322 Commits (549b2c0cc32662c938331c3282eaa5f876b3ffc1)

Author SHA1 Message Date
Loren Merritt 1e4ecf26f5 ff_fft_calc_3dn/3dn2/sse: convert intrinsics to inline asm. 19 years ago
Michael Niedermayer cf5aed5bad simplify 19 years ago
Michael Niedermayer 3829a62eae insufficient alignment 19 years ago
Marco Manfredini 6bb9e49249 Fix building with --disable-opts but MMX enabled. 19 years ago
John Dalgliesh 4454dc1b6f Support for MacIntel, last part: balign directives 19 years ago
Loren Merritt 069720565c vorbis simd tweaks 19 years ago
Michael Niedermayer 1f1aa1d955 convert vector_fmul_reverse_sse2 and vector_fmul_add_add_sse2 to sse 19 years ago
Loren Merritt eb4825b5d4 sse and 3dnow implementations of float->int conversion and mdct windowing. 19 years ago
Luca Barbato ffad4ed154 Fix x86 SIMD asm and pic, patch from Martin von Gagern <Martin.vGagern@gmx.net> 19 years ago
John Dalgliesh 347be47226 Support for MacIntel, take xx: '/nop' illegal for old versions of GAS 19 years ago
John Dalgliesh 0fc256f3d9 Add support for Mac OS X Intel part 2: Assembler macros in fdct_mmx.c 19 years ago
John Dalgliesh fc48b6fe74 Support for Mac OS X Intel, part 3: binary integer constants: 19 years ago
Loren Merritt ee5df92750 emms -> femms 19 years ago
Loren Merritt 2494bdd90d gcc 2.95 and 3.4.x on x86 32bit without fomit-frame-pointer can't even find 5 registers for asm input. 19 years ago
Loren Merritt 1b87c40245 slightly faster ff_imdct_calc_3dn2() on amd64. (gcc added a bunch of useless movsxd) 19 years ago
Michael Niedermayer 21bb884fb7 change vorbis_inverse_coupling_sse2() so it works on sse1 cpus 19 years ago
Loren Merritt bcfa3e58ee 3dnow2 implementation of imdct. 19 years ago
Loren Merritt cd035a6051 10l, vorbis_inverse_coupling_sse() was really 3dnow 19 years ago
Loren Merritt 2dac4acfc0 sse & sse2 implementations of vorbis channel coupling. 19 years ago
Stefan Gehrer 595e7bd940 some MMX optimizations for the CAVS decoder 19 years ago
Michael Niedermayer 5ced7b80ad disable the vp3 mmx and sse2 idcts, their output doesnt match the c idct (tested with -f crc) and the theora spec does not allow different idcts not to mention the difference is quite vissible ... 19 years ago
Måns Rullgård 98d417cbcd #define SBUTTERFLY outside CONFIG_ENCODERS 19 years ago
Luca Abeni 9c39071d6d Move REG_* macros from libavcodec/i386/mmx.h to libavutil/x86_cpu.h 19 years ago
Måns Rullgård 3f8674a902 remove redundant macro definitions 19 years ago
Måns Rullgård 8fb0d07339 kill warning 19 years ago
Michael Niedermayer e27b6e62f7 missmatch control for mpeg2 intra dequantization if bitexact=1 19 years ago
Zuxy Meng 392f6da897 Remove unused and unsupported Cyrix's "Extended MMX", 19 years ago
Wolfram Gloger f42635f558 gcc-2.95 compile fix, patch by Wolfram Gloger <wmglo A dent PIS med PIS uni-muenchen PIS de> 19 years ago
Loren Merritt 75ca1a5f70 gmc_mmx tweaks 19 years ago
Loren Merritt 703c8195a8 mmx implementation of 3-point GMC. (5x faster than C) 19 years ago
Luca Barbato 22b48b85b6 altivec support for snow 19 years ago
Loren Merritt 5e8b787afa simplified and slightly faster h264_chroma_mc8_mmx 19 years ago
Loren Merritt 513fbd8e5a prefetch pixels for future motion compensation. 2-5% faster h264. 19 years ago
Loren Merritt 5e6a5c4daf 10l 19 years ago
Loren Merritt fdd3057981 added mmx implementation of h264_chroma_mc2 19 years ago
Robert Edele e8600e5edc add MMX and SSE versions of ff_snow_inner_add_yblock 19 years ago
Robert Edele 2c9a0285d4 snow mmx+sse2 optimizations, part 4 19 years ago
Robert Edele 4567b4bdab Add the mmx and sse2 implementations of ff_snow_vertical_compose(). 19 years ago
Robert Edele 059715a41c First part of a series of speed-enchancing patches. 19 years ago
Zuxy Meng 82eb4b0f1b 3DNow! & Extended 3DNow! versions of FFT 19 years ago
Loren Merritt 548a1c8a35 h264_idct8_add_mmx 19 years ago
Loren Merritt 6da971f160 h264_idct_add only needs mmx1 19 years ago
Zuxy Meng 2ffb22d2ad use xorps instead of mulps to toggle the sign of a float, as suggested by Software Optimization Guide for AMD64 Processors. 19 years ago
Loren Merritt d84f7c61ee gcc2.95 workaround 19 years ago
Loren Merritt 7a5b2fa812 remove some useless instructions 19 years ago
Loren Merritt 6a8eb0f45a 4% faster h264_qpel_mc 19 years ago
Loren Merritt ef9d1d1575 h264: special case dc-only idct. ~1% faster overall 19 years ago
Loren Merritt 4e295993ba 10l in 1.12 19 years ago
Loren Merritt 6ee669732d 10l (x86_64) 19 years ago
Loren Merritt e545f37527 18% faster put_h264_qpel16_mc[13]2_mmx2 19 years ago