| Commit message (Expand) | Author | Age | Files | Lines |
* | sort H.264 mmx dsp functions into their own file | Loren Merritt | 2005-06-02 | 4 | -886/+917 |
* | adding a few const | Michael Niedermayer | 2005-06-01 | 3 | -5/+5 |
* | 100l for myself (breaking amd64) | Michael Niedermayer | 2005-06-01 | 1 | -4/+4 |
* | merge a few asm blocks so gcc cant unoptimize it (658->631 dezicycles on duron) | Michael Niedermayer | 2005-06-01 | 1 | -7/+13 |
* | get rid of 2 movq (680 -> 658 dezicycles on duron) | Michael Niedermayer | 2005-06-01 | 1 | -17/+15 |
* | avoid one transpose (730->680 dezicycles on duron) | Michael Niedermayer | 2005-06-01 | 1 | -7/+4 |
* | 10l (symbol mangling) | Loren Merritt | 2005-06-01 | 1 | -7/+7 |
* | add rounding bias before the horizontal idct (765->730 dezicyles on duron) | Michael Niedermayer | 2005-06-01 | 1 | -2/+3 |
* | MMX for H.264 iDCT (adapted from x264) | Loren Merritt | 2005-05-31 | 2 | -0/+90 |
* | MMX code for (put|avg)_h264_chroma_mc8 | Zoltán Hidvégi | 2005-05-25 | 2 | -0/+168 |
* | H.264 deblocking optimizations (mmx for chroma_bS4 case, convert existing cas... | Loren Merritt | 2005-05-18 | 1 | -171/+235 |
* | porting the mmx&sse2 (sse2 untested) vp3 idcts to the lavc idct API | Michael Niedermayer | 2005-05-17 | 3 | -266/+43 |
* | disabling vp3 mmx&mmx2 idcts, they must be ported over to the lavc idct API, ... | Michael Niedermayer | 2005-05-17 | 1 | -7/+7 |
* | fix PIC | Michael Niedermayer | 2005-05-08 | 1 | -1/+1 |
* | MMX for H.264 deblocking filter | Loren Merritt | 2005-04-25 | 1 | -0/+204 |
* | read 32bit instead of 64bit to avoid overreading and missalignments | Michael Niedermayer | 2005-04-17 | 1 | -4/+8 |
* | optimization and gcc 4.0 bug workaround patch by (Martin Drab >drab kepler.fj... | Martin Drab | 2005-02-07 | 1 | -16/+12 |
* | x86 cpu capabilities detection rewrite / cleanup | Michael Niedermayer | 2004-12-13 | 1 | -61/+40 |
* | detect sse on athlon-xp patch by (matthieu castet <castet >.< matthieu >at< f... | Matthieu Castet | 2004-12-05 | 1 | -3/+3 |
* | H.261 encoder by (Maarten Daniels <maarten dot daniels at luc dot ac dot be>) | Michael Niedermayer | 2004-10-28 | 1 | -1/+1 |
* | gcc 3.4.3 preversions do not appreciate invalid instruction and operand combi... | Aurelien Jacobs | 2004-10-17 | 1 | -4/+5 |
* | adapting existing mmx/mmx2/sse/3dnow optimizations so they work on x86_64 pat... | Aurelien Jacobs | 2004-10-11 | 9 | -586/+603 |
* | 1/2 resolution decoding | Michael Niedermayer | 2004-09-25 | 1 | -16/+17 |
* | h264_qpel8_hv_lowpass_mmx2/3dnow | Michael Niedermayer | 2004-09-08 | 1 | -6/+79 |
* | h264_qpel4_hv_lowpass_mmx2/3dnow | Michael Niedermayer | 2004-09-08 | 1 | -49/+96 |
* | optimization | Michael Niedermayer | 2004-09-08 | 1 | -54/+20 |
* | optimization | Michael Niedermayer | 2004-09-07 | 1 | -80/+49 |
* | optimization | Michael Niedermayer | 2004-09-07 | 1 | -17/+31 |
* | h264 luma motion compensation in mmx2/3dnow | Michael Niedermayer | 2004-09-07 | 3 | -1/+641 |
* | 10000l fix and use more mmx2/3dnow code for mpeg4 qpel which has been written... | Michael Niedermayer | 2004-09-06 | 2 | -39/+329 |
* | 10l and better MMX/SSE detection for VIA1000 | Michael Niedermayer | 2004-07-16 | 1 | -1/+3 |
* | dc_precission=11 fix | Michael Niedermayer | 2004-07-06 | 1 | -1/+1 |
* | transmeta crusoe mmx detection by "Nobody/Anonymous - nobody" / sf feature re... | Michael Niedermayer | 2004-06-24 | 1 | -0/+11 |
* | sse8 and nsse in mmx | Michael Niedermayer | 2004-06-08 | 1 | -0/+302 |
* | some of the warning fixes by (Michael Roitzsch <mroi at users dot sourceforge... | Michael Niedermayer | 2004-05-18 | 7 | -6/+11 |
* | mmx dct optimization | Michael Niedermayer | 2004-04-30 | 1 | -138/+135 |
* | move the 0x80 vector outside of the function, thus saving the compiler | Mike Melanson | 2004-04-27 | 1 | -2/+3 |
* | separate out put_signed_pixels_clamped() into its own function and | Mike Melanson | 2004-04-27 | 1 | -0/+19 |
* | yes, that's nice... | Mike Melanson | 2004-04-26 | 1 | -1/+0 |
* | reorganize and simplify the VP3 IDCT stuff | Mike Melanson | 2004-04-26 | 3 | -141/+8 |
* | hush... | Mike Melanson | 2004-04-25 | 1 | -1/+1 |
* | hook up support for SSE2-optimized VP3 IDCT | Mike Melanson | 2004-04-25 | 1 | -3/+9 |
* | add selected SSE2 ASM macros | Mike Melanson | 2004-04-25 | 1 | -0/+24 |
* | SSE2-optimized variant of VP3 IDCT | Mike Melanson | 2004-04-25 | 1 | -0/+890 |
* | correct MMX-optimized variant of VP3 IDCT, with comments (thank you | Mike Melanson | 2004-04-25 | 1 | -407/+396 |
* | fixing alignment problems -> SSE2 support enabled again in libavcodec (from f... | Michael Niedermayer | 2004-04-09 | 1 | -4/+17 |
* | fft_*() renamed into ff_fft_*() patch by (Gildas Bazin <gbazin at altern dot ... | Gildas Bazin | 2004-03-13 | 1 | -1/+1 |
* | use optimized VP3 functions where appropriate | Mike Melanson | 2004-03-08 | 1 | -7/+12 |
* | seperated out the C-based VP3 DSP functions into a different file; also | Mike Melanson | 2004-03-08 | 1 | -0/+652 |
* | attribute used patch by (mitya at school dot ioffe dot ru (Dmitry Baryshkov)) | Dmitry Baryshkov | 2004-02-29 | 3 | -11/+11 |