358 Commits (160ab30fcccea5697b2c065e7647c370e321cca6)

Author SHA1 Message Date
Aurelien Jacobs 73f51a4d3e help some gcc version to optimize out those functions 17 years ago
Aurelien Jacobs 674eeb5f57 cosmetics: indentation 17 years ago
Aurelien Jacobs eb75a69818 Avoid linking with h263.c functions when the relevant codecs 17 years ago
Måns Rullgård a00177a952 make arguments to ssd_int8_vs_int16() const 17 years ago
Diego Biurrun 09a6682648 typos 17 years ago
Diego Biurrun e5a389a1b7 license header consistency cosmetics 17 years ago
Diego Biurrun 7b94177e37 Group all copyright and author notices together. 17 years ago
Guillaume Poirier efb775777f add a comment to indicate which #endif belong to which #define 18 years ago
Måns Rullgård 699b3f99d0 add multiple inclusion guards to headers 18 years ago
Måns Rullgård 8657d5e549 correct type for {put,avg}_h264_chroma_mc2_mmx2 18 years ago
Diego Biurrun 90b5b51eab misc typo fixes 18 years ago
Diego Biurrun 755bfeabcc misc spelling fixes 18 years ago
Graham Booker ee387b57fd work around issues with the old version of Gnu Assembler shipped on 18 years ago
Diego Biurrun 34933442ac Preprocessor #defines starting with __ are reserved for the system. 18 years ago
Ronald S. Bultje 3d4e3e560f Use FFmpeg-specific CPU feature definitions. 18 years ago
Carl Eugen Hoyos 154e30f6c2 rename attribute_unused to av_unused and moves its declaration to common.h 18 years ago
Zuxy Meng 663deb54af Remove incorrect comment; MMX2 is preferred over 3DNow! on Athlon 18 years ago
Zuxy Meng 038bfcf9d6 3DNow! and SSSE3 optimization to QNS DSP functions; use pmulhrw/pmulhrsw instead of pmulhw 18 years ago
Aurelien Jacobs 5b0b7054b4 better separation of vp3dsp functions from dsputil_mmx.c 18 years ago
Ronald S. Bultje b550bfaa61 Add libavcodec to compiler include flags in order to simplify header 18 years ago
Panagiotis Issaris 9b5dc86746 Make vp3dsp*.c compilation optional. 18 years ago
Reimar Döffinger e36d79c837 Change some leftover __attribute__((unused)) and __attribute__((used)) to 18 years ago
Zuxy Meng 25e4f8aaee Faster SSE FFT/MDCT, patch by Zuxy Meng %zuxy P meng A gmail P com% 18 years ago
Loren Merritt ff506a906e sse2 & ssse3 versions of dct_quantize. 18 years ago
Loren Merritt 1edbfe1994 factor sum_abs_dctelem out of dct_sad, and simd it. 18 years ago
Loren Merritt 561f940c03 sse2 & ssse3 versions of hadamard. unroll and inline diff_pixels. 18 years ago
Loren Merritt ba53071acb 10l, r8991 broke mmx1 sad 18 years ago
Loren Merritt 72946825fa sse2 version of fullpel sad. 18 years ago
Loren Merritt 164d75ebf3 tweak mmx2 sad. 18 years ago
Loren Merritt eca3810e31 tweak mmx2 sad. 18 years ago
Loren Merritt 7c3a9fe2a3 sse2 version of fdct_col. 18 years ago
Loren Merritt 5adf43e47e cosmetics: remove code duplication in hadamard8_diff_mmx 18 years ago
Loren Merritt bba5293bb7 cosmetics: remove duplicate transpose macro 18 years ago
Reimar Döffinger a1ce61108b Fix parts missed in clip -> av_clip rename 18 years ago
Diego Biurrun fe0372296a typos 18 years ago
Loren Merritt 5900637219 mmx 16-bit ssd. 2.3x faster svq1 encoding. 18 years ago
Diego Biurrun d42f88025a Fix wrong conditional, Snow decoding, not encoding, was SIMD-accelerated. 18 years ago
Michael Niedermayer 58e31fb1d5 reorder a few more paddws to reduce dependancy chains 18 years ago
Michael Niedermayer b4fe97696c reorder paddws to reduce dependancy chain 18 years ago
Michael Niedermayer 0c67082e02 shortening dependancy chain in chroma mc2 18 years ago
Michael Niedermayer af26516261 remove now wrong comment 18 years ago
Michael Niedermayer 61240ae556 fix chroma mc2 bug, this is based on a patch by (Oleg Metelitsa oleg hitron co kr) 18 years ago
Michael Niedermayer 470d2d03cc gcc 2.95 fix 18 years ago
Måns Rullgård 459022f504 fix for x86-64 18 years ago
Michael Niedermayer b21e0b6dfc rewrite H264_CHROMA_MC4_TMPL (20% faster) 18 years ago
Michael Niedermayer 2a115873af add a few asserts to ensure alignment 18 years ago
Michael Niedermayer 00e210ddbb prevent h.264 MC related functions from being inlined (yes this is much faster the code just doesnt fit in the code cache otherwise) 18 years ago
Reimar Döffinger 392b76ca93 Minor AMD64 compilation fix 18 years ago
Michael Niedermayer 9bc0d3ef3e maybe fix x86_64 (untested) 18 years ago
Michael Niedermayer 7c4fd7eb0c factor out common subexprssion (gcc of course is too stupid to do this ...) 18 years ago