| Commit message (Expand) | Author | Age | Files | Lines |
* | Do not misuse long as the size of a register in x86. | Ramiro Polla | 2008-05-08 | 1 | -28/+28 |
* | h264 chroma mc ssse3 | Loren Merritt | 2008-04-01 | 1 | -0/+36 |
* | asm argument that might be in memory needs a size | Loren Merritt | 2008-02-10 | 1 | -1/+1 |
* | sse2 h264 motion compensation. not new code, just separate out the cases that... | Loren Merritt | 2008-02-06 | 1 | -113/+210 |
* | put loop counter in a register if possible. makes some of the qpel functions ... | Loren Merritt | 2008-02-06 | 1 | -4/+4 |
* | fix aliasing warnings. simpler too. | Loren Merritt | 2008-02-06 | 1 | -41/+34 |
* | ssse3 h264 motion compensation. | Loren Merritt | 2008-02-05 | 1 | -56/+443 |
* | add qpel rounder once during hv rather than twice during hv and whatever it's... | Loren Merritt | 2008-02-05 | 1 | -23/+8 |
* | clean up an ugliness introduced in r11826. this syntax will require fewer cha... | Loren Merritt | 2008-02-05 | 1 | -4/+4 |
* | use mmx2/3dnow avg functions in avg_qpel*_mc00 | Loren Merritt | 2008-02-03 | 1 | -1/+1 |
* | ff_h264_idct8_add_sse2. | Loren Merritt | 2008-02-03 | 1 | -3/+90 |
* | remove some movq in ff_h264_idct8_add_mmx. 225->217 cycles on core2. | Loren Merritt | 2008-02-03 | 1 | -29/+23 |
* | Factorize some duplicated code from CAVS and H.264 into a common file. | Christophe Gisquet | 2008-01-11 | 1 | -6/+0 |
* | add MMX version for put_no_rnd_h264_chroma_mc8_c, used in VC-1 decoding. | Christophe Gisquet | 2007-12-21 | 1 | -0/+18 |
* | use ff_ prefix for extern vars | Aurelien Jacobs | 2007-11-27 | 1 | -4/+4 |
* | make ff_p* vars extern so that they can be used in various *_mmx.c files | Aurelien Jacobs | 2007-11-27 | 1 | -0/+1 |
* | Fix intended order of operations for 4 assert() checks. | Shane | 2007-10-11 | 1 | -4/+4 |
* | cosmetics: remove duplicate transpose macro | Loren Merritt | 2007-05-08 | 1 | -6/+0 |
* | Fix parts missed in clip -> av_clip rename | Reimar Döffinger | 2007-04-19 | 1 | -1/+1 |
* | add a few asserts to ensure alignment | Michael Niedermayer | 2007-02-16 | 1 | -0/+4 |
* | prevent h.264 MC related functions from being inlined (yes this is much faste... | Michael Niedermayer | 2007-02-16 | 1 | -13/+13 |
* | ensure alignment (no speed change) | Michael Niedermayer | 2006-11-03 | 1 | -6/+6 |
* | merging mov & and (no speedchange) | Michael Niedermayer | 2006-11-03 | 1 | -3/+2 |
* | 2 instructions less (same speed) | Michael Niedermayer | 2006-11-03 | 1 | -6/+13 |
* | comment about failed optimization | Michael Niedermayer | 2006-11-03 | 1 | -2/+2 |
* | move luma tc0 related init into asm | Michael Niedermayer | 2006-11-03 | 1 | -12/+17 |
* | 2 instructions less in h264_loop_filter_luma_mmx2() | Michael Niedermayer | 2006-11-03 | 1 | -5/+3 |
* | preempt possible overflow | Michael Niedermayer | 2006-11-03 | 1 | -1/+1 |
* | 1 instruction less | Michael Niedermayer | 2006-11-03 | 1 | -7/+6 |
* | optimize H264_DEBLOCK_P0_Q0 | Michael Niedermayer | 2006-11-03 | 1 | -40/+21 |
* | Change license headers to say 'FFmpeg' instead of 'this program/this library' | Diego Biurrun | 2006-10-07 | 1 | -4/+6 |
* | mmx implementation of deblocking strength decision. | Loren Merritt | 2006-08-28 | 1 | -0/+95 |
* | remove redundant macro definitions | Måns Rullgård | 2006-07-02 | 1 | -6/+0 |
* | added mmx implementation of h264_chroma_mc2 | Loren Merritt | 2006-03-22 | 1 | -0/+4 |
* | h264_idct8_add_mmx | Loren Merritt | 2006-03-07 | 1 | -0/+127 |
* | h264_idct_add only needs mmx1 | Loren Merritt | 2006-03-07 | 1 | -3/+3 |
* | gcc2.95 workaround | Loren Merritt | 2006-03-05 | 1 | -22/+24 |
* | remove some useless instructions | Loren Merritt | 2006-03-04 | 1 | -18/+4 |
* | 4% faster h264_qpel_mc | Loren Merritt | 2006-03-02 | 1 | -40/+137 |
* | h264: special case dc-only idct. ~1% faster overall | Loren Merritt | 2006-02-10 | 1 | -0/+81 |
* | 10l in 1.12 | Loren Merritt | 2006-02-09 | 1 | -6/+6 |
* | 10l (x86_64) | Loren Merritt | 2006-02-07 | 1 | -1/+1 |
* | 18% faster put_h264_qpel16_mc[13]2_mmx2 | Loren Merritt | 2006-02-07 | 1 | -14/+87 |
* | 11% faster put_h264_qpel16_v_lowpass_mmx2 | Loren Merritt | 2006-02-07 | 1 | -11/+27 |
* | 15% faster put_h264_qpel16_hv_lowpass_mmx2 | Loren Merritt | 2006-02-07 | 1 | -26/+45 |
* | Update licensing information: The FSF changed postal address. | Diego Biurrun | 2006-01-12 | 1 | -1/+1 |
* | tweak h264_biweight | Loren Merritt | 2006-01-09 | 1 | -4/+4 |
* | fix some potential arithmetic overflows in pred_direct_motion() and | Loren Merritt | 2005-12-30 | 1 | -6/+6 |
* | COSMETICS: tabs --> spaces, some prettyprinting | Diego Biurrun | 2005-12-22 | 1 | -234/+234 |
* | COSMETICS: Remove all trailing whitespace. | Diego Biurrun | 2005-12-17 | 1 | -2/+2 |