Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/FFmpeg/FFmpeg.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/libavcodec/x86
AgeCommit message (Expand)Author
2012-07-19x86: dsputil: drop some unused CPU flag debug codeDiego Biurrun
2012-07-18vp3: move idct and loop filter pointers to new vp3dsp contextMans Rullgard
2012-07-18build: add CONFIG_VP3DSP, reduce repetition in OBJS listsMans Rullgard
2012-07-06x86: h264_intrapred: Don't add the 'd' suffix to the SPLATB_REG macroMartin Storsjö
2012-07-05x86: h264_intrapred: use newly introduced SPLAT* and PSHUFLW macrosDiego Biurrun
2012-07-05x86inc: add SPLATB_LOAD, SPLATB_REG, PSHUFLW macrosLoren Merritt
2012-07-05x86: h264_intrapred: port to cpuflag macrosDiego Biurrun
2012-07-05vp8: Add ifdef guards around the sse2 loopfilter in the sse2slow branch tooMartin Storsjö
2012-07-04vp8: loopfilter >=sse2 functions need aligned stack on x86-32.Martin Storsjö
2012-07-04dsputilenc: group yasm and inline asm function pointer assignment.Ronald S. Bultje
2012-06-30dsputilenc_mmx: split assignment of ff_sse16_sse2 to SSE2 section.Ronald S. Bultje
2012-06-30x86: fmtconvert: add special asm for float_to_int16_interleave_misc_*Ronald S. Bultje
2012-06-30x86: vc1: fix and enable optimised loop filterMans Rullgard
2012-06-27x86: fft: replace call to memcpy by a loopChristophe Gisquet
2012-06-26x86: fft: elf64: fix PIC buildMans Rullgard
2012-06-25x86: fft: win64: fix stack alignment for memcpy() callMans Rullgard
2012-06-25x86: fft: convert sse inline asm to yasmMans Rullgard
2012-06-25x86: place some inline asm under #if HAVE_INLINE_ASMRonald S. Bultje
2012-06-24h264: use asm cabac reader under a generic conditionMans Rullgard
2012-06-23x86: Only use optimizations with cmov if the CPU supports the instructionDiego Biurrun
2012-06-23x86: remove unused inline asm macros from dsputil_mmx.hMans Rullgard
2012-06-23x86: move some inline asm macros to the only places they are usedMans Rullgard
2012-06-22cosmetics: do not use full path for local headersDiego Biurrun
2012-06-18dwt: remove variable-length arraysRonald S. Bultje
2012-06-08Add a float DSP framework to libavutilJustin Ruggles
2012-05-29x86: use new schema for ASM macrosVitor Sessak
2012-05-22x86: lavc: use %if HAVE_AVX guards around AVX functions in yasm code.Justin Ruggles
2012-05-22Convert vector_fmul range of functions to YASM and add AVX versionsKieran Kunhya
2012-05-16x86: rv40: Mark rv40_weight functions as MMX2; they use MMX2 instructions.Michael Kostylev
2012-05-15ac3dsp: simplify x86 versions of ac3_max_msb_abs_int16Justin Ruggles
2012-05-14x86: use more standard construct for setting ASM functions in FFT codeVitor Sessak
2012-05-12x86: vc1: drop MMX loop filter implementation, which uses MMX2 instructions.Michael Kostylev
2012-05-10rv40dsp x86: MMX/MMX2/3DNow/SSE2/SSSE3 implementations of MCChristophe Gisquet
2012-05-02snowdsp: explicitily state instruction size.Ronald S. Bultje
2012-04-28dsputil x86: revert a test back to its previous valueChristophe GISQUET
2012-04-28rv34dsp x86: implement MMX2 inverse transformChristophe Gisquet
2012-04-28h264: new assembly version of get_cabac for x86_64 with PICRoland Scheidegger
2012-04-28h264: use one table instead of several for cabac functionsRoland Scheidegger
2012-04-28h264: (trivial) remove unneeded macro argument in x86/cabac.hRoland Scheidegger
2012-04-21Remove lowres video decodingMans Rullgard
2012-04-21avcodec: remove AVCodecContext.dsp_maskMans Rullgard
2012-04-16h264: use proper PROLOGUE statement for a function using 8 registers.Ronald S. Bultje
2012-04-13dsputil: fix optimized emu_edge function on Win64.Ronald S. Bultje
2012-04-13ac3dsp: call femms/emms at the end of float_to_fixed24() for 3DNow and SSEJustin Ruggles
2012-04-13h264: fix 10bit biweight functions after recent x86inc.asm fixes.Ronald S. Bultje
2012-04-12build: Consistently handle conditional compilation for all optimization OBJS.Diego Biurrun
2012-04-11x86inc improvements for 64-bitHenrik Gramner
2012-04-10rv40dsp x86: use only one register, for both increment and loop counterChristophe GISQUET
2012-04-10rv40dsp: implement prescaled versions for biweight.Christophe GISQUET
2012-04-04dsputil x86: use SSE float instruction instead of SSE2 integer equivalentChristophe GISQUET
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-01 04:02:59 +0300