92 Commits (5763e63913940f8d2d2eb8750931e5f12dd2a481)

Author SHA1 Message Date
Alexander Strange 1500be13f2 dsputil: allow to skip drawing of top/bottom edges. 14 years ago
Justin Ruggles e6e9823488 Add apply_window_int16() to DSPContext with x86-optimized versions and use it 14 years ago
Mans Rullgard 2912e87a6c Replace FFmpeg with Libav in licence headers 14 years ago
Ronald S. Bultje bf6fa73245 dsputil_mmx.c: remove ff_vector128. 14 years ago
Ronald S. Bultje 12802ec060 dsputil: move VC1-specific stuff into VC1DSPContext. 14 years ago
Justin Ruggles c73d99e672 Separate format conversion DSP functions from DSPContext. 14 years ago
Ronald S. Bultje 81f2a3f4ff Implement a SIMD version of emulated_edge_mc() for x86. 14 years ago
Justin Ruggles d19b744a36 cosmetics: indentation 14 years ago
Justin Ruggles 80ba1ddb58 Remove unneeded add bias from 3 functions. 14 years ago
Justin Ruggles 6eabb0d3ad Change DSPContext.vector_fmul() from dst=dst*src to dest=src0*src1. 14 years ago
Mans Rullgard ef4a65149d Replace ASMALIGN() with .p2align 14 years ago
Mans Rullgard ac3c9d0169 x86: remove VLA in ac3_downmix_sse 14 years ago
Ronald S. Bultje ec3233a855 Fix ff_pw_3 alignment. 14 years ago
Jason Garrett-Glaser 19fb234e4a H.264: split luma dc idct out and implement MMX/SSE2 versions 14 years ago
Ronald S. Bultje 8d147f1f60 For rounding in chroma MC SSSE3, use 16-byte pw_3/4 instead of reading 8 bytes 14 years ago
Baptiste Coudurier 90f1f3bf00 In yadif filter, declare asm constants directly to avoid dependency on libavcodec 14 years ago
Baptiste Coudurier 9e95999e2a 10l, add ff_pw_1 to dsputil_mmx for yadif sse2 14 years ago
İsmail Dönmez 80e33d2451 dsputil: Use explicit movzbl instead of movzx 14 years ago
Ramiro Polla 153ca56b38 xmm_clobbers: list xmm registers first in clobber list 14 years ago
Ramiro Polla 5d543a3d13 dsputil_mmx: add xmm registers to clobber list 14 years ago
Ramiro Polla 559738eff3 dsputil_mmx: prefer xmm registers below xmm6 when they are available 14 years ago
Ronald S. Bultje dd68d4db43 MMX, MMX2, SSE2 and SSSE3 optimizations for pred16x16/8x8_plane H264 intra 14 years ago
Eli Friedman 329d689f75 Use sse2 variant of put_pixels16() for no_rnd also. Provides a minor speed 14 years ago
Stefano Sabatini c6c98d0897 Move mm_support() from libavcodec to libavutil, make it a public 15 years ago
Stefano Sabatini 7160bb716b Rename FF_MM_ symbols related to CPU features flags as AV_CPU_FLAG_ 15 years ago
Ronald S. Bultje 2c166c3af1 Port latest x264 deblock asm (before they moved to using NV12 as internal 15 years ago
Ronald S. Bultje 14bc1f2485 Split h264dsp_mmx.c (which was #included in dsputil_mmx.c) in h264_qpel_mmx.c, 15 years ago
Ronald S. Bultje 79ce0f002e Fix compilation failure if yasm is disabled (missing vp3 symbols). 15 years ago
Ronald S. Bultje d0eb5a1174 Move H264 chroma MC from inline asm to yasm. This fixes VP3/5/6 and VC-1 15 years ago
Ronald S. Bultje e9f5f020c6 Move VP3 IDCT functions from inline ASM to YASM. This fixes part of the VP3/5/6 15 years ago
Ronald S. Bultje 7e7c4b6008 Put ff_ prefix on non-static {put_signed,put,add}_pixels_clamped_mmx() 15 years ago
Ronald S. Bultje 3a0885146c Move vp6_filter_diag4() from DSPContext to VP56DSPContext. 15 years ago
Måns Rullgård c0ec9918b0 Remove global mm_flags variable 15 years ago
Eli Friedman c12d6955e2 H.264: SSE2/SSSE3 weighted prediction asm 15 years ago
Måns Rullgård f079a64aea Move cavs dsp functions to their own struct 15 years ago
Loren Merritt c7b1d9768c relicense h264 deblock sse2 to lgpl 15 years ago
David Conrad c7eec58170 Move ff_pw_* from vc1dsp_mmx.c to dsputil_mmx.c 15 years ago
Ronald S. Bultje e9e456d850 VP8 MBedge loopfilter MMX/MMX2/SSE2 functions for both luma (width=16) 15 years ago
Ronald S. Bultje a711eb4829 VP8 H/V inner loopfilter MMX/MMXEXT/SSE2 optimizations. 15 years ago
David Conrad 7af8fbd348 Make ff_pw_4 128 bits 15 years ago
Ronald S. Bultje f2a30bd840 Simple H/V loopfilter for VP8 in MMX, MMX2 and SSE2 (yay for yasm macros). 15 years ago
Eli Friedman b3858964d6 Add const to some pointer parameters. 15 years ago
Jason Garrett-Glaser 4af8cdfc3f 16x16 and 8x8c x86 SIMD intra pred functions for VP8 and H.264 15 years ago
David Conrad 413abbe164 Add bitexact versions of put_no_rnd_pixels8 _x2 and _y2 for vp3/theora 15 years ago
David Conrad eb6a6cd788 vp3: DC-only IDCT 15 years ago
Måns Rullgård 4693b031a3 Move H264 dsputil functions into their own struct 15 years ago
Måns Rullgård 05aec7bb87 Separate DWT from snow and dsputil 15 years ago
Måns Rullgård f49747e904 x86: move function prototypes to header files 15 years ago
Måns Rullgård 84dc2d8afa Remove DECLARE_ALIGNED_{8,16} macros 15 years ago
David Conrad 19530266a5 Enable SSE2 (put|avg)_pixels_16_sse2 15 years ago