239fdf1b4a
x86: build: replace mmx2 by mmxext
...
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.
2012-08-03 22:51:05 +02:00
2254b559cb
swscale: make filterPos 32bit.
...
Fixes overflows for large image sizes.
Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind
CC: libav-stable@libav.org
2012-03-06 10:47:41 -08:00
b18f8cbf3d
Revert two swscale commits.
...
Revert "swscale: update context offsets after removal of AlpMmxFilter."
(commit a95e3fa90b9d03cb9fc5
2012-02-19 13:31:12 -08:00
1bab6f852c
swscale: make access to filter data conditional on filter type.
...
Prevents crashes on 1-tap filter (unscaled). Also rename "bguf" argument
to "vbuf", seems that was a typo.
2012-02-17 10:31:15 -08:00
a95e3fa90b
swscale: update context offsets after removal of AlpMmxFilter.
2012-02-17 10:31:15 -08:00
b7542dd3d7
swscale: fix V plane memory location in bilinear/unscaled RGB/YUYV case.
...
Fixes bug 221.
CC: libav-stable@libav.org
2012-02-07 11:33:20 -08:00
b5d08c27c3
swscale: convert rgb/bgr24ToY/UV_mmx functions from inline asm to yasm.
...
Also implement sse2/ssse3/avx versions.
2012-01-27 11:00:30 +08:00
b14fa5572c
swscale: fix crash in fast_bilinear code when compiled with -mred-zone.
...
Additional comments from Måns Rullgard have been integrated
by Reinhard Tartler.
Signed-off-by: Reinhard Tartler <siretart@tauware.de>
2012-01-10 18:20:37 +01:00
2170a0e6ad
swscale: convert yuy2/uyvy/nv12/nv21ToY/UV from inline asm to yasm.
...
Also implement SSE2/AVX variants.
2012-01-08 16:37:43 -08:00
c435653627
swscale: write yuv2plane1 MMX/SSE2/SSE4/AVX functions.
2011-11-05 20:48:14 -07:00
6cacecdca3
swscale: make yuv2yuvX_10_sse2/avx 8/9/16-bits aware.
...
Also implement MMX/MMX2 versions and SSE4 versions.
2011-10-22 10:35:14 -07:00
34e8d147b3
Split out yuv2yuv1 luma and chroma in order to make them generic DSP functions
...
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-10-22 10:35:13 -07:00
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).
2011-09-13 09:53:42 -07:00
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.
2011-08-17 20:56:06 -07:00
28c1115a91
swscale: use 15-bit intermediates for 9/10-bit scaling.
2011-08-12 11:54:25 -07:00
5c391a161a
swscale: rename uv_off/uv_off2 to uv_off_px/byte.
2011-07-08 15:15:31 -07:00
4e3e333a79
swscale: error dithering for 16/9/10-bit to 8-bit.
...
Based on a somewhat similar idea in FFmpeg's swscale copy.
2011-07-08 15:15:30 -07:00
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.
2011-07-08 15:15:30 -07:00
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.
2011-07-01 09:08:26 -07:00
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).
2011-06-29 09:45:52 -07:00
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.
2011-06-27 21:24:44 -07:00
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.
2011-06-27 17:15:41 -07:00
97535ffb97
swscale: remove unused xInc/srcW arguments from hScale().
2011-06-26 14:41:44 -07:00
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.
2011-06-09 09:25:59 -04:00
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).
2011-06-08 11:39:26 -04:00
496d95c34c
swscale: move two macros that are only used once into caller.
...
This way, they look like regular code, which is easier to
understand.
2011-06-08 11:33:46 -04:00
0fb5193156
swscale: reindent x86 init code.
2011-06-07 10:05:50 -04:00
ca364a5b43
swscale: extract SWS_FULL_CHR_H_INT conditional into init code.
2011-06-07 10:03:47 -04:00
bda9b20fa4
swscale: un-special-case yuv2yuvX16_c().
...
Make yuv2yuvX16_c a function pointer for yuv2yuvX(), so that the
function pointer becomes bitdepth-independent.
2011-06-07 10:03:12 -04:00
983260b0a4
swscale: split out x86/swscale_template.c from swscale.c.
2011-06-03 09:52:09 -07:00
b8e893399f
sws: replace all long with int.
...
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2011-05-28 10:03:37 -04:00
009f829dde
swscale: fix crash in bilinear scaling.
2011-05-28 08:59:56 -04:00
5a5a0f1613
swscale: Remove unused variables in x86 code.
...
libswscale/x86/swscale_template.c:2072: warning: unused variable ‘canMMX2BeUsed’
libswscale/x86/swscale_template.c:2145: warning: unused variable ‘canMMX2BeUsed’
libswscale/x86/swscale_template.c:2209: warning: unused variable ‘chrVPixBuf’
libswscale/x86/swscale_template.c:2237: warning: unused variable ‘chrVSrcPtr’
2011-05-27 21:25:57 +02:00
9f5d45025e
swscale: fix non-bitexact yuv2yuv[X2]() MMX/MMX2 functions.
2011-05-27 09:41:48 -04:00
e758573a88
swscale: fix compile on x86-32.
2011-05-26 10:41:27 -04:00
b4a224c5e4
swscale: split chroma buffers into separate U/V planes.
...
Preparatory step to implement support for sizes > VOFW.
2011-05-26 09:31:27 -04:00
836b82e3c9
swscale: reindent h[cy]scale_fast() and updateDitherTables().
2011-05-26 09:31:02 -04:00
e2bad983b5
swscale: reformat x86/swscale_template.c.
...
Interleave macros and code so that it's easier to find the
actual code that belongs to a function. Also reindent where
appropriate and remove dead code.
2011-05-26 09:30:15 -04:00
71d9c33c86
swscale: remove duplicate mmx/mmx2 functions if they are identical.
2011-05-26 09:30:15 -04:00
acb96bc268
swscale: remove if (c->dstFormat) branch from yuv2packed[12X]().
...
This allows cutting up the function in much smaller and easier-
to-maintain chunks.
2011-05-26 09:30:14 -04:00
b6cac9b3bf
swscale: remove if(full_chr_int) from yuv2packed1().
...
If that flag is set, swScale() already proxies the call to
yuv2rgbXinC_full(). Therefore, this flag is never set when
yuv2packed1() is called.
2011-05-26 09:30:14 -04:00
2159a24573
swscale: remove if(accurate_rnd) branch from functions.
2011-05-26 09:30:14 -04:00
0093199184
swscale: Remove commented-out printf cruft.
2011-05-26 03:45:58 +02:00
1bb0f0c925
swscale: remove if(bitexact) branch from functions.
...
Instead, only set the function pointers if bitexact flag is
not set during initialization. Since a change in flags triggers
a re-init anyway, this doesn't situations where flag values
change during runtime.
2011-05-24 14:50:20 -04:00
566b5fbbb3
swscale: remove if(canMMX2BeUsed) conditional.
...
Instead, set function pointers conditionally during init. This
patch also reveals a whole branch of dead assembly code that is
therefore also removed.
2011-05-24 14:50:19 -04:00
aaca69c130
swscale: remove swScale_{c,MMX,MMX2} duplication.
2011-05-24 14:50:15 -04:00
c4fd283a46
swscale: use emms_c().
2011-05-24 14:48:49 -04:00
b9eb2136af
swscale: remove dead macro WRITEBGR24OLD.
2011-05-24 10:46:40 -04:00
1dd4f4be5a
swscale: remove AMD3DNOW "optimizations".
...
The functions are identical to their MMX counterparts. Thus,
pretending that swscale is highly optimized for AMD3DNOW
extensions is a poorly executed practical joke at best.
2011-05-24 10:19:41 -04:00
11ffefefdb
swscale: remove duplicated x86/ functions.
2011-05-24 10:11:26 -04:00
Diego Biurrun
Ronald S. Bultje
Kieran Kunhya
Anton Khirnov