clashes with libavutil/internal.h. 18 years ago
Luca Barbato a5db5bda07 ppc generic prefetch 18 years ago
Guillaume Poirier a0490b324a adds some useful comments after some of the #else, #elseif, 18 years ago
Diego Biurrun c26abfa541 Rename ABS macro to FFABS. 18 years ago
Loren Merritt a957c27b03 more prefetches, 2% faster h264 18 years ago
Michael Niedermayer 1f4d5e9f69 slightly faster on P3 slightly slower on athlon and probably faster on P4 18 years ago
Baptiste Coudurier dc56e0de1d update doc, changelog, and increase libavcodec version for .cin files support 18 years ago
Baptiste Coudurier 72450e50a5 support for Delphine Software .cin files demuxing / audio and video decoding, by Gregory Montoir %cyx A users P sourceforge P net% 18 years ago
Michael Niedermayer 2b5269b51c moving lps state transition code a little up in the branched asm code (1% faster on P3) 18 years ago
Michael Niedermayer b99f3cabed write cabac low and range variables as early as possible to prevent stalls from reading them before they where written, the P4 is said to disslike that alot, on P3 its 2% faster (START/STOP_TIMER over decode_residual) 18 years ago
Michael Niedermayer d17faef011 use ecx instead of cl (no speed change on P3 but might avoid partial register stalls on some cpus) 18 years ago
Michael Niedermayer d61c4e731e make state transition tables global as they are constant and the code is slightly faster that way 18 years ago
Michael Niedermayer 5f3eca121e 10l 18 years ago
Michael Niedermayer 0fa352c7e6 make lps_range a global table its constant anyway (saves 1 addition for accessing it) 18 years ago
Michael Niedermayer 3650b43959 enable CMOV_IS_FAST as its faster or equal speed on every cpu (duron, athlon, PM, P3) from which ive seen benchmarks, it might be slower on P4 but noone has posted benchmarks ... 18 years ago
Michael Niedermayer 6ab312daa2 doxy 18 years ago
Diego Biurrun dadb850a50 Move CFLAGS handling to common.mak. 18 years ago
Diego Biurrun a33fe57287 Switch to the LGPL as agreed to by the author according to the 18 years ago
Kostya Shishkov 3689cf1649 Targa image decoder 18 years ago
Diego Biurrun 15e35274d8 Rename SIGN macro to the more fitting UNFOLD. 18 years ago
Diego Biurrun 0bc2e7f081 BRANCHLESS_CABAD --> BRANCHLESS_CABAC_DECODER 18 years ago
Guillaume Poirier ab5a1435ec Move TRANSPOSE8 macro to dsputil_altivec.h. 18 years ago
Michael Niedermayer 9ed92c65f1 moving another bit&1 out, this is as fast as with it in there, but it makes more sense with it outside of the loop 18 years ago
Michael Niedermayer f1b37db48d move the &1 out of the asm so gcc can optimize it away in inlined cases (yes this is slightly faster) 18 years ago
Michael Niedermayer ab0151d163 replace a few and/sub/... by cmov 18 years ago
Michael Niedermayer a6672acf45 reading 8bit mem into a 8bit register needs 2 uops on P4, 8bit->32bit with zero extension needs just 1 18 years ago
Michael Niedermayer 2d3df05ca0 on the P4 inc needs twice as much time a add 18 years ago
Michael Niedermayer 2ee9dc65be 10l 18 years ago