log i386/dsputil_mmx.c @ 4319:8e11023556c3 libavcodec

age author description
2006-11-14 mru revert bad checkin libavcodec
2006-11-14 mru move some CFLAGS settings away from config.* writing section libavcodec
2006-11-12 mru adding more static keywords libavcodec
2006-11-03 michael optimize H264_DEBLOCK_P0_Q0 libavcodec
2006-10-14 diego Put libmpeg2 IDCT functions under CONFIG_GPL, fixes link failure libavcodec
2006-10-11 diego Rename ABS macro to FFABS. libavcodec
2006-10-07 diego Change license headers to say 'FFmpeg' instead of 'this program/this library' libavcodec
2006-10-05 diego Switch idct_mmx_xvid.c from GPL to LGPL as permitted by the libavcodec
2006-10-01 lorenm approximate qpel functions: sacrifice some quality for some decoding speed. enabled on B-frames with -lavdopts fast. libavcodec
2006-09-27 mru add some #ifdef CONFIG_ENCODERS/DECODERS libavcodec
2006-09-14 aurel disable vp3 mmx idct for theora files to avoid artifacts libavcodec
2006-09-14 diego Remove the LGPL exception clause as discussed on ffmpeg-devel libavcodec
2006-09-12 aurel Enables back the mmx/sse optimized version of the vp3 idct. libavcodec
2006-09-02 mru remove redundant declarations libavcodec
2006-08-28 lorenm mmx implementation of deblocking strength decision. libavcodec
2006-08-12 gpoirier Support for MacIntel, last part: balign directives libavcodec
2006-08-11 lorenm vorbis simd tweaks libavcodec
2006-08-10 michael convert vector_fmul_reverse_sse2 and vector_fmul_add_add_sse2 to sse libavcodec
2006-08-10 lorenm sse and 3dnow implementations of float->int conversion and mdct windowing. libavcodec
2006-08-09 lorenm emms -> femms libavcodec
2006-08-08 michael change vorbis_inverse_coupling_sse2() so it works on sse1 cpus libavcodec
2006-08-03 lorenm 10l, vorbis_inverse_coupling_sse() was really 3dnow libavcodec
2006-08-03 lorenm sse & sse2 implementations of vorbis channel coupling. libavcodec
2006-07-29 stefang some MMX optimizations for the CAVS decoder libavcodec
2006-07-19 michael 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 ... libavcodec
2006-07-05 mru #define SBUTTERFLY outside CONFIG_ENCODERS libavcodec
2006-07-03 lucabe Move REG_* macros from libavcodec/i386/mmx.h to libavutil/x86_cpu.h libavcodec
2006-04-05 lorenm gmc_mmx tweaks libavcodec
2006-04-04 lorenm mmx implementation of 3-point GMC. (5x faster than C) libavcodec
2006-03-23 lorenm prefetch pixels for future motion compensation. 2-5% faster h264. libavcodec
2006-03-22 lorenm added mmx implementation of h264_chroma_mc2 libavcodec
2006-03-22 gpoirier add MMX and SSE versions of ff_snow_inner_add_yblock libavcodec
2006-03-21 corey snow mmx+sse2 optimizations, part 4 libavcodec
2006-03-20 gpoirier Add the mmx and sse2 implementations of ff_snow_vertical_compose(). libavcodec
2006-03-07 lorenm h264_idct8_add_mmx libavcodec
2006-03-07 lorenm h264_idct_add only needs mmx1 libavcodec
2006-02-10 lorenm h264: special case dc-only idct. ~1% faster overall libavcodec
2006-02-05 diego MSVC-compatible __align8/__align16 declaration libavcodec
2006-01-12 diego Update licensing information: The FSF changed postal address. libavcodec
2005-12-22 diego COSMETICS: tabs --> spaces, some prettyprinting libavcodec
2005-12-17 diego COSMETICS: Remove all trailing whitespace. libavcodec
2005-11-12 lorenm use sse16_sse2() in nsse libavcodec
2005-10-27 lorenm faster h264_chroma_mc8_mmx, added h264_chroma_mc4_mmx. libavcodec
2005-10-09 lorenm h264 mmx weighted prediction. up to 3% overall speedup. libavcodec
2005-09-30 lorenm sse2 16x16 sum squared diff (306=>268 cycles on a K8) libavcodec
2005-09-21 michael replace a few mov + psrlq with pshufw, there are more cases which could benefit from this but they would require us to duplicate some functions ... libavcodec
2005-09-10 reimar Fix compile without CONFIG_GPL, misplaced #endif caused a missing }. libavcodec
2005-09-10 michael xvids mmx&mmx2 idcts libavcodec
2005-09-06 mru Kill some compiler warnings. Compiled code verified identical after changes. libavcodec
2005-06-02 lorenm sort H.264 mmx dsp functions into their own file libavcodec
2005-06-01 michael adding a few const libavcodec
2005-05-31 lorenm MMX for H.264 iDCT (adapted from x264) libavcodec
2005-05-25 hzoli MMX code for (put|avg)_h264_chroma_mc8 libavcodec
2005-05-18 lorenm H.264 deblocking optimizations (mmx for chroma_bS4 case, convert existing cases to 8-bit math) libavcodec
2005-05-17 michael porting the mmx&sse2 (sse2 untested) vp3 idcts to the lavc idct API libavcodec
2005-05-17 michael disabling vp3 mmx&mmx2 idcts, they must be ported over to the lavc idct API, ill port the vp3 c idct libavcodec
2005-05-08 michael fix PIC libavcodec
2005-04-25 lorenm MMX for H.264 deblocking filter libavcodec
2005-02-07 michael optimization and gcc 4.0 bug workaround patch by (Martin Drab >drab kepler.fjfi.cvut cz<) libavcodec
2004-10-11 michael adapting existing mmx/mmx2/sse/3dnow optimizations so they work on x86_64 patch by (Aurelien Jacobs <aurel at gnuage dot org>) libavcodec
2004-09-25 michael 1/2 resolution decoding libavcodec
2004-09-08 michael h264_qpel8_hv_lowpass_mmx2/3dnow libavcodec
2004-09-08 michael h264_qpel4_hv_lowpass_mmx2/3dnow libavcodec
2004-09-08 michael optimization libavcodec
2004-09-07 michael optimization libavcodec
2004-09-07 michael optimization libavcodec
2004-09-07 michael h264 luma motion compensation in mmx2/3dnow libavcodec
2004-09-06 michael 10000l fix and use more mmx2/3dnow code for mpeg4 qpel which has been written and commited long time ago but appearently never used, qpel motion compensation is 5% faster libavcodec
2004-06-08 michael sse8 and nsse in mmx libavcodec
2004-05-18 michael some of the warning fixes by (Michael Roitzsch <mroi at users dot sourceforge dot net>) libavcodec
2004-04-27 melanson move the 0x80 vector outside of the function, thus saving the compiler libavcodec
2004-04-27 melanson separate out put_signed_pixels_clamped() into its own function and libavcodec
2004-04-26 melanson reorganize and simplify the VP3 IDCT stuff libavcodec
2004-04-25 melanson hook up support for SSE2-optimized VP3 IDCT libavcodec
2004-03-08 melanson use optimized VP3 functions where appropriate libavcodec
2004-02-29 michael attribute used patch by (mitya at school dot ioffe dot ru (Dmitry Baryshkov)) libavcodec
2004-02-06 michael quantizer noise shaping optimization libavcodec
2004-01-31 melanson vsad16_mmx2 only applies if encoders are turned on libavcodec
2004-01-29 michael SSE2 fdct by (Balatoni Denes <pnis at coder dot hu>) libavcodec
2004-01-10 michael copyright year update of the files i touched and remembered, things look annoyingly unmaintained otherwise libavcodec
2004-01-05 michael interlaced dct decision cleanup libavcodec
2003-12-30 michael interlaced motion estimation libavcodec
2003-12-13 michael Here are juste two added #ifdef CONFIG_ENCODERS to allow libavcodec
2003-12-02 michael h263_h_loop_filter_mmx libavcodec
2003-12-02 michael h263_v_loop_filter_mmx libavcodec
2003-10-23 alex 1l libavcodec
2003-10-23 michael minor mmx2 optimization if the dct libavcodec
2003-10-14 melanson disable encoders where appropriate (patch courtesy of BERO libavcodec
2003-10-13 michael mmx2 optimization of huffyuv median encoding libavcodec
2003-06-21 michaelni the return of the idct with 16bit output by ("Ivan Kalvachev" <ivan at cacad dot com>) libavcodec
2003-05-07 michaelni more #ifdef CONFIG_ENCODERS by (Wolfgang Hesseler <qv at multimediaware dot com>) libavcodec
2003-04-14 michaelni 10l (hadamard fix) libavcodec
2003-03-26 michaelni faster hadamard transform libavcodec
2003-03-10 kabi * oooooops - sorry for this one - wrong logic libavcodec
2003-03-07 kabi * support FF_MM_FORCE libavcodec
2003-03-03 michaelni MpegEncContext.(i)dct_* -> DspContext.(i)dct_* libavcodec
2003-02-11 kabi * prototypes at one place libavcodec
2003-02-11 kabi * UINTX -> uintx_t INTX -> intx_t libavcodec
2003-02-10 kabi * static,const,compiler warning cleanup libavcodec
2003-01-11 michaelni sse16 & pix_norm1 optimization patch by (Felix von Leitner <felix-ffmpeg at fefe dot de>) (with some modifications) libavcodec
2003-01-09 michaelni qpel fix libavcodec
2003-01-07 michaelni PIC / ebx fix libavcodec
2003-01-07 michaelni more gcc bug workarounds libavcodec
2003-01-06 michaelni 1000l (push & esp) using mangle now ... libavcodec
2003-01-05 michaelni qpel in b frames bugfixes libavcodec
2003-01-05 michaelni slowdown / gcc 2.95.* bug workaround (this should be reversed as soon as gcc 2.95.* support is droped) libavcodec
2003-01-05 michaelni qpel in mmx2/3dnow libavcodec
2002-12-27 michaelni qpel encoding libavcodec
2002-11-14 michaelni huffyuv libavcodec
2002-11-11 kabi * using DSPContext - so each codec could use its local (sub)set of CPU extension libavcodec
2002-09-29 michaelni idct permutation cleanup, idct can be selected per context now libavcodec
2002-09-20 michaelni pix_sum16_mmx() libavcodec
2002-09-11 michaelni put/avg_pixels16 libavcodec
2002-09-01 michaelni be less verbose patch by (Lennert Buytenhek <buytenh at math dot leidenuniv dot nl>) libavcodec
2002-08-31 michaelni bitexact hack for the simple mmx idct libavcodec
2002-08-29 michaelni slow but accurate integer dct from IJG (should be ok with the LGPL as the old DCT is the fast integer DCT from IJG) libavcodec
2002-07-21 michaelni pix_abs mmx2 isnt bit-exact ... libavcodec
2002-06-03 kabi * reimplemented remaing avg_ pixel functions libavcodec
2002-05-30 kabi * removed MANGLE from macros for setting constants libavcodec
2002-05-29 kabi * reenabled original xy2 put routine - rounding error is really bad with libavcodec