Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | x86: rename libavutil/x86_cpu.h to libavutil/x86/asm.h | Mans Rullgard | 2012-08-09 |
| | | | | | | | This puts x86-specific things in the x86/ subdirectory where they belong. Signed-off-by: Mans Rullgard <mans@mansr.com> | ||
* | x86: build: replace mmx2 by mmxext | Diego Biurrun | 2012-08-03 |
| | | | | | | | Refactoring mmx2/mmxext YASM code with cpuflags will force renames. So switching to a consistent naming scheme beforehand is sensible. The name "mmxext" is more official and widespread and also the name of the CPU flag, as reported e.g. by the Linux kernel. | ||
* | swscale: Mark all init functions as av_cold | Diego Biurrun | 2012-07-23 |
| | |||
* | swscale: x86: Drop pointless _mmx suffix from filenames | Diego Biurrun | 2012-07-23 |
| | | | | The files do not contain only MMX code. | ||
* | x86: swscale: Place inline assembly code under appropriate #ifdefs | Ronald S. Bultje | 2012-07-21 |
| | | | | | | Fixes compilation for compilers that do not support gcc inline assembly. Signed-off-by: Diego Biurrun <diego@biurrun.de> | ||
* | swscale: yuv2planeX 8bit >=sse2 functions need aligned stack on x86-32. | Martin Storsjö | 2012-07-04 |
| | | | | Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> | ||
* | build: Move all arch OBJS declarations into arch subdirectory Makefiles. | Diego Biurrun | 2012-04-12 |
| | |||
* | x86inc improvements for 64-bit | Henrik Gramner | 2012-04-11 |
| | | | | | | | | | | | | Add support for all x86-64 registers Prefer caller-saved register over callee-saved on WIN64 Support up to 15 function arguments Also (by Ronald S. Bultje) Fix up our asm to work with new x86inc.asm. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> Signed-off-by: Justin Ruggles <justin.ruggles@gmail.com> | ||
* | swscale: convert hscale() to use named arguments. | Ronald S. Bultje | 2012-03-14 |
| | |||
* | swscale: convert hscale to cpuflags(). | Ronald S. Bultje | 2012-03-14 |
| | |||
* | swscale: make filterPos 32bit. | Ronald S. Bultje | 2012-03-06 |
| | | | | | | | Fixes overflows for large image sizes. Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind CC: libav-stable@libav.org | ||
* | swscale: make %rep unconditional. | Ronald S. Bultje | 2012-03-03 |
| | | | | Fixes pre-processing with latest versions of nasm. | ||
* | swscale: remove now unnecessary hack. | Ronald S. Bultje | 2012-03-03 |
| | |||
* | swscale: take first/lastline over/underflows into account for MMX. | Ronald S. Bultje | 2012-02-23 |
| | | | | | | | Fixes crashes for extremely large resizes (several 100-fold). Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind CC: libav-stable@libav.org | ||
* | Revert two swscale commits. | Ronald S. Bultje | 2012-02-19 |
| | | | | | | | | | | | Revert "swscale: update context offsets after removal of AlpMmxFilter." (commit a95e3fa90b4190381b65d180eec5a4027075e2da) and Revert "swscale: Remove some write-only variables related to alpha handling." (commit 9d03cb9fc5ddf914920ab0dbe13f19a34c754966). They broke alpha handling - it's the evil inline asm that still uses that variable, so it's not truely write-only. | ||
* | swscale: make access to filter data conditional on filter type. | Ronald S. Bultje | 2012-02-17 |
| | | | | | Prevents crashes on 1-tap filter (unscaled). Also rename "bguf" argument to "vbuf", seems that was a typo. | ||
* | swscale: update context offsets after removal of AlpMmxFilter. | Ronald S. Bultje | 2012-02-17 |
| | |||
* | swscale: Remove some write-only variables related to alpha handling. | Diego Biurrun | 2012-02-14 |
| | |||
* | swscale: fix crashes in yuv2yuvX on x86-32. | Ronald S. Bultje | 2012-02-13 |
| | | | | | | They were introduced in an earlier commit that introduced use of named arguments. One cause was a typo, a second cause appears to be a bug in x264asm that I work around by not using named arguments. | ||
* | swscale: convert yuv2yuvX() to using named arguments. | Ronald S. Bultje | 2012-02-12 |
| | |||
* | swscale: rename "dstw" to "w" to prevent name collisions. | Ronald S. Bultje | 2012-02-12 |
| | | | | | "dstw" can collide with the word-version of the "dst" argument, causing all kind of weird stuff down the pipe. | ||
* | swscale: use named registers in yuv2yuv1_plane() place. | Ronald S. Bultje | 2012-02-12 |
| | | | | | Most of the function had been converted before, but I forgot this particular location. | ||
* | swscale: sign-extend integer function argument to qword on x86-64. | Ronald S. Bultje | 2012-02-08 |
| | |||
* | swscale: make yuv2yuv1 use named registers. | Ronald S. Bultje | 2012-02-07 |
| | |||
* | swscale: fix V plane memory location in bilinear/unscaled RGB/YUYV case. | Ronald S. Bultje | 2012-02-07 |
| | | | | | | Fixes bug 221. CC: libav-stable@libav.org | ||
* | win64: add a XMM clobber test configure option. | Ronald S. Bultje | 2012-02-02 |
| | | | | | | | This will be useful to test more aggressively for failures to mark XMM registers as clobbered in Win64 builds, and prevent regressions thereof. Based on a patch by Ramiro Polla <ramiro.polla@gmail.com> | ||
* | swscale: implement MMX, SSE2 and AVX functions for RGB32 input. | Ronald S. Bultje | 2012-02-01 |
| | |||
* | swscale: enable dithering in MMX functions. | Ronald S. Bultje | 2012-02-01 |
| | | | | | | This was accidently disabled. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> | ||
* | swscale: make rgb24 function macros slightly smaller. | Ronald S. Bultje | 2012-02-01 |
| | |||
* | swscale: convert rgb/bgr24ToY/UV_mmx functions from inline asm to yasm. | Ronald S. Bultje | 2012-01-27 |
| | | | | Also implement sse2/ssse3/avx versions. | ||
* | config.asm: change %ifdef directives to %if directives. | Ronald S. Bultje | 2012-01-27 |
| | | | | This allows combining multiple conditionals in a single statement. | ||
* | swscale: change yuv2yuvX code to use cpuflag(). | Ronald S. Bultje | 2012-01-13 |
| | |||
* | swscale: fix crash in fast_bilinear code when compiled with -mred-zone. | Ronald S. Bultje | 2012-01-10 |
| | | | | | | | Additional comments from Måns Rullgard have been integrated by Reinhard Tartler. Signed-off-by: Reinhard Tartler <siretart@tauware.de> | ||
* | swscale: specify register type. | Oka Motofumi | 2012-01-10 |
| | | | | | | Fixes a compilation failure on win64. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> | ||
* | swscale: convert yuy2/uyvy/nv12/nv21ToY/UV from inline asm to yasm. | Ronald S. Bultje | 2012-01-08 |
| | | | | Also implement SSE2/AVX variants. | ||
* | swscale: split scale.asm. | Ronald S. Bultje | 2012-01-03 |
| | | | | | scale.asm keeps horizontal scaling functions, whereas output.asm gets the vertical scaling/output functions. | ||
* | swscale_mmx: drop no longer required parameters from VSCALEX macros | Diego Biurrun | 2011-12-14 |
| | |||
* | swscale: Mark yuv2planeX_8_mmx as MMX2; it contains MMX2 instructions. | Diego Biurrun | 2011-12-14 |
| | |||
* | Remove extraneous semicolons | Mans Rullgard | 2011-12-11 |
| | | | | | | These semicolons cause invalid empty top-level declarations. Signed-off-by: Mans Rullgard <mans@mansr.com> | ||
* | swscale: handle unaligned buffers in yuv2plane1 | Ronald S. Bultje | 2011-11-13 |
| | | | | | | | The issue had been introduced in c435653627529e22d74214c2266f571255e404d6 Signed-off-by: Luca Barbato <lu_zero@gentoo.org> | ||
* | swscale: write yuv2plane1 MMX/SSE2/SSE4/AVX functions. | Ronald S. Bultje | 2011-11-05 |
| | |||
* | swscale: add missing colons to x86 assembly yuv2planeX. | Ronald S. Bultje | 2011-10-23 |
| | | | | This fixes assembling using "nasm". | ||
* | swscale: make yuv2yuvX_10_sse2/avx 8/9/16-bits aware. | Ronald S. Bultje | 2011-10-22 |
| | | | | Also implement MMX/MMX2 versions and SSE4 versions. | ||
* | yuv2planeX10 SIMD | Kieran Kunhya | 2011-10-22 |
| | | | | Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> | ||
* | Split out yuv2yuv1 luma and chroma in order to make them generic DSP functions | Kieran Kunhya | 2011-10-22 |
| | | | | Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> | ||
* | swscale: use aligned move for storage into temporary buffer. | Ronald S. Bultje | 2011-10-11 |
| | | | | The intermediate buffer is always aligned. | ||
* | sws: implement MMX/SSE2/SSSE3/SSE4 versions for horizontal scaling. | Ronald S. Bultje | 2011-09-13 |
| | | | | | | Speed: from 3.9x to 9.6x speed improvement over C, and some small (up to 15%) speed improvements over existing MMX code (particularly for bigger filters). | ||
* | swscale: split hScale() function pointer into h[cy]Scale(). | Ronald S. Bultje | 2011-08-17 |
| | | | | | | This allows using more specific implementations for chroma/luma, e.g. we can make assumptions on filterSize being constant, thus avoiding that test at runtime. | ||
* | swscale: use 15-bit intermediates for 9/10-bit scaling. | Ronald S. Bultje | 2011-08-12 |
| | |||
* | swscale: rename uv_off/uv_off2 to uv_off_px/byte. | Ronald S. Bultje | 2011-07-08 |
| |