- 20 10月, 2015 1 次提交
-
-
由 Timothy Gu 提交于
That's where all yasm initiation steps are. Also removes the overlap between the two files.
-
- 17 6月, 2015 1 次提交
-
-
由 Andreas Cadhalpun 提交于
Also fix typo found by Lou Logan: Sacrifying -> Sacrificing Reviewed-by: NLou Logan <lou@lrcd.com> Signed-off-by: NAndreas Cadhalpun <Andreas.Cadhalpun@googlemail.com>
-
- 15 3月, 2015 1 次提交
-
-
由 Christophe Gisquet 提交于
The later may yield incorrect code for on-stack variables. Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>
-
- 21 5月, 2014 1 次提交
-
-
由 Christophe Gisquet 提交于
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>
-
- 22 4月, 2014 1 次提交
-
-
由 Hendrik Leppkes 提交于
Reviewed-by: NChristophe Gisquet <christophe.gisquet@gmail.com> Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>
-
- 21 4月, 2014 1 次提交
-
-
由 Christophe Gisquet 提交于
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: NMichael Niedermayer <michaelni@gmx.at>
-
- 19 4月, 2014 1 次提交
-
-
由 Carl Eugen Hoyos 提交于
Can be tested with: $ ./configure --cc='cc -m32' --disable-optimizations --enable-pic
-
- 22 3月, 2014 1 次提交
-
-
由 Diego Biurrun 提交于
-
- 19 3月, 2014 1 次提交
-
-
由 Matt Oliver 提交于
Automatically change MANGLE() into named inline asm operands when direct symbol reference in inline asm are not supported. This is part of the patch-set for intel C inline asm on windows support Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>
-
- 13 5月, 2013 1 次提交
-
-
由 Diego Biurrun 提交于
The header is not (anymore) MMX-specific.
-
- 09 5月, 2013 1 次提交
-
-
由 Diego Biurrun 提交于
-
- 02 5月, 2013 1 次提交
-
-
由 Diego Biurrun 提交于
-
- 26 3月, 2013 1 次提交
-
-
由 Martin Storsjö 提交于
Signed-off-by: NMartin Storsjö <martin@martin.st>
-
- 13 3月, 2013 1 次提交
-
-
由 Luca Barbato 提交于
Signed-off-by: NLuca Barbato <lu_zero@gentoo.org>
-
- 27 2月, 2013 2 次提交
-
-
由 Diego Biurrun 提交于
The external assembly function uses mmxext instructions and should not be masqueraded as an mmx-only function. Instead, use the mmx-only inline assembly function.
-
由 Diego Biurrun 提交于
-
- 26 2月, 2013 1 次提交
-
-
由 Diego Biurrun 提交于
-
- 27 1月, 2013 1 次提交
-
-
由 Daniel Kang 提交于
Signed-off-by: NLuca Barbato <lu_zero@gentoo.org>
-
- 23 1月, 2013 1 次提交
-
-
由 Diego Biurrun 提交于
It does not help as an abstraction and adds dsputil dependencies. Signed-off-by: NRonald S. Bultje <rsbultje@gmail.com>
-
- 01 11月, 2012 1 次提交
-
-
由 Diego Biurrun 提交于
-
- 08 10月, 2012 1 次提交
-
-
由 Janne Grunau 提交于
-
- 31 8月, 2012 1 次提交
-
-
由 Diego Biurrun 提交于
-
- 16 8月, 2012 2 次提交
-
-
由 Michael Niedermayer 提交于
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>
-
由 Martin Storsjö 提交于
Signed-off-by: NMartin Storsjö <martin@martin.st>
-
- 09 8月, 2012 1 次提交
-
-
由 Mans Rullgard 提交于
This puts x86-specific things in the x86/ subdirectory where they belong. Signed-off-by: NMans Rullgard <mans@mansr.com>
-
- 04 8月, 2012 1 次提交
-
-
由 Diego Biurrun 提交于
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.
-
- 30 6月, 2012 1 次提交
-
-
由 Mans Rullgard 提交于
The problem is that the ssse3 psign instruction does the wrong thing here. Commit ea60dfe2 incorrectly removed a macro emulating this instruction for pre-ssse3 code. However, the emulation is incorrect, and the code relies on the behaviour of the macro. Specifically, the psign sets destination elements to zero where the corresponding source element is zero, whereas the emulation only negates destination elements where the source is negative. Furthermore, the PSIGNW_MMX macro in x86util.asm is totally bogus, which is why the original VC-1 code had an additional right shift when using it. Since the psign instruction cannot be used here, skip all the macro hell and use the working instruction sequence directly. None of this was noticed due a stray return statement in ff_vc1dsp_init_mmx() which meant that only the mmx version of the loop filter was ever used (before being removed in ea60dfe2). Signed-off-by: NMans Rullgard <mans@mansr.com>
-
- 25 6月, 2012 1 次提交
-
-
由 Ronald S. Bultje 提交于
Signed-off-by: NMans Rullgard <mans@mansr.com>
-
- 12 5月, 2012 1 次提交
-
-
由 Michael Kostylev 提交于
-
- 24 3月, 2012 2 次提交
-
-
由 Carl Eugen Hoyos 提交于
-
由 Reimar Döffinger 提交于
They were moved into code under HAVE_YASM and most of them even into completely disabled code with no reason given for that in the commit message. Signed-off-by: NReimar Döffinger <Reimar.Doeffinger@gmx.de>
-
- 19 2月, 2011 1 次提交
-
-
由 Ronald S. Bultje 提交于
(cherry picked from commit 12802ec0)
-
- 18 2月, 2011 1 次提交
-
-
由 Ronald S. Bultje 提交于
-
- 19 1月, 2011 1 次提交
-
-
由 Mans Rullgard 提交于
This macro has unconditionally used .p2align for a long time and serves no useful purpose.
-
- 08 9月, 2010 1 次提交
-
-
由 Stefano Sabatini 提交于
function and rename it to av_get_cpu_flags(). Originally committed as revision 25076 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 04 9月, 2010 1 次提交
-
-
由 Stefano Sabatini 提交于
symbols, and move them from libavcodec/avcodec.h to libavutil/cpu.h. Originally committed as revision 25040 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 25 8月, 2010 1 次提交
-
-
由 Måns Rullgård 提交于
Originally committed as revision 24909 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 21 7月, 2010 2 次提交
-
-
由 David Conrad 提交于
Should fix compilation with icc and should help prevent any future duplicates Originally committed as revision 24380 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
由 Ronald S. Bultje 提交于
and chroma (width=8). Originally committed as revision 24378 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 12 7月, 2010 1 次提交
-
-
由 David Conrad 提交于
Originally committed as revision 24208 to svn://svn.ffmpeg.org/ffmpeg/trunk
-