FFmpeg

Commit Graph

Author	SHA1	Message	Date
Ronald S. Bultje	c435653627	swscale: write yuv2plane1 MMX/SSE2/SSE4/AVX functions.	13 years ago
Michael Niedermayer	e484b64ce3	sws: fallback to mmx2 when yuv2yuvX_sse3() cannot be used. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	b616600516	sws: replace long by x86_reg in x86 asm Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	9eb867e117	sws: add yuv2yuvX_sse3() Code is about 2x as fast as previous Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	8b4b2ddf8d	sws: x86_32 fix Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	76a3490672	sws: add yuv2yuvX() back and updated to the just 1 plane API Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	4d31f42020	sws: port to thw new 1 plane API and add back yuv2yuv1_ar(). Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	f15359727d	sws: better MOVNTQ macro Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Ronald S. Bultje	9e66b892e8	swscale: add missing colons to x86 assembly yuv2planeX. This fixes assembling using "nasm".	13 years ago
Michael Niedermayer	1ac5b51203	swscale: disable functions that do not yet work Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Ronald S. Bultje	6cacecdca3	swscale: make yuv2yuvX_10_sse2/avx 8/9/16-bits aware. Also implement MMX/MMX2 versions and SSE4 versions.	13 years ago
Kieran Kunhya	7fbbf95293	yuv2planeX10 SIMD Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>	13 years ago
Kieran Kunhya	34e8d147b3	Split out yuv2yuv1 luma and chroma in order to make them generic DSP functions Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>	13 years ago
Ronald S. Bultje	6aa3cac6bf	swscale: use aligned move for storage into temporary buffer. The intermediate buffer is always aligned.	13 years ago
Michael Niedermayer	bd141af460	swscale: Fix prototypes of *toyv12 so they can be used with planar rgb input. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Reimar Döffinger	424bcc46b5	Compile x86/swscale_template with -mno-red-zone. Replaces a very hackish hack to fix the same issue (call instruction overwriting stack variables). Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>	13 years ago
Reimar Döffinger	c928e91729	Hack around gcc 4.6 breaking asm using call. gcc 4.6 no longer decrements esp to account for local variables. Thus using call will end up overwriting some local variable. So add an extra one it can safely clobber. This is a huge hack because it's basically pure chance it works, no idea how this is supposed to be done. Fixes trac ticket #397. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>	13 years ago
Michael Niedermayer	d06c5b44cc	swscale: drop redundant code. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Michael Niedermayer	1eb8014b49	swscale: add 14bit support to the "MMX/SSE2/SSSE3/SSE4 versions for horizontal scaling" Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	13 years ago
Ronald S. Bultje	e0c3e07387	sws: implement MMX/SSE2/SSSE3/SSE4 versions for horizontal scaling. 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).	13 years ago
Michael Niedermayer	27bf599350	swscale: Fix unused asm and enable it Author of the fix is ronald, the enabling & commit message are mine. This fixes commit `4e3e333a79` Author: Ronald S. Bultje <rsbultje@gmail.com> Date: Tue Jul 5 12:49:11 2011 -0700 swscale: error dithering for 16/9/10-bit to 8-bit. Based on a somewhat similar idea in FFmpeg's swscale copy. The Fix was originally commited in: (and i missed it due to the commit message) commit `5c391a161a` Author: Ronald S. Bultje <rsbultje@gmail.com> Date: Fri Jul 8 14:39:04 2011 -0700 swscale: rename uv_off/uv_off2 to uv_off_px/byte.	14 years ago
Reimar Döffinger	746f1f14de	Remove unused variables. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>	14 years ago
Ronald S. Bultje	3f04ab4fcd	swscale: split hScale() function pointer into h[cy]Scale(). 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.	14 years ago
Ronald S. Bultje	28c1115a91	swscale: use 15-bit intermediates for 9/10-bit scaling.	14 years ago
Ronald S. Bultje	c59f9a68e2	swscale: error dithering for 16/9/10-bit to 8-bit. Based on a somewhat similar idea in FFmpeg's swscale copy.	14 years ago
Ronald S. Bultje	ac9ac45aca	swscale: fix 16-bit scaling when output is 8-bits. We would use the second half of the U plane buffer, rather than the V plane buffer, to output the V plane pixels.	14 years ago
Michael Niedermayer	ca78fa24b7	sws: disable scale16 when int32 is used	14 years ago
Michael Niedermayer	987e4c1787	sws: fix rgb -> 16bit	14 years ago
Ronald S. Bultje	948ccdadf4	swscale: for >8bit scaling, read in native bit-depth. For 9/10bit, it means we don't have to upscale to 16bit before actual scaling or pixel format conversion, and thus a performance gain.	14 years ago
Ronald S. Bultje	5c391a161a	swscale: rename uv_off/uv_off2 to uv_off_px/byte.	14 years ago
Ronald S. Bultje	4e3e333a79	swscale: error dithering for 16/9/10-bit to 8-bit. Based on a somewhat similar idea in FFmpeg's swscale copy.	14 years ago
Ronald S. Bultje	42d622fab3	swscale: fix 16-bit scaling when output is 8-bits. We would use the second half of the U plane buffer, rather than the V plane buffer, to output the V plane pixels.	14 years ago
Ronald S. Bultje	8a8d0ce208	swscale: for >8bit scaling, read in native bit-depth. For 9/10bit, it means we don't have to upscale to 16bit before actual scaling or pixel format conversion, and thus a performance gain.	14 years ago
Ronald S. Bultje	45f6ffe5e9	swscale: implement >8bit scaling support. This means that precision is retained when scaling between sample formats with >8 bits per component (48bit RGB, 16bit grayscale, 9/10/16bit YUV).	14 years ago
Ronald S. Bultje	ef1ee362b3	swscale: implement >8bit scaling support. This means that precision is retained when scaling between sample formats with >8 bits per component (48bit RGB, 16bit grayscale, 9/10/16bit YUV).	14 years ago
Ronald S. Bultje	13a099799e	swscale: change prototypes of scaled YUV output functions. Remove unused variables "flags" and "dstFormat" in yuv2packed1, merge source rows per plane for yuv2packed[12], and make every source argument int16_t (some where invalidly set to uint16_t). This prevents stack pollution and is part of the Great Evil Plan to simplify swscale.	14 years ago
Ronald S. Bultje	0d994b2f45	swscale: don't use planar output functions to write to NV12/21. This prevents a crash when converting to NV12/21 without the bitexact flags enabled.	14 years ago
Ronald S. Bultje	97535ffb97	swscale: remove unused xInc/srcW arguments from hScale().	14 years ago
Diego Biurrun	a60466dbc3	swscale: Remove HAVE_MMX from files that are only compiled with MMX enabled.	14 years ago
Diego Biurrun	97e057ff81	swscale: Fix compilation with --disable-mmx2. Some MMX2 functions were being referenced without proper #ifdefs.	14 years ago
Ronald S. Bultje	a27db4c349	swscale: fix function declaration keywords in x86/swscale_template.c. Remove inline keyword for functions that are only called through their function pointers (and thus cannot be inlined); add av_cold keyword to init function, and use av_always_inline instead of inline for functions that must be inlined for performance reasons.	14 years ago
Ronald S. Bultje	9bcbb250e2	swscale: fix types of assembly arguments. This prevents the following compiler warnings: "warning: initialization from incompatible pointer type". Since the variables are only ever used in inline assembly, their type is actually irrelevant (so the part where it was wrong did not invoke any buggy behaviour).	14 years ago
Ronald S. Bultje	496d95c34c	swscale: move two macros that are only used once into caller. This way, they look like regular code, which is easier to understand.	14 years ago
Ronald S. Bultje	0fb5193156	swscale: reindent x86 init code.	14 years ago
Ronald S. Bultje	ca364a5b43	swscale: extract SWS_FULL_CHR_H_INT conditional into init code.	14 years ago
Ronald S. Bultje	bda9b20fa4	swscale: un-special-case yuv2yuvX16_c(). Make yuv2yuvX16_c a function pointer for yuv2yuvX(), so that the function pointer becomes bitdepth-independent.	14 years ago
Michael Niedermayer	ba91bf58cd	swscale: override the lack of the accurate rounding flag when needed for dither. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	14 years ago
Ronald S. Bultje	983260b0a4	swscale: split out x86/swscale_template.c from swscale.c.	14 years ago
Baptiste Coudurier	5aa70309ad	In libswscale, use all lines when converting from 422p to rgb with mmx, improve quality. Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	14 years ago
Michael Niedermayer	6713989c23	swscale: dither for planar yuv outputs Signed-off-by: Michael Niedermayer <michaelni@gmx.at>	14 years ago

1 2 3 4 5 ...

275 Commits (61883a2e896a3e427358b11ed73fbb4fdaf8c739)