2010-12-04 |
Baptiste Coudurier | 10l, add ff_pw_1 to dsputil_mmx for yadif sse2 |
tree | commitdiff |
2010-12-01 |
avcoder | Use SECTION .text for yasm code. |
tree | commitdiff |
2010-11-02 |
Ramiro Polla | dnxhd_mmx: prefer xmm registers below xmm6 when they... |
tree | commitdiff |
2010-11-01 |
İsmail Dönmez | dsputil: Use explicit movzbl instead of movzx |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | lpc_mmx: add xmm registers to clobber list |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | lpc_mmx: merge some asm blocks |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | sad16_sse2: merge 2 asm blocks |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | xmm_clobbers: list xmm registers first in clobber list |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | idct_sse2_xvid: only mark xmm>=8 as clobbered on x86_64 |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | motion_est_mmx: prefer xmm registers below xmm6 when... |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | dsputil_mmx: add xmm registers to clobber list |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | cosmetics: split long line |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | fdct_mmx: add xmm registers to clobber list |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | idct_sse2_xvid: add xmm registers to clobber list |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | mpegvideo_mmx: add xmm registers to clobber list |
tree | commitdiff |
2010-10-31 |
Ramiro Polla | dsputil_mmx: prefer xmm registers below xmm6 when they... |
tree | commitdiff |
2010-10-30 |
Ramiro Polla | h264dsp: add xmm registers to clobber list |
tree | commitdiff |
2010-10-28 |
Ramiro Polla | indent |
tree | commitdiff |
2010-10-28 |
Ramiro Polla | h264dsp: merge some more asm blocks |
tree | commitdiff |
2010-10-25 |
Ramiro Polla | dct32: mark xmm registers in clobber list in ff_dct32_f... |
tree | commitdiff |
2010-10-25 |
Ramiro Polla | h264dsp: merge some asm blocks |
tree | commitdiff |
2010-10-07 |
Reimar Döffinger | Add d modifier to asm argument to fix nasm compilation. |
tree | commitdiff |
2010-10-06 |
Ramiro Polla | fft: mark xmm registers as clobbered in ff_imdct_calc_sse |
tree | commitdiff |
2010-10-05 |
Ronald S. Bultje | MMX, MMX2, SSE2 and SSSE3 optimizations for pred16x16... |
tree | commitdiff |
2010-10-04 |
İsmail Dönmez | snowdsp: Explicitly state the operand sizes |
tree | commitdiff |
2010-09-29 |
Ronald S. Bultje | Move static inline function to a macro, so that constan... |
tree | commitdiff |
2010-09-29 |
Eli Friedman | Use sse2 variant of put_pixels16() for no_rnd also... |
tree | commitdiff |
2010-09-29 |
Ronald S. Bultje | Merge b_idx and edge variables, and optimize the ASM... |
tree | commitdiff |
2010-09-29 |
Ronald S. Bultje | Remove mv_mask variable. Replace the related pand ... |
tree | commitdiff |
2010-09-29 |
Ronald S. Bultje | Remove d_idx as a variable, and instead load it as... |
tree | commitdiff |
2010-09-29 |
Ronald S. Bultje | Unroll inner bidir loop in h264_loop_filter_strength_mm... |
tree | commitdiff |
2010-09-29 |
Ronald S. Bultje | Unloop the outer loop in h264_loop_filter_strength_mmx2... |
tree | commitdiff |
2010-09-26 |
Reimar Döffinger | Add d suffix to movd target register to make it work... |
tree | commitdiff |
2010-09-26 |
Reimar Döffinger | Split and then simplify address generation macro. |
tree | commitdiff |
2010-09-24 |
Ronald S. Bultje | Remove unused variable. |
tree | commitdiff |
2010-09-24 |
Ronald S. Bultje | Unroll loop in h264_idct_add16intra_sse2(). Basically... |
tree | commitdiff |
2010-09-24 |
Ronald S. Bultje | Unroll loop in h264_idct_add8_sse2(). This means we... |
tree | commitdiff |
2010-09-21 |
Måns Rullgård | x86: disable SSE functions using stack when stack is... |
tree | commitdiff |
2010-09-18 |
Måns Rullgård | x86: remove hack disabling sse2 h264 loop filter with... |
tree | commitdiff |
2010-09-17 |
Ronald S. Bultje | Don't access upper 32 bits of a 32-bit int on 64-bit... |
tree | commitdiff |
2010-09-17 |
Ronald S. Bultje | Properly add HAVE_YASM around yasmified symbols. Should... |
tree | commitdiff |
2010-09-17 |
Ronald S. Bultje | Move hadamard_diff{,16}_{mmx,mmx2,sse2,ssse3}() from... |
tree | commitdiff |
2010-09-17 |
Ronald S. Bultje | Move sse16_sse2() from inline asm to yasm. It is one... |
tree | commitdiff |
2010-09-14 |
Ronald S. Bultje | Rename h264_idct_sse2.asm to h264_idct.asm; move inline... |
tree | commitdiff |
2010-09-10 |
Jason Garrett-Glaser | LGPL SSE2 H.264 iDCT |
tree | commitdiff |
2010-09-08 |
Stefano Sabatini | Move mm_support() from libavcodec to libavutil, make... |
tree | commitdiff |
2010-09-05 |
Reimar Döffinger | Use "d" suffix for general-purpose registers used with... |
tree | commitdiff |
2010-09-04 |
Stefano Sabatini | Rename FF_MM_ symbols related to CPU features flags... |
tree | commitdiff |
2010-09-03 |
Ronald S. Bultje | Port latest x264 deblock asm (before they moved to... |
tree | commitdiff |
2010-09-01 |
Eli Friedman | Fix typo in r25019. |
tree | commitdiff |
2010-09-01 |
Ronald S. Bultje | Unscrew breakage after my last commit because of symbol... |
tree | commitdiff |
2010-09-01 |
Ronald S. Bultje | Rename h264_weight_sse2.asm to h264_weight.asm; add... |
tree | commitdiff |
2010-09-01 |
Ronald S. Bultje | Split h264dsp_mmx.c (which was #included in dsputil_mmx... |
tree | commitdiff |
2010-08-31 |
Ronald S. Bultje | Fix vertical align. |
tree | commitdiff |
2010-08-30 |
Ronald S. Bultje | Fix compilation failure if yasm is disabled (missing... |
tree | commitdiff |
2010-08-30 |
Ronald S. Bultje | Split intra prediction initialization (i.e. assigning... |
tree | commitdiff |
2010-08-30 |
Ronald S. Bultje | Move H264 chroma MC from inline asm to yasm. This fixes... |
tree | commitdiff |
2010-08-30 |
Ronald S. Bultje | Move VP3 IDCT functions from inline ASM to YASM. This... |
tree | commitdiff |
2010-08-30 |
Ronald S. Bultje | Put ff_ prefix on non-static {put_signed,put,add}_pixel... |
tree | commitdiff |
2010-08-28 |
Loren Merritt | cosmetics in imdct_sse |
tree | commitdiff |
2010-08-26 |
Ronald S. Bultje | Fix typos when converting inline asm to yasm, fixes... |
tree | commitdiff |
2010-08-25 |
Ronald S. Bultje | Revert r24931, it broke Win32 and some BSD compiles... |
tree | commitdiff |
2010-08-25 |
Ronald S. Bultje | Mark xmm6 and xmm7 as clobbered in ff_vp3_idct_sse2... |
tree | commitdiff |
2010-08-25 |
Måns Rullgård | VP6: fix vp6_filter_diag4_mmx/sse on 64-bit |
tree | commitdiff |
2010-08-25 |
Ronald S. Bultje | Move vp6_filter_diag4() x86 SIMD code from inline ASM... |
tree | commitdiff |
2010-08-25 |
Ronald S. Bultje | Move vp6_filter_diag4() from DSPContext to VP56DSPContext. |
tree | commitdiff |
2010-08-24 |
Måns Rullgård | Remove global mm_flags variable |
tree | commitdiff |
2010-08-24 |
Ronald S. Bultje | Mark xmm registers as clobbered in simple loopfilter... |
tree | commitdiff |
2010-08-23 |
Alex Converse | imdct/x86: Use "s->mdct_size" instead of "1 << s->mdct_... |
tree | commitdiff |
2010-08-23 |
Ronald S. Bultje | Fix segfaults in VP8 SIMD code on Win64 (and FATE/win64... |
tree | commitdiff |
2010-08-22 |
Alex Converse | Convert ff_imdct_half_sse() to yasm. |
tree | commitdiff |
2010-08-12 |
Jason Garrett-Glaser | VP5/6/8: ~7% faster arithmetic decoding |
tree | commitdiff |
2010-08-07 |
Jason Garrett-Glaser | Split h264dsp and h264pred in configure. |
tree | commitdiff |
2010-08-05 |
Jason Garrett-Glaser | Add file missing in r24702 |
tree | commitdiff |
2010-08-05 |
Eli Friedman | H.264: SSE2/SSSE3 weighted prediction asm |
tree | commitdiff |
2010-08-03 |
Måns Rullgård | Move cavs dsp functions to their own struct |
tree | commitdiff |
2010-08-03 |
Jason Garrett-Glaser | VP5/6/8: add one inline missed in r24677 |
tree | commitdiff |
2010-08-02 |
Jason Garrett-Glaser | VP8: move zeroing of luma DC block into the WHT |
tree | commitdiff |
2010-07-31 |
Ronald S. Bultje | Use word-writing instead of dword-writing (with two... |
tree | commitdiff |
2010-07-31 |
Vitor Sessak | Remove x86/mmx.h. It is not used anymore and has been... |
tree | commitdiff |
2010-07-31 |
Vitor Sessak | Convert deinterlacing MMX code to YASM |
tree | commitdiff |
2010-07-29 |
Vitor Sessak | Fix compilation in x86_64. I broke it with r24580. |
tree | commitdiff |
2010-07-29 |
Vitor Sessak | Translate libmpeg2 MMX IDCT to plain asm |
tree | commitdiff |
2010-07-26 |
Ronald S. Bultje | Use pmaddubsw for the mbedge_filter (>=ssse3), 6-10... |
tree | commitdiff |
2010-07-26 |
Jason Garrett-Glaser | VP8: Much faster SSE2 MC |
tree | commitdiff |
2010-07-26 |
Ronald S. Bultje | Enable no-loop memory/register saving for ssse3/sse4... |
tree | commitdiff |
2010-07-26 |
Ronald S. Bultje | Save a register (or regsize of stackspace for x86-32... |
tree | commitdiff |
2010-07-26 |
Ronald S. Bultje | Use nested ifs instead of &&, which appears to not... |
tree | commitdiff |
2010-07-26 |
Ronald S. Bultje | Split pextrw macro-spaghetti into several opt-specific... |
tree | commitdiff |
2010-07-25 |
Ronald S. Bultje | Fix obvious bug in assignment. Somehow, the test vector... |
tree | commitdiff |
2010-07-24 |
Ronald S. Bultje | Fix SPLATB_REG mess. Used to be a if/elseif/elseif... |
tree | commitdiff |
2010-07-23 |
Eli Friedman | Inline asm for VP56 arith coder |
tree | commitdiff |
2010-07-23 |
Jason Garrett-Glaser | VP8: optimize DC-only chroma case in the same way as... |
tree | commitdiff |
2010-07-23 |
Jason Garrett-Glaser | VP8 asm: cosmetics (spacing) |
tree | commitdiff |
2010-07-23 |
Jason Garrett-Glaser | VP8: 30% faster idct_mb |
tree | commitdiff |
2010-07-23 |
Jason Garrett-Glaser | VP8: clear DCT blocks in iDCT instead of using clear_bl... |
tree | commitdiff |
2010-07-22 |
Ronald S. Bultje | Use pextrw for SSE4 mbedge filter result writing, speed... |
tree | commitdiff |
2010-07-22 |
Ronald S. Bultje | Fix and enable horizontal >=SSE2 mbedge loopfilter. |
tree | commitdiff |
2010-07-22 |
Loren Merritt | relicense h264 deblock sse2 to lgpl |
tree | commitdiff |
2010-07-21 |
Loren Merritt | sync yasm macros from x264 |
tree | commitdiff |
next |