aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/vc1dsp_init.c
Commit message (Collapse)AuthorAgeFilesLines
* avcodec/x86/vc1: guard usage of undefined functions with preprocessorKacper Michajłow10 days1-0/+2
| | | | | | | | The asumption is that DCE will remove references to those functions. However some compilers with certain instrumentation enabled doesn't DCE those at all, resulting in linking failure. Tested with cl.exe -RTCu -RTCs. Signed-off-by: Kacper Michajłow <kasper93@gmail.com>
* avcodec/h264chroma: Constify src in h264_chroma_mc_funcAndreas Rheinhardt2022-08-051-4/+4
| | | | Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
* avcodec/x86/vc1dsp_init: Remove obsolete 3dnow, MMX(EXT) functionsAndreas Rheinhardt2022-06-221-26/+14
| | | | | | | | | | | x64 always has MMX, MMXEXT, SSE and SSE2 and this means that some functions for MMX, MMXEXT and 3dnow are always overridden by other functions (unless one e.g. explicitly disables SSE2) for x64. So given that the only systems that benefit from these functions are truely ancient 32bit x86s they are removed. Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
* vc1dsp: Change remaining stride parameters to ptrdiff_tMartin Storsjö2022-03-301-8/+8
| | | | | | | | | | | The existing x86 assembly for loop filters uses the stride as a full register without clearing/sign extending the upper half of the registers on x86_64. This avoids crashes if the caller would have passed nonzero bits in the previously undefined upper 32 bits of the parameters. Signed-off-by: Martin Storsjö <martin@martin.st>
* build: Generalize yasm/nasm-related variable namesDiego Biurrun2017-06-211-4/+4
| | | | | | | | None of them are specific to the YASM assembler. (Cherry-picked from libav commit 39e208f4d4756367c7cd2d581847e0c1b8a429c1) Signed-off-by: James Almer <jamrial@gmail.com>
* avcodec/x86/vc1dsp_init: Fix build failure with --disable-optimizations and ↵Michael Niedermayer2017-04-271-2/+4
| | | | | | | | | clang compilers doing DCE at -O0 do not necessarily understand "complex" boolean expressions Build succeeds with this change, this was the only failure Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
* Merge commit 'e4a94d8b36c48d95a7d412c40d7b558422ff659c'James Almer2017-03-211-5/+5
|\ | | | | | | | | | | | | * commit 'e4a94d8b36c48d95a7d412c40d7b558422ff659c': h264chroma: Change type of stride parameters to ptrdiff_t Merged-by: James Almer <jamrial@gmail.com>
| * h264chroma: Change type of stride parameters to ptrdiff_tDiego Biurrun2016-09-291-5/+5
| | | | | | | | | | This avoids SIMD-optimized functions having to sign-extend their stride argument manually to be able to do pointer arithmetic.
* | Merge commit '2ec9fa5ec60dcd10e1cb10d8b4e4437e634ea428'James Almer2017-03-211-4/+4
|\| | | | | | | | | | | | | * commit '2ec9fa5ec60dcd10e1cb10d8b4e4437e634ea428': idct: Change type of array stride parameters to ptrdiff_t Merged-by: James Almer <jamrial@gmail.com>
* | x86: vc1dsp: Convert vc1_inv_trans_*_dc to NASM formatTimothy Gu2016-02-011-0/+13
| |
* | lavc/x86/vc1dsp_init: Fix compilation with --disable-yasm.Carl Eugen Hoyos2015-10-221-2/+2
| |
* | x86: vc1dsp_mmx: Move yasm initiation steps to vc1dsp_initTimothy Gu2015-10-191-11/+25
| | | | | | | | | | That's where all yasm initiation steps are. Also removes the overlap between the two files.
* | vc1dsp: fix build without inline asmHendrik Leppkes2014-04-221-14/+0
| | | | | | | | | | Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* | vc1dsp: introduce cases for 8x8 and 16x16Christophe Gisquet2014-04-201-1/+21
| | | | | | | | | | | | | | | | | | | | | | | | This allows further unrolling the DSP implementation where possible. x86 and ARM DSP modified by simply moving the multiple calls from vc1dec to the DSP code. Decoding improvements should only occurs because of the compiler actually able to unroll more. Decoding time: ~8.80s -> 8.64s (ie around 2%) Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
* | Fix compilation with !HAVE_6REGS.Carl Eugen Hoyos2014-04-191-2/+3
|/ | | | | Can be tested with: $ ./configure --cc='cc -m32' --disable-optimizations --enable-pic
* x86: dsputil: Move fpel declarations to a separate headerDiego Biurrun2014-03-221-1/+1
|
* x86: avcodec: Add a bunch of missing #includes for av_coldDiego Biurrun2014-01-091-0/+1
|
* x86: avcodec: Consistently structure CPU extension initializationDiego Biurrun2013-08-291-2/+3
|
* x86: avcodec: Use convenience macros to check for CPU flagsDiego Biurrun2013-08-291-8/+6
|
* Consistently use "cpu_flags" as variable/parameter name for CPU flagsDiego Biurrun2013-07-181-9/+9
|
* x86: dsputil: Rename dsputil_mmx.h --> dsputil_x86.hDiego Biurrun2013-05-121-1/+1
| | | | The header is not (anymore) MMX-specific.
* dsputil: convert remaining functions to use ptrdiff_t stridesLuca Barbato2013-03-121-1/+1
| | | | Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
* x86: vc1dsp: Move ff_avg_vc1_mspel_mc00_mmxext out of dsputil_mmx.cDiego Biurrun2013-02-261-0/+9
|
* x86: mmx2 ---> mmxext in asm constructsDiego Biurrun2012-11-141-3/+3
|
* x86: vc1dsp: port to cpuflagsDiego Biurrun2012-11-051-2/+2
|
* x86: Move optimization suffix to end of function namesDiego Biurrun2012-10-311-10/+10
| | | | This simplifies cpuflags porting.
* x86: vc1: call ff_vc1dsp_init_x86() under if (ARCH_X86)Janne Grunau2012-10-081-0/+123
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-04 07:18:55 +0000