summaryrefslogtreecommitdiff
path: root/libavcodec/i386
Commit message (Expand)AuthorAgeFilesLines
* #define SBUTTERFLY outside CONFIG_ENCODERSMåns Rullgård2006-07-051-5/+5
* Move REG_* macros from libavcodec/i386/mmx.h to libavutil/x86_cpu.hLuca Abeni2006-07-035-21/+4
* remove redundant macro definitionsMåns Rullgård2006-07-021-6/+0
* kill warningMåns Rullgård2006-07-021-0/+1
* missmatch control for mpeg2 intra dequantization if bitexact=1Michael Niedermayer2006-04-281-1/+2
* Remove unused and unsupported Cyrix's "Extended MMX",Zuxy Meng2006-04-281-30/+4
* gcc-2.95 compile fix, patch by Wolfram Gloger <wmglo A dent PIS med PIS uni-m...Wolfram Gloger2006-04-181-2/+2
* gmc_mmx tweaksLoren Merritt2006-04-051-13/+11
* mmx implementation of 3-point GMC. (5x faster than C)Loren Merritt2006-04-041-0/+122
* altivec support for snowLuca Barbato2006-03-271-29/+0
* simplified and slightly faster h264_chroma_mc8_mmxLoren Merritt2006-03-251-128/+68
* prefetch pixels for future motion compensation. 2-5% faster h264.Loren Merritt2006-03-231-0/+16
* 10lLoren Merritt2006-03-221-1/+1
* added mmx implementation of h264_chroma_mc2Loren Merritt2006-03-223-1/+70
* add MMX and SSE versions of ff_snow_inner_add_yblockRobert Edele2006-03-222-0/+297
* snow mmx+sse2 optimizations, part 4Robert Edele2006-03-212-0/+412
* Add the mmx and sse2 implementations of ff_snow_vertical_compose().Robert Edele2006-03-202-0/+261
* First part of a series of speed-enchancing patches.Robert Edele2006-03-161-0/+2
* 3DNow! & Extended 3DNow! versions of FFTZuxy Meng2006-03-082-0/+272
* h264_idct8_add_mmxLoren Merritt2006-03-072-0/+129
* h264_idct_add only needs mmx1Loren Merritt2006-03-072-4/+6
* use xorps instead of mulps to toggle the sign of a float, as suggested by Sof...Zuxy Meng2006-03-051-10/+10
* gcc2.95 workaroundLoren Merritt2006-03-051-22/+24
* remove some useless instructionsLoren Merritt2006-03-041-18/+4
* 4% faster h264_qpel_mcLoren Merritt2006-03-021-40/+137
* h264: special case dc-only idct. ~1% faster overallLoren Merritt2006-02-102-0/+83
* 10l in 1.12Loren Merritt2006-02-091-6/+6
* 10l (x86_64)Loren Merritt2006-02-071-1/+1
* 18% faster put_h264_qpel16_mc[13]2_mmx2Loren Merritt2006-02-071-14/+87
* 11% faster put_h264_qpel16_v_lowpass_mmx2Loren Merritt2006-02-071-11/+27
* 15% faster put_h264_qpel16_hv_lowpass_mmx2Loren Merritt2006-02-071-26/+45
* MSVC-compatible __align8/__align16 declarationSteve L'Homme2006-02-054-11/+11
* Update licensing information: The FSF changed postal address.Diego Biurrun2006-01-1214-15/+16
* tweak h264_biweightLoren Merritt2006-01-091-4/+4
* fix some potential arithmetic overflows in pred_direct_motion() andLoren Merritt2005-12-301-6/+6
* COSMETICS: tabs --> spaces, some prettyprintingDiego Biurrun2005-12-2213-4428/+4428
* COSMETICS: Remove all trailing whitespace.Diego Biurrun2005-12-1714-397/+397
* Add the rest of missing Reg_* macros to support both AMD-64 style regs and IA...Guillaume Poirier2005-12-101-0/+10
* use sse16_sse2() in nsseLoren Merritt2005-11-121-2/+5
* faster h264_chroma_mc8_mmx, added h264_chroma_mc4_mmx.Loren Merritt2005-10-273-34/+239
* h264 mmx weighted prediction. up to 3% overall speedup.Loren Merritt2005-10-092-0/+115
* sse2 16x16 sum squared diff (306=>268 cycles on a K8)Loren Merritt2005-09-301-5/+85
* replace a few mov + psrlq with pshufw, there are more cases which could benef...Michael Niedermayer2005-09-212-17/+17
* Fix compile without CONFIG_GPL, misplaced #endif caused a missing }.Reimar Döffinger2005-09-101-1/+1
* remove unused table entriesMichael Niedermayer2005-09-101-27/+10
* xvids mmx&mmx2 idctsMichael Niedermayer2005-09-102-0/+586
* Kill some compiler warnings. Compiled code verified identical after changes.Måns Rullgård2005-09-062-5/+7
* simplify (d&a) and (d&~a) calculation, hint by skalMichael Niedermayer2005-09-031-4/+3
* add consts (this was in my local tree, dunno where it came from, probably for...Michael Niedermayer2005-09-021-22/+22
* kill a bunch of compiler warningsMåns Rullgård2005-08-141-1/+0
View Lorry Controller Status