summaryrefslogtreecommitdiff
path: root/libavcodec/ppc/dsputil_altivec.c
Commit message (Collapse)AuthorAge
* dsputil: Split motion estimation compare bits off into their own contextDiego Biurrun2014-07-17
|
* ppc: dsputil: Coalesce all init filesDiego Biurrun2014-07-13
|
* dsputil: Drop unused bit_depth parameter from all init functionsDiego Biurrun2014-07-11
|
* dsputil: Split off pixel block routines into their own contextDiego Biurrun2014-07-09
|
* dsputil: Move pix_sum, pix_norm1, shrink function pointers to mpegvideoencDiego Biurrun2014-07-06
|
* dsputil: Split clear_block*/fill_block* off into a separate contextDiego Biurrun2014-06-18
|
* dsputil: Split off HuffYUV decoding bits into their own contextDiego Biurrun2014-05-27
| | | | Also shorten HuffYUV context member names to avoid clutter.
* dsputil: Use correct type in me_cmp_func function pointerDiego Biurrun2014-03-20
|
* dsputil: Propagate bit depth information to all (sub)init functionsDiego Biurrun2014-03-20
| | | | This avoids recalculating the value over and over again.
* ppc: dsputil: Merge some declarations and initializationsDiego Biurrun2014-03-20
|
* ppc: dsputil: Drop some unnecessary parenthesesDiego Biurrun2014-03-20
|
* ppc: dsputil: K&R formatting cosmeticsDiego Biurrun2014-03-20
|
* ppc: dsputil: comment formatting and wording/grammar improvementsDiego Biurrun2014-03-20
|
* ppc: Add some missing headersDiego Biurrun2014-03-13
|
* ppc: reduce overreads when loading 8 pixels in altivec dsp functionsJanne Grunau2014-02-14
| | | | | | | | | | | Altivec can only load naturally aligned vectors. To handle possibly unaligned data a second vector is loaded from an offset of the original location and the data is recovered through a vector permutation. Overreads are minimal if the offset for second load points to the last element of data. This is 7 for loading eight 8-bit pixels and overreads are reduced from 16 bytes to 8 bytes if the pixels are 64-bit aligned. For unaligned pixels the overread is reduced from 23 bytes to 15 bytes in the worst case.
* ppc: hpeldsp: Move half-pel assembly from dsputil to hpeldspRonald S. Bultje2013-04-19
| | | | Signed-off-by: Martin Storsjö <martin@martin.st>
* Add av_cold attributes to arch-specific init functionsDiego Biurrun2013-02-05
|
* Use ptrdiff_t instead of int for {avg, put}_pixels line_size parameter.Diego Biurrun2013-02-05
| | | | | This avoids SIMD-optimized functions having to sign-extend their line size argument manually to be able to do pointer arithmetic.
* Drop DCTELEM typedefDiego Biurrun2013-01-22
| | | | | | It does not help as an abstraction and adds dsputil dependencies. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
* Move vorbis_inverse_coupling from dsputil to vorbisdspcontext.Ronald S. Bultje2013-01-19
| | | | | Conveniently (together with Justin's earlier patches), this makes our vorbis decoder entirely independent of dsputil.
* PPC: Move types_altivec.h and util_altivec.h from libavcodec to libavutilJustin Ruggles2012-06-08
| | | | | This will allow for easier implementation of Altivec functions in libraries other than libavcodec.
* ppc: dsputil: do unaligned block accesses correctlyMans Rullgard2012-05-01
| | | | | | | | | | | | To load unaligned vector data in the usual way, explicit vec_ld() should be used rather than dereferencing a pointer to a vector type. When the VSX extension is enabled, gcc may compile vector pointer dereferences using the VSX lxvw4x instruction instead of the lvx instruction typically used with Altivec/VMX. As the behaviour of these instructions with unaligned addresses differs, it is important that only lvx is used here. Signed-off-by: Mans Rullgard <mans@mansr.com>
* ppc: Add ff_ prefix to nonstatic symbolsMartin Storsjö2012-02-15
| | | | Signed-off-by: Martin Storsjö <martin@martin.st>
* dsputil: Add ff_ prefix to the dsputil*_init* functionsMartin Storsjö2012-02-15
| | | | Signed-off-by: Martin Storsjö <martin@martin.st>
* dsputil: update per-arch init funcs for non-h264 high bit depthMans Rullgard2011-07-21
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* dsputil: template get_pixels() for different bit depthsMans Rullgard2011-07-21
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* ppc: remove disabled codeDiego Biurrun2011-07-16
|
* Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 ↵Oskar Arvidsson2011-05-10
| | | | | | | | | | | | | | | | | decoder. This patch lets e.g. dsputil_init chose dsp functions with respect to the bit depth to decode. The naming scheme of bit depth dependent functions is <base name>_<bit depth>[_<prefix>] (i.e. the old clear_blocks_c is now named clear_blocks_8_c). Note: Some of the functions for high bit depth is not dependent on the bit depth, but only on the pixel size. This leaves some room for optimizing binary size. Preparatory patch for high bit depth h264 decoding support. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
* Replace FFmpeg with Libav in licence headersMans Rullgard2011-03-19
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* Fix overread in altivec DSP function sad16Vitor Sessak2011-01-29
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* Remove PPC perf counter supportMåns Rullgård2010-06-26
| | | | | | This functionality is better accessed through tools like oprofile. Originally committed as revision 23808 to svn://svn.ffmpeg.org/ffmpeg/trunk
* PPC: move prototypes to headers and make some functions staticMåns Rullgård2010-03-06
| | | | Originally committed as revision 22267 to svn://svn.ffmpeg.org/ffmpeg/trunk
* PPC: remove unnecessary alignment on local variablesMåns Rullgård2009-08-24
| | | | | | | | | Storing a single element from a vector where all elements have the same value does not require an aligned destination. Which element is stored depends on the alignment of the destination address, but since they all have the same value, the result is the same regardless of the alignment. Originally committed as revision 19696 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove useless casts of vec_ld() parameters.Diego Biurrun2009-05-18
| | | | | | Gets rid of 'cast discards qualifiers from pointer target type' warnings. Originally committed as revision 18867 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove gcc_fixes.h. It only contains workarounds for unsupported gcc versions.Diego Biurrun2009-04-12
| | | | Originally committed as revision 18476 to svn://svn.ffmpeg.org/ffmpeg/trunk
* replace all occurrence of ENABLE_ by the corresponding CONFIG_, HAVE_ or ARCH_Aurelien Jacobs2009-01-14
| | | | | | and remove all ENABLE_ definitions. Originally committed as revision 16600 to svn://svn.ffmpeg.org/ffmpeg/trunk
* add Altivec implementation of clear_blockGuillaume Poirier2008-12-12
| | | | Originally committed as revision 16078 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove AltiVec vector declaration compiler compatibility macros.Diego Biurrun2008-07-24
| | | | | | | | | | The original problem was that FSF and Apple gcc used a different syntax for vector declarations, i.e. {} vs. (). Nowadays Apple gcc versions support the standard {} syntax and versions that support {} are available on all relevant Mac OS X versions. Thus the greater compatibility is no longer worth cluttering the code with macros. Originally committed as revision 14366 to svn://svn.ffmpeg.org/ffmpeg/trunk
* cosmetics: Make libavcodec/ppc/dsputil_altivec.c conform to style guidelines.Diego Biurrun2008-07-20
| | | | | | | This includes indentation changes, comment reformatting, consistent brace placement and some prettyprinting. Originally committed as revision 14318 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Use full path for #includes from another directory.Diego Biurrun2008-05-09
| | | | Originally committed as revision 13098 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Change some files to only include the necessary headers.Diego Biurrun2008-01-04
| | | | Originally committed as revision 11394 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix alignment broke by my last patchVitor Sessak2007-12-01
| | | | Originally committed as revision 11123 to svn://svn.ffmpeg.org/ffmpeg/trunk
* spellingVitor Sessak2007-12-01
| | | | Originally committed as revision 11122 to svn://svn.ffmpeg.org/ffmpeg/trunk
* cosmetics: Fix indentation after last commit.Diego Biurrun2007-10-02
| | | | Originally committed as revision 10643 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Replace CONFIG_VORBIS_DECODER #ifdef by if (ENABLE_VORBIS_DECODER).Diego Biurrun2007-10-02
| | | | | | Blessed by Luca Barbato on IRC. Originally committed as revision 10642 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Sanitize altivec code so it can be built with runtime check properlyLuca Barbato2007-10-02
| | | | Originally committed as revision 10640 to svn://svn.ffmpeg.org/ffmpeg/trunk
* cosmetics: Fix AltiVec spelling.Diego Biurrun2007-10-02
| | | | Originally committed as revision 10639 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Remove const vector macro indirection that is useless and obfuscatingDiego Biurrun2007-10-01
| | | | | | now that the Metrowerks workarounds are gone. Originally committed as revision 10633 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Simplify preprocessor directives.Diego Biurrun2007-08-27
| | | | Originally committed as revision 10249 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Change SYS_DARWIN preprocessor checks to __APPLE__, they are specificDiego Biurrun2007-08-27
| | | | | | to Mac OS X rather than to Darwin. Originally committed as revision 10247 to svn://svn.ffmpeg.org/ffmpeg/trunk
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-13 10:56:18 +0000