| Commit message (Expand) | Author | Age | Files | Lines |
* | x86: Replace checks for CPU extensions and flags by convenience macros | Diego Biurrun | 2012-09-08 | 1 | -4/+3 |
* | x86: float_dsp: fix ff_vector_fmac_scalar_avx() on Win64 | Justin Ruggles | 2012-09-07 | 1 | -3/+3 |
* | x86: Add convenience macros to check for CPU extensions and flags | Diego Biurrun | 2012-09-04 | 1 | -0/+57 |
* | x86: Split inline and external assembly #ifdefs | Diego Biurrun | 2012-08-31 | 1 | -2/+2 |
* | x86: cosmetics: Comment some #endifs for better readability | Diego Biurrun | 2012-08-30 | 1 | -2/+2 |
* | vf_hqdn3d: x86 asm | Loren Merritt | 2012-08-26 | 1 | -0/+1 |
* | lavr: x86: optimized 6-channel s16 to fltp conversion | Justin Ruggles | 2012-08-23 | 1 | -0/+12 |
* | x86: remove FASTDIV inline asm | Mans Rullgard | 2012-08-22 | 1 | -37/+0 |
* | Add more missing includes after removing the implicit common.h | Martin Storsjö | 2012-08-16 | 1 | -0/+1 |
* | Add some more missing includes after removing the implicit common.h | Martin Storsjö | 2012-08-15 | 1 | -0/+1 |
* | x86: move MANGLE() and related macros to libavutil/x86/asm.h | Mans Rullgard | 2012-08-09 | 1 | -0/+12 |
* | x86: rename libavutil/x86_cpu.h to libavutil/x86/asm.h | Mans Rullgard | 2012-08-09 | 2 | -1/+99 |
* | x86: fix build with nasm 2.08 | Mans Rullgard | 2012-08-07 | 1 | -11/+7 |
* | x86: use nop cpu directives only if supported | Mans Rullgard | 2012-08-07 | 1 | -3/+9 |
* | x86: fix rNmp macros with nasm | Mans Rullgard | 2012-08-07 | 1 | -2/+2 |
* | x86: add colons after labels | Mans Rullgard | 2012-08-07 | 1 | -2/+2 |
* | x86: build: replace mmx2 by mmxext | Diego Biurrun | 2012-08-03 | 1 | -2/+2 |
* | x86: Use consistent 3dnowext function and macro name suffixes | Diego Biurrun | 2012-08-03 | 1 | -1/+1 |
* | x86inc: clip num_args to 7 on x86-32. | Loren Merritt | 2012-07-28 | 1 | -0/+3 |
* | x86inc: sync to latest version from x264. | Ronald S. Bultje | 2012-07-28 | 1 | -92/+124 |
* | x86: add support for fmaddps fma4 instruction with abstraction to avx/sse | Justin Ruggles | 2012-07-27 | 1 | -5/+11 |
* | x86inc: automatically insert vzeroupper for YMM functions. | Ronald S. Bultje | 2012-07-26 | 2 | -13/+12 |
* | dsputil: x86: add SHUFFLE_MASK_W macro | Jason Garrett-Glaser | 2012-07-22 | 1 | -0/+12 |
* | x86/cpu: implement get/set_eflags using intrinsics | Ronald S. Bultje | 2012-07-10 | 1 | -0/+14 |
* | x86/cpu: implement support for cpuid through intrinsics | Ronald S. Bultje | 2012-07-10 | 1 | -0/+14 |
* | x86/cpu: implement support for xgetbv through intrinsics | Ronald S. Bultje | 2012-07-10 | 1 | -0/+11 |
* | x86/timer: implement an intrinsic-based version for rdtsc (AV_READ_TIME). | Ronald S. Bultje | 2012-07-07 | 1 | -0/+8 |
* | x86inc: add SPLATB_LOAD, SPLATB_REG, PSHUFLW macros | Loren Merritt | 2012-07-05 | 1 | -4/+37 |
* | x86inc: modify ALIGN to not generate long nops on i586 | Loren Merritt | 2012-07-05 | 1 | -0/+4 |
* | x86: cpu: clean up check for cpuid instruction support | Mans Rullgard | 2012-07-01 | 1 | -20/+16 |
* | x86: cpu: whitespace (mostly) cosmetics | Mans Rullgard | 2012-06-25 | 1 | -34/+36 |
* | x86: place some inline asm under #if HAVE_INLINE_ASM | Ronald S. Bultje | 2012-06-25 | 2 | -0/+5 |
* | x86: Add CPU flag for the i686 cmov instruction | Diego Biurrun | 2012-06-23 | 1 | -0/+2 |
* | float_dsp: add x86-optimized functions for vector_fmac_scalar() | Justin Ruggles | 2012-06-18 | 2 | -0/+54 |
* | Add a float DSP framework to libavutil | Justin Ruggles | 2012-06-08 | 3 | -0/+99 |
* | x86: Avoid movs on BUTTERFLYPS when in AVX mode | Vitor Sessak | 2012-05-29 | 1 | -7/+6 |
* | lavr: replace the SSE version of ff_conv_fltp_to_flt_6ch() with SSE4 and AVX | Justin Ruggles | 2012-05-09 | 1 | -4/+3 |
* | Add libavresample | Justin Ruggles | 2012-04-24 | 1 | -0/+9 |
* | x86inc: support AVX abstraction for 2-operand instructions | Loren Merritt | 2012-04-18 | 1 | -2/+8 |
* | build: Move all arch OBJS declarations into arch subdirectory Makefiles. | Diego Biurrun | 2012-04-12 | 1 | -0/+1 |
* | x86inc improvements for 64-bit | Henrik Gramner | 2012-04-11 | 1 | -104/+114 |
* | x86inc: add *mp named argument support to DEFINE_ARGS. | Ronald S. Bultje | 2012-03-14 | 1 | -0/+2 |
* | x86inc: don't "bake" stack_offset in named arguments. | Loren Merritt | 2012-03-03 | 1 | -1/+4 |
* | x86inc: support yasm -f win64 flag also. | Haruhiko Yamagata | 2012-02-08 | 1 | -0/+2 |
* | x86inc: allow manual use of WIN64_SPILL_XMM. | Henrik Gramner | 2012-02-08 | 1 | -4/+5 |
* | win64: add a XMM clobber test configure option. | Ronald S. Bultje | 2012-02-02 | 1 | -0/+71 |
* | x86inc.asm: fix typo. | Ronald S. Bultje | 2012-01-27 | 1 | -1/+1 |
* | config.asm: change %ifdef directives to %if directives. | Ronald S. Bultje | 2012-01-27 | 2 | -14/+16 |
* | mpegaudiodec: optimized iMDCT transform | Vitor Sessak | 2012-01-08 | 1 | -0/+2 |
* | x86: bswap: remove test for bswap instruction | Mans Rullgard | 2011-12-12 | 1 | -7/+0 |