392 Commits (952062909dee8c70ca3fa81ab8f237fb735cbc4f)

Author SHA1 Message Date
Zdenek Kabelac 85bd552606 * using DSPContext - so each codec could use its local (sub)set of CPU extension 22 years ago
Zdenek Kabelac ec7e0bf0fd * using DSPContext - so each codec could use its local (sub)set of CPU extension 22 years ago
Zdenek Kabelac eb4b3dd3c3 * using DSPContext - so each codec could use its local (sub)set of CPU extension 22 years ago
Michael Niedermayer 3d71589f27 cleanup 22 years ago
Fabrice Bellard bb6f569072 new generic FFT/MDCT code for audio codecs 22 years ago
Michael Niedermayer 50eb9cbc44 idct_permutation_type variable, so the permutation type can quickly be identified 22 years ago
Michael Niedermayer 2ad1516a6c idct permutation cleanup, idct can be selected per context now 22 years ago
Michael Niedermayer 084c726ba3 pix_sum16_mmx() 22 years ago
Arpi 3f09f52adf fdct_mmx -> ff_fdct_mmx (renamed to avoid namespace conflict with xvid) 22 years ago
Michael Niedermayer b318477992 put/avg_pixels16 22 years ago
Michael Niedermayer 1a684b3d53 fixing encoding at high QPs (was broken after the dct accuracy increase due to too small inverse table) 22 years ago
Michael Niedermayer ad324c9351 dct cleanup 22 years ago
Lennert Buytenhek 1565dabc1a be less verbose patch by (Lennert Buytenhek <buytenh at math dot leidenuniv dot nl>) 22 years ago
Michael Niedermayer e7fce5e9fb bitexact hack for the simple mmx idct 22 years ago
Michael Niedermayer 28db7fce02 slow but accurate integer dct from IJG (should be ok with the LGPL as the old DCT is the fast integer DCT from IJG) 22 years ago
Dominik Mierzejewski 0778718635 warning patch by (Dominik Mierzejewski <dominik at rangers dot eu dot org>) 22 years ago
Michael Niedermayer 9f36153415 dont trash mm0, its still used in the next iteration of the loop (fixes strange horizontal lines on some blocks in b frames on mmx only cpus) 22 years ago
Michael Niedermayer 87f8cab45b mpeg4 mpeg quantizer encoding 22 years ago
Michael Niedermayer 4afeaec92f pix_abs mmx2 isnt bit-exact ... 22 years ago
Zdenek Kabelac 39825f315f * reimplemented remaing avg_ pixel functions 23 years ago
Zdenek Kabelac d3cd07425a * implemented remaing avg_ pixel functions (these are not used offen) 23 years ago
Zdenek Kabelac fca0f0e59f * removed MANGLE from macros for setting constants 23 years ago
Zdenek Kabelac ff9657069a * using unrolled loops seems to help to MMX Celerons 23 years ago
Zdenek Kabelac 6aa6ea8e11 * reenabled original xy2 put routine - rounding error is really bad with 23 years ago
Zdenek Kabelac 91abb473fb * code with new PAVGB for MMX only CPU splited into separate file 23 years ago
Zdenek Kabelac def60345ad * new mmx code - based upon http://aggregate.org/MAGIC 23 years ago
Zdenek Kabelac 541027e26a * cosmetic minor change 23 years ago
Zdenek Kabelac d17b6f0bbb * optimized remaing avg_pixels_xy2 23 years ago
Zdenek Kabelac e9c0a38ff0 * optimized avg_* functions (except xy2) 23 years ago
Zdenek Kabelac c0eb0bb717 * more PIC friendly and faster code 23 years ago
Zdenek Kabelac 5f6230016a * removed TESTCPU_MAIN - not needed for testing 23 years ago
Zdenek Kabelac e5f3d22d35 * undefine local defines when they are no longer needed 23 years ago
Zdenek Kabelac 30eb039652 * avoids double inclusion of this header 23 years ago
Fabrice Bellard ff4ec49e64 license/copyright change 23 years ago
Zdenek Kabelac 52af45ad77 * baling 8 seems to have the same speed 23 years ago
Zdenek Kabelac fbdedc1704 * always baling even though it seems to produce sometime worse 23 years ago
Zdenek Kabelac 31ddcf9851 * cleanup for put_pixels_mmx 23 years ago
Zdenek Kabelac ec9a41f57d * somewhat more advanced test suit for dsp code - for now i386 only 23 years ago
Zdenek Kabelac 6efad6fd85 * align the source initialy address 23 years ago
Zdenek Kabelac 2bd978bdb8 * fixed contrains and avoid usage of scale index access 23 years ago
Zdenek Kabelac dcb9cd4b81 * added simple test main - see comments about how to 23 years ago
Michael Niedermayer ba0420d83e using 1 operand less and slightly faster put_pixels_y2 23 years ago
Zdenek Kabelac a213d66486 * fix for -fPIC compilation - compiles with 2.95.2 as well - any 23 years ago
Fabrice Bellard 4f12a4976a removed unused code 23 years ago
Fabrice Bellard 61a4e8ae3b removed debug function 23 years ago
Fabrice Bellard 9241551049 tried to avoid gcc 2.95.2 bug by puting explicit register constraints - added comment about rounding bug in some functions (need to correct or suppress them for regression tests) 23 years ago
Michael Niedermayer a7bd879798 shared lib support (req by kabi) ... 23 years ago
Michael Niedermayer 607dce96c0 hopefully faster mmx2&3dnow MC 23 years ago
Michael Niedermayer ccf589a8fe C4=16383 for the c version too and even for some outcommented code 23 years ago
Michael Niedermayer 9e1795dd13 set C4 to 16383 23 years ago