2008-08-31 |
conrad | Use ff_vp3_idct_data in vp3dsp_mmx.c rather than duplic... |
blob | commitdiff | raw |
2008-08-30 |
conrad | Let ff_pw_8 be used as an SSE constant |
blob | commitdiff | raw | diff to current |
2008-08-14 |
lorenm | gcc chokes on the 7 registers needed for float_to_int16... |
blob | commitdiff | raw | diff to current |
2008-08-14 |
lorenm | gcc chokes on xmm constraints, so pessimize int32_to_fl... |
blob | commitdiff | raw | diff to current |
2008-08-13 |
lorenm | special case 6 channel version of float_to_int16_interleave |
blob | commitdiff | raw | diff to current |
2008-08-13 |
lorenm | simd int->float |
blob | commitdiff | raw | diff to current |
2008-08-13 |
lorenm | simd downmix |
blob | commitdiff | raw | diff to current |
2008-08-12 |
lorenm | cosmetics in dsp init |
blob | commitdiff | raw | diff to current |
2008-08-02 |
diego | Mark add_png_paeth_prediction_* functions which are... |
blob | commitdiff | raw | diff to current |
2008-07-16 |
lorenm | float_to_int16_interleave: change src to an array of... |
blob | commitdiff | raw | diff to current |
2008-07-15 |
lorenm | 10l, float_to_int16_interleave_sse/3dnow wrote the... |
blob | commitdiff | raw | diff to current |
2008-07-13 |
lorenm | exploit mdct symmetry |
blob | commitdiff | raw | diff to current |
2008-07-13 |
lorenm | simplify vorbis windowing |
blob | commitdiff | raw | diff to current |
2008-07-11 |
kostya | SSE2 optimizations for Monkey's Audio decoder vector... |
blob | commitdiff | raw | diff to current |
2008-07-09 |
michael | float_to_int16_sse2() |
blob | commitdiff | raw | diff to current |
2008-07-07 |
michael | 1 c-asm loop less and 1x unroll of float_to_int16_sse() |
blob | commitdiff | raw | diff to current |
2008-07-07 |
michael | Fix x86-64 |
blob | commitdiff | raw | diff to current |
2008-07-07 |
michael | dont use C-asm loops and unroll once float_to_int16_3dnow() |
blob | commitdiff | raw | diff to current |
2008-06-22 |
reimar | Fix add_bytes_mmx and add_bytes_l2_mmx for w < 16 |
blob | commitdiff | raw | diff to current |
2008-05-09 |
diego | Use full path for #includes from another directory. |
blob | commitdiff | raw | diff to current |
2008-05-08 |
ramiro | Do not misuse long as the size of a register in x86. |
blob | commitdiff | raw | diff to current |
2008-04-16 |
astrange | Add a new xvid-style IDCT using SSE2. |
blob | commitdiff | raw | diff to current |
2008-04-12 |
diego | Add a header file to declare Xvid IDCT functions. |
blob | commitdiff | raw | diff to current |
2008-04-01 |
lorenm | h264 chroma mc ssse3 |
blob | commitdiff | raw | diff to current |
2008-03-21 |
zuxy | Add missed call to ff_cavsdsp_init_3dnow() in dsputil_i... |
blob | commitdiff | raw | diff to current |
2008-03-20 |
michael | Hardcode register to prevent aparent miscompilation. |
blob | commitdiff | raw | diff to current |
2008-03-20 |
michael | remove unused temp |
blob | commitdiff | raw | diff to current |
2008-03-04 |
aurel | move draw_edges() into dsputil |
blob | commitdiff | raw | diff to current |
2008-02-25 |
aurel | split encoding part of dsputil_mmx into its own file |
blob | commitdiff | raw | diff to current |
2008-02-24 |
reimar | __asm __volatile -> asm volatile, improves code consist... |
blob | commitdiff | raw | diff to current |
2008-02-21 |
lorenm | simd and unroll png_filter_row |
blob | commitdiff | raw | diff to current |
2008-02-06 |
lorenm | sse2 h264 motion compensation. not new code, just separ... |
blob | commitdiff | raw | diff to current |
2008-02-06 |
lorenm | put loop counter in a register if possible. makes some... |
blob | commitdiff | raw | diff to current |
2008-02-06 |
lorenm | constant was excessively aligned |
blob | commitdiff | raw | diff to current |
2008-02-05 |
lorenm | ssse3 h264 motion compensation. |
blob | commitdiff | raw | diff to current |
2008-02-05 |
lorenm | clean up an ugliness introduced in r11826. this syntax... |
blob | commitdiff | raw | diff to current |
2008-02-04 |
lorenm | reduce code duplication |
blob | commitdiff | raw | diff to current |
2008-02-03 |
lorenm | avg_pixels4_mmx2 |
blob | commitdiff | raw | diff to current |
2008-02-03 |
lorenm | use mmx2/3dnow avg functions in avg_qpel*_mc00 |
blob | commitdiff | raw | diff to current |
2008-02-03 |
lorenm | ff_h264_idct8_add_sse2. |
blob | commitdiff | raw | diff to current |
2008-01-30 |
bcoudurier | add parenthesis, fix warning: i386/dsputil_mmx.c:2618... |
blob | commitdiff | raw | diff to current |
2008-01-30 |
bcoudurier | fix prototypes, remove warning: i386/dsputil_mmx.c... |
blob | commitdiff | raw | diff to current |
2008-01-27 |
reimar | Use DECLARE_ALIGNED |
blob | commitdiff | raw | diff to current |
2008-01-11 |
diego | Factorize some duplicated code from CAVS and H.264... |
blob | commitdiff | raw | diff to current |
2007-12-21 |
gpoirier | add MMX version for put_no_rnd_h264_chroma_mc8_c, used... |
blob | commitdiff | raw | diff to current |
2007-12-21 |
diego | Fix typo in macro name: WARPER8_16_SQ --> WRAPPER8_16_SQ. |
blob | commitdiff | raw | diff to current |
2007-12-16 |
aurel | move FLAC mmx dsp to its own file |
blob | commitdiff | raw | diff to current |
2007-12-11 |
diego | typo/clarification |
blob | commitdiff | raw | diff to current |
2007-12-01 |
vitor | spelling |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | remove some unused ff_p* vars from dsputil |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | remove useless #ifdef around extern declaration |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | cosmetics: indentation |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | convert some #ifdef CONFIG_ to if(ENABLE_ |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | build vc1dsp_mmx.c in its own compilation unit |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | use ff_ prefix for extern vars |
blob | commitdiff | raw | diff to current |
2007-11-27 |
aurel | make ff_p* vars extern so that they can be used in... |
blob | commitdiff | raw | diff to current |
2007-11-21 |
gpoirier | add VC-1 MMX DSP functions, under MIT license. |
blob | commitdiff | raw | diff to current |
2007-11-12 |
michael | tring to workaround gcc 2.95 bug which causes random... |
blob | commitdiff | raw | diff to current |
2007-09-29 |
lorenm | sse2 version of compute_autocorr(). |
blob | commitdiff | raw | diff to current |
2007-08-26 |
ramiro | CONFIG_7REGS has been renamed to HAVE_7REGS |
blob | commitdiff | raw | diff to current |
2007-08-26 |
michael | workaound gcc bug, untested as my gcc isnt complaining |
blob | commitdiff | raw | diff to current |
2007-08-26 |
michael | avoid overflow in the 3rd lifting step, this now needs... |
blob | commitdiff | raw | diff to current |
2007-08-25 |
michael | update mmx code to latest snow changes |
blob | commitdiff | raw | diff to current |
2007-08-25 |
michael | use 16bit IDWT (a SIMD implementation of it should... |
blob | commitdiff | raw | diff to current |
2007-07-24 |
aurel | help some gcc version to optimize out those functions |
blob | commitdiff | raw | diff to current |
2007-07-10 |
aurel | cosmetics: indentation |
blob | commitdiff | raw | diff to current |
2007-07-10 |
aurel | Avoid linking with h263.c functions when the relevant... |
blob | commitdiff | raw | diff to current |
2007-07-08 |
mru | make arguments to ssd_int8_vs_int16() const |
blob | commitdiff | raw | diff to current |
2007-05-20 |
zuxy | Remove incorrect comment; MMX2 is preferred over 3DNow... |
blob | commitdiff | raw | diff to current |
2007-05-18 |
zuxy | 3DNow! and SSSE3 optimization to QNS DSP functions... |
blob | commitdiff | raw | diff to current |
2007-05-16 |
aurel | better separation of vp3dsp functions from dsputil_mmx.c |
blob | commitdiff | raw | diff to current |
2007-05-16 |
diego | Add libavcodec to compiler include flags in order to... |
blob | commitdiff | raw | diff to current |
2007-05-14 |
takis | Make vp3dsp*.c compilation optional. |
blob | commitdiff | raw | diff to current |
2007-05-12 |
lorenm | factor sum_abs_dctelem out of dct_sad, and simd it. |
blob | commitdiff | raw | diff to current |
2007-05-12 |
lorenm | sse2 & ssse3 versions of hadamard. unroll and inline... |
blob | commitdiff | raw | diff to current |
2007-05-09 |
lorenm | cosmetics: remove code duplication in hadamard8_diff_mmx |
blob | commitdiff | raw | diff to current |
2007-05-08 |
lorenm | cosmetics: remove duplicate transpose macro |
blob | commitdiff | raw | diff to current |
2007-04-07 |
diego | typos |
blob | commitdiff | raw | diff to current |
2007-03-30 |
lorenm | mmx 16-bit ssd. 2.3x faster svq1 encoding. |
blob | commitdiff | raw | diff to current |
2007-02-24 |
diego | Fix wrong conditional, Snow decoding, not encoding... |
blob | commitdiff | raw | diff to current |
2007-01-30 |
takis | Add the const specifier as needed to reduce the number... |
blob | commitdiff | raw | diff to current |
2006-11-14 |
mru | revert bad checkin |
blob | commitdiff | raw | diff to current |
2006-11-14 |
mru | move some CFLAGS settings away from config.* writing... |
blob | commitdiff | raw | diff to current |
2006-11-12 |
mru | adding more static keywords |
blob | commitdiff | raw | diff to current |
2006-11-03 |
michael | optimize H264_DEBLOCK_P0_Q0 |
blob | commitdiff | raw | diff to current |
2006-10-14 |
diego | Put libmpeg2 IDCT functions under CONFIG_GPL, fixes... |
blob | commitdiff | raw | diff to current |
2006-10-11 |
diego | Rename ABS macro to FFABS. |
blob | commitdiff | raw | diff to current |
2006-10-07 |
diego | Change license headers to say 'FFmpeg' instead of ... |
blob | commitdiff | raw | diff to current |
2006-10-05 |
diego | Switch idct_mmx_xvid.c from GPL to LGPL as permitted... |
blob | commitdiff | raw | diff to current |
2006-10-01 |
lorenm | approximate qpel functions: sacrifice some quality... |
blob | commitdiff | raw | diff to current |
2006-09-27 |
mru | add some #ifdef CONFIG_ENCODERS/DECODERS |
blob | commitdiff | raw | diff to current |
2006-09-14 |
aurel | disable vp3 mmx idct for theora files to avoid artifacts |
blob | commitdiff | raw | diff to current |
2006-09-14 |
diego | Remove the LGPL exception clause as discussed on ffmpeg... |
blob | commitdiff | raw | diff to current |
2006-09-12 |
aurel | Enables back the mmx/sse optimized version of the vp3... |
blob | commitdiff | raw | diff to current |
2006-09-02 |
mru | remove redundant declarations |
blob | commitdiff | raw | diff to current |
2006-08-28 |
lorenm | mmx implementation of deblocking strength decision. |
blob | commitdiff | raw | diff to current |
2006-08-12 |
gpoirier | Support for MacIntel, last part: balign directives |
blob | commitdiff | raw | diff to current |
2006-08-11 |
lorenm | vorbis simd tweaks |
blob | commitdiff | raw | diff to current |
2006-08-10 |
michael | convert vector_fmul_reverse_sse2 and vector_fmul_add_a... |
blob | commitdiff | raw | diff to current |
2006-08-10 |
lorenm | sse and 3dnow implementations of float->int conversion... |
blob | commitdiff | raw | diff to current |
next |