Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/FFmpeg/FFmpeg.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/libavcodec/ppc
AgeCommit message (Collapse)Author
2014-01-06h264: do not use 422 functions for monochromeAnton Khirnov
Fixes invalid memory access. Found-by: Mateusz "j00ru" Jurczyk and Gynvael Coldwind CC:libav-stable@libav.org
2013-08-29ppc: cosmetics: Consistently format CPU flag detection invocationsDiego Biurrun
2013-08-29ppc: Add missing AltiVec cpuflag detection invocationsDiego Biurrun
2013-08-29ppc: fdct: Remove vim editor settings commentDiego Biurrun
2013-08-29ppc: Add and use convenience macro to check for AltiVec availabilityDiego Biurrun
2013-08-16altivec: perform an explicit unaligned loadKostya Shishkov
Implicit vector loads on POWER7 hardware can use the VSX instruction set instead of classic Altivec/VMX. Let's force a VMX load in this case. Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-18Consistently use "cpu_flags" as variable/parameter name for CPU flagsDiego Biurrun
2013-07-17fmtconvert: Explicitly use int32_t instead of intChristophe Gisquet
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-05-26fix scalarproduct_and_madd_int16_altivec() for orders > 16Kostya Shishkov
the second and third sources were incremented only by half of the needed size
2013-05-02ppc: Only compile AltiVec FFT assembly when AltiVec is enabledDiego Biurrun
2013-04-30ppc: Drop unnecessary ff_ name prefixes from static functionsDiego Biurrun
2013-04-30ppc: More consistent arch initializationDiego Biurrun
2013-04-30ppc: Move AltiVec utility headers out of AltiVec ifdefsDiego Biurrun
Now that the headers themselves have ifdef protection this is no longer necessary and more consistent with normal include handling.
2013-04-30ppc: More consistent names for H.264 optimizations filesDiego Biurrun
2013-04-30mpegaudiosp: More consistent names for ppc/x86 optimization filesDiego Biurrun
2013-04-20ppc: hpeldsp: Include attributes.hMartin Storsjö
This fixes building in configurations where altivec is disabled. Signed-off-by: Martin Storsjö <martin@martin.st>
2013-04-20ppc: hpeldsp: Move half-pel assembly from dsputil to hpeldspRonald S. Bultje
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-04-15vp3: Use full transpose for all IDCTsRonald S. Bultje
This way, the special IDCT permutations are no longer needed. This is similar to how H264 does it, and removes the dsputil dependency imposed by the scantable code. Also remove the unused type == 0 cases from the plain C version of the idct. Signed-off-by: Martin Storsjö <martin@martin.st>
2013-04-10h264: Integrate clear_blocks calls with IDCTRonald S. Bultje
The non-intra-pcm branch in hl_decode_mb (simple, 8bpp) goes from 700 to 672 cycles, and the complete loop of decode_mb_cabac and hl_decode_mb (in the decode_slice loop) goes from 1759 to 1733 cycles on the clip tested (cathedral), i.e. almost 30 cycles per mb faster. Signed-off-by: Martin Storsjö <martin@martin.st>
2013-03-12dsputil: convert remaining functions to use ptrdiff_t stridesLuca Barbato
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2013-02-26Remove unnecessary dsputil.h #includesDiego Biurrun
2013-02-09dsputil: Move LOCAL_ALIGNED macros to libavutilDiego Biurrun
2013-02-06dsputil: Separate h264chromaDiego Biurrun
2013-02-05Add av_cold attributes to arch-specific init functionsDiego Biurrun
2013-02-05Use ptrdiff_t instead of int for {avg, put}_pixels line_size parameter.Diego Biurrun
This avoids SIMD-optimized functions having to sign-extend their line size argument manually to be able to do pointer arithmetic.
2013-02-01ppc: fmtconvert: Drop two unused variables.Diego Biurrun
2013-01-24dsputil: Separate h264 qpelMans Rullgard
The sh4 optimizations are removed, because the code is 100% identical to the C code, so it is unlikely to provide any real practical benefit. Signed-off-by: Diego Biurrun <diego@biurrun.de> Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com> Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2013-01-23Drop DCTELEM typedefDiego Biurrun
It does not help as an abstraction and adds dsputil dependencies. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
2013-01-22floatdsp: move vector_fmul_reverse from dsputil to avfloatdsp.Ronald S. Bultje
Now, nellymoserenc and aacenc no longer depends on dsputil. Independent of this patch, wmaprodec also does not depend on dsputil, so I removed it from there also.
2013-01-22floatdsp: move vector_fmul_add from dsputil to avfloatdsp.Ronald S. Bultje
2013-01-21vorbisdsp: change block_size type from int to intptr_t.Ronald S. Bultje
This saves one instruction in the x86-64 assembly.
2013-01-20ppc: vorbisdsp: Drop some unnecessary #includesDiego Biurrun
Also fixes compilation with AltiVec disabled.
2013-01-20ppc: Include string.h for memsetMartin Storsjö
This fixes build failures on ppc machines with a compiler that supports -Werror=implicit-function-declaration. Signed-off-by: Martin Storsjö <martin@martin.st>
2013-01-20Move vorbis_inverse_coupling from dsputil to vorbisdspcontext.Ronald S. Bultje
Conveniently (together with Justin's earlier patches), this makes our vorbis decoder entirely independent of dsputil.
2013-01-20vp3: integrate clear_blocks with idct of previous block.Ronald S. Bultje
This is identical to what e.g. vp8 does, and prevents the function call overhead (plus dependency on dsputil for this particular function). Arm asm updated by Janne Grunau <janne-libav@jannau.net>. Signed-off-by: Janne Grunau <janne-libav@jannau.net>
2013-01-16lavc: Move vector_fmul_window to AVFloatDSPContextJustin Ruggles
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2012-12-20lavc: introduce VideoDSPContextRonald S. Bultje
Move some functions from dsputil. The idea is that videodsp contains functions that are useful for a large and varied set of video decoders. Currently, it contains emulated_edge_mc() and prefetch(). Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2012-11-12ppc: replace pointer casting with AV_COPY32Mans Rullgard
This removes warnings about strict aliasing violations. Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-11-12ppc: fix some unused variable warningsMans Rullgard
The third argument of OP_U8_ALTIVEC is evaluated at most once so there is no need for a potentially unused temporary variable. Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-10-09build: non-x86: Only compile mpegvideo optimizations when necessaryDiego Biurrun
2012-10-09ppc: fix Altivec build with old compilersMans Rullgard
The vec_splat() intrinsic requires a constant argument for the element number, and the code relies on the compiler unrolling the loop to provide this. Manually unrolling the loop avoids this reliance and works with all compilers. Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-10-06ppc: fmtconvert: kill VLA in float_to_int16_interleave_altivec()Mans Rullgard
Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-08-16Add more missing includes after removing the implicit common.hMartin Storsjö
Signed-off-by: Martin Storsjö <martin@martin.st>
2012-08-16Add some more missing includes after removing the implicit common.hMartin Storsjö
Signed-off-by: Martin Storsjö <martin@martin.st>
2012-08-15Don't include common.h from avutil.hMartin Storsjö
Signed-off-by: Martin Storsjö <martin@martin.st>
2012-07-23dsputil: ppc: cosmetics: pretty-printJustin Ruggles
2012-07-18ppc: fix build with altivec disabledMans Rullgard
Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-07-18vp3: move idct and loop filter pointers to new vp3dsp contextMans Rullgard
This moves all VP3-specific function pointers from dsputil to a new vp3dsp context. There is no reason to ever use the VP3 IDCT where an MPEG2 IDCT is expected or vice versa. Signed-off-by: Mans Rullgard <mans@mansr.com>
2012-06-13ppc: Rename H.264 optimization template file for consistency.Diego Biurrun
2012-06-08Add a float DSP framework to libavutilJustin Ruggles
Move vector_fmul() from DSPContext to AVFloatDSPContext.
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-27 18:14:53 +0300