Commit Graph

378 Commits

Author SHA1 Message Date
Andreas Rheinhardt f3c197b129 Include attributes.h directly
Some files currently rely on libavutil/cpu.h to include it for them;
yet said file won't use include it any more after the currently
deprecated functions are removed, so include attributes.h directly.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2021-04-19 14:34:10 +02:00
Alan Kelly 3ce8d09244 libswscale/x86/yuv2yuvX: Removes unrolling for mmx and mmxext
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2021-04-01 20:47:52 +02:00
Alan Kelly dc57762cb4 libswscale/x86/swscale: Only call ff_yuv2yuvX functions if the input size is > 0
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2021-04-01 20:47:52 +02:00
Andreas Rheinhardt c23a5523b5 swscale/x86/swscale: Remove unused ASM constants
The last user of g15Mask, r15Mask, g16Mask and r16Mask was disabled
in 77a416e8aa and finally removed in
36e8de07ed62609df45d064b56501e3084d25723; b15Mask and b16Mask were
apparently always unused (except for in_asm_used_var_warning_killer,
a function that only existed to make the compiler not optimize ASM
constants away).
w10 is unused since d604bab901, w02
since ef423a6618.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
2021-02-24 09:47:54 +01:00
Andreas Rheinhardt aad597a93c swscale/x86/rgb2rgb: Remove unused ASM constants
mask24hh etc. are unused since f099fbf5f3,
mask32b and mask32r since 296609f859,
mask32g since b38d487466 and mask32 since
f8a138be52.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
2021-02-24 09:45:17 +01:00
Andreas Rheinhardt 49db6e4b4e swscale/x86/yuv2rgb: Remove unused ASM constants
mmx_grnmask is unused since 531f97b0c3,
the other constants since e934194b6a.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
2021-02-24 09:43:14 +01:00
James Almer 1a555d3c60 swscale/x86/yuv2yuvX: use the movsxdifnidn helper macro
Simplifies code

Signed-off-by: James Almer <jamrial@gmail.com>
2021-02-18 18:47:43 -03:00
James Almer ebb48d85a0 swscale/x86/yuv2yuvX: use movq to load 8 bytes in all non-AVX2 functions
mova expands to movq on non-XMM functions

Signed-off-by: James Almer <jamrial@gmail.com>
2021-02-18 18:47:43 -03:00
James Almer d512ebbaed swscale/x86/yuv2yuvX: use the SPLATW helper macro
Simplifies code

Signed-off-by: James Almer <jamrial@gmail.com>
2021-02-18 18:47:43 -03:00
James Almer c00567647e swscale/x86/swscale: fix mix of inline and external function definitions
This includes removing pointless static function forward declarations.

Signed-off-by: James Almer <jamrial@gmail.com>
2021-02-18 18:47:42 -03:00
James Almer c2bf1dcace swscale/x86/swscale: fix compilation with old yasm
Where AVX2 may not be supported.

Signed-off-by: James Almer <jamrial@gmail.com>
2021-02-17 21:09:36 -03:00
Alan Kelly 554c2bc708 swscale: move yuv2yuvX_sse3 to yasm, unrolls main loop
And other small optimizations for ~20% speedup.
2021-02-17 21:21:03 +01:00
Anton Khirnov e15371061d lavu/mem: move the DECLARE_ALIGNED macro family to mem_internal on next+1 bump
They are not properly namespaced and not intended for public use.
2021-01-01 14:14:57 +01:00
Carl Eugen Hoyos 46e362b765 lsws/x86/yuv2rgb: Fix compilation with mmxext or ssse3 disabled.
Fixes ticket #8986.
2020-11-14 15:37:57 +01:00
Marton Balint 993429cfb4 swscale/x86/yuv2rgb: fix crashes when loading alpha from unaligned buffers
Regression since fc6a5883d6 on SSSE3 enabled
CPUs.

Fixes ticket #8955.

Signed-off-by: Marton Balint <cus@passwd.hu>
2020-11-02 00:31:34 +01:00
James Almer 621e2625e0 swscale/x86/output: add missing AVX2 support preprocessor wrappers
Fixes compilation with old yasm

Signed-off-by: James Almer <jamrial@gmail.com>
2020-08-20 15:14:56 -03:00
James Almer ba3e771a42 x86/yuv2rgb: fix crashes when storing data on unaligned buffers
Regression since fc6a5883d6 on SSSE3 enabled
CPUs.

Fixes ticket #8747

Signed-off-by: James Almer <jamrial@gmail.com>
2020-07-14 14:06:04 -03:00
Nelson Gomez bc01337db4 swscale/x86/output: add AVX2 version of yuv2nv12cX
256 bits is just wide enough to fit all the operands needed to vectorize
the software implementation, but AVX2 is needed to for a couple of
instructions like cross-lane permutation.

Output is bit-for-bit identical to C.

Signed-off-by: Nelson Gomez <nelson.gomez@microsoft.com>
2020-06-14 16:34:07 +01:00
Ruiling Song 4700f7d6fc swscale/swscale: remove useless code
Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2020-04-03 00:58:07 +02:00
Ting Fu 828f7db5d9 libswscale/x86/yuv2rgb: Fix Segmentation Fault when load unaligned data
Fixes ticket #8532

Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-02-26 11:10:46 +01:00
Ting Fu fc6a5883d6 libswscale/x86/yuv2rgb: add ssse3 version
Tested using this command:
/ffmpeg -pix_fmt yuv420p -s 1920*1080 -i ArashRawYuv420.yuv \
-vcodec rawvideo -s 1920*1080 -pix_fmt rgb24 -f null /dev/null

The fps increase from 389 to 640 on Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz

Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-02-10 15:08:33 +01:00
Ting Fu e934194b6a libswscale/x86/yuv2rgb: Change inline assembly into nasm code
The original inline assembly and nasm code have the same fps when called by command.
NASM code almost has no impact on the perfromance.

Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2020-02-05 17:41:59 +01:00
Andreas Rheinhardt 736c7c20e7 swscale/x86/swscale: Fix undefined left shifts of negative numbers
This affected many FATE-tests: The number of failing tests went down
from 663 to 344. (Both numbers exclude tests that failed because of
unaligned accesses in code that is inside #if HAVE_FAST_UNALIGNED.)

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2019-09-28 17:24:32 +02:00
Philip Langdale cd48318035 swscale: Add support for NV24 and NV42
The implementation is pretty straight-forward. Most of the existing
NV12 codepaths work regardless of subsampling and are re-used as is.
Where necessary I wrote the slightly different NV24 versions.

Finally, the one thing that confused me for a long time was the
asm specific x86 path that did an explicit exclusion check for NV12.
I replaced that with a semi-planar check and also updated the
equivalent PPC code, which Lauri kindly checked.
2019-05-12 07:51:02 -07:00
Martin Vignali 658bbc0060 swscale/x86/rgb2rgb.asm : add Ivo Van Poorten name to the top of the file
suggested by Carl Eugen Hoyos
2018-10-18 21:43:19 +02:00
Martin Vignali 296609f859 swscale/x86/rgb2rgb : port shuffle 2103 mmxext to external asm and remove inline asm version 2018-10-13 14:12:41 +02:00
Martin Vignali 04afdbb560 swscale/x86/rgb2rgb : remove mmx version for shuffle2103 2018-10-13 14:12:36 +02:00
Sergey Lavrushkin 582bc5a348 libswscale: Adds conversions from/to float gray format.
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-08-14 18:22:39 +02:00
Martin Vignali 07a566e7d6 swscale/swscale_unscaled : add X86_64 (SSE2 and AVX) for uyvyto422
and checkasm test
2018-04-22 19:15:32 +02:00
Martin Vignali 1ba5ca2d72 swscale/rgb : add X86 SIMD (SSSE3), for shuffle_bytes_1230, shuffle_bytes_3012, shuffle_bytes_3210 2018-03-24 20:22:08 +01:00
Martin Vignali 923a324174 swscale/rgb : add X86 SIMD (SSSE3) for shuffle_bytes_2103 and shuffle_bytes_0321 2018-03-24 20:21:58 +01:00
Thomas Köppe 43171a2a73 Fix missing used attribute for inline assembly variables
Variables used in inline assembly need to be marked with attribute((used)).
Static constants already were, via the define of DECLARE_ASM_CONST.
But DECLARE_ALIGNED does not add this attribute, and some of the variables
defined with it are const only used in inline assembly, and therefore
appeared dead. This change adds a macro DECLARE_ASM_ALIGNED that marks
variables as used.

This change makes FFMPEG work with Clang's ThinLTO.

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2017-11-13 03:58:34 +01:00
James Almer 2904db9045 Merge commit '994c4bc10751e39c7ed9f67ffd0c0dea5223daf2'
* commit '994c4bc10751e39c7ed9f67ffd0c0dea5223daf2':
  x86util: Port all macros to cpuflags

See d5f8a642f6

Merged-by: James Almer <jamrial@gmail.com>
2017-10-21 12:15:57 -03:00
Diego Biurrun fd502f4f5f build: Generalize yasm/nasm-related variable names
None of them are specific to the YASM assembler.

(Cherry-picked from libav commit 39e208f4d4)

Signed-off-by: James Almer <jamrial@gmail.com>
2017-06-21 17:00:29 -03:00
Diego Biurrun 994c4bc107 x86util: Port all macros to cpuflags
Also do some small cosmetic changes: Drop pointless _MMX suffix from ABSD2
macro name, drop pointless check for MMX support, we always assume MMX is
available in our SIMD code, fix spelling.
2017-03-14 17:23:32 +01:00
Diego Biurrun 39e208f4d4 build: Generalize yasm/nasm-related variable names
None of them are specific to the YASM assembler.
2017-03-01 10:18:15 +01:00
Andreas Cadhalpun 319438e2f2 swscale: save ebx register when it is not available
Configure checks if the ebx register can be used for asm and it has to
be saved if and only if this is not the case.
Without this the build fails when configuring with --toolchain=hardened
--disable-pic on i386 using gcc 4.8:
error: PIC register clobbered by '%ebx' in 'asm'

In that case gcc 4.8 reserves the ebx register for the GOT needed for
PIE, so it can't be used in asm directly.

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Andreas Cadhalpun <Andreas.Cadhalpun@googlemail.com>
2016-12-21 01:26:10 +01:00
Michael Niedermayer d736b52a04 swscale: Drop is9_OR_10BPS() use, its name is not correct
Found-by: Luca Barbato
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2016-11-10 00:33:12 +01:00
Michael Niedermayer f59750641a swscale: x86: Add some forgotten 12-bit planar YUV cases
Signed-off-by: Diego Biurrun <diego@biurrun.de>
2016-10-12 17:39:30 +02:00
Michael Niedermayer 328ea6a9a5 swscale: Add input support for 12-bit formats
Implemented for AV_PIX_FMT_GBRP12.

Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
2016-10-12 17:39:30 +02:00
Luca Barbato 2b5b1e1e9b swscale: Rename is9_OR_10 to match what it does
It is used to select functions that work with 9-15bits.
2016-09-27 18:48:30 +02:00
Luca Barbato e87a501e7d swscale: Update bitdepth range check
Make sure the scaling functions for the 9-15bits are used for
9-15bits bit depths correctly.
2016-09-27 17:17:54 +02:00
Timo Rothenpieler 99882d05a6 swscale: add support for P010LE/BE output 2016-08-31 13:19:46 +02:00
Diego Biurrun facdfe4080 swscale: Add proper ff_ prefix to init functions
They are internal symbols that should not be exported.

based on a patch by Andreas Cadhalpun <Andreas.Cadhalpun@googlemail.com>

Signed-off-by: Diego Biurrun <diego@biurrun.de>
2016-07-16 17:38:37 +02:00
Matthieu Bouron 9eb3da2f99 asm: FF_-prefix internal macros used in inline assembly
See merge commit '39d6d3618d48625decaff7d9bdbb45b44ef2a805'.
2016-06-27 17:21:18 +02:00
Hendrik Leppkes c142dc203e Merge commit 'dc40a70c5755bccfb1a1349639943e1f408bea50'
* commit 'dc40a70c5755bccfb1a1349639943e1f408bea50':
  Drop unnecessary libavutil/x86/asm.h #includes

Merged-by: Hendrik Leppkes <h.leppkes@gmail.com>
2016-06-26 15:53:00 +02:00
Clément Bœsch 8ef57a0d61 Merge commit '41ed7ab45fc693f7d7fc35664c0233f4c32d69bb'
* commit '41ed7ab45fc693f7d7fc35664c0233f4c32d69bb':
  cosmetics: Fix spelling mistakes

Merged-by: Clément Bœsch <u@pkh.me>
2016-06-21 21:55:34 +02:00
Diego Biurrun dc40a70c57 Drop unnecessary libavutil/x86/asm.h #includes 2016-05-28 19:18:26 +02:00
Diego Biurrun 1e9c5bf4c1 asm: FF_-prefix internal macros used in inline assembly
These warnings conflict with system macros on Solaris, producing
truckloads of warnings about macro redefinition.
2016-05-28 19:18:26 +02:00
Vittorio Giovara 41ed7ab45f cosmetics: Fix spelling mistakes
Signed-off-by: Diego Biurrun <diego@biurrun.de>
2016-05-04 18:16:21 +02:00