summaryrefslogtreecommitdiff
path: root/libavcodec/dsputil.h
Commit message (Collapse)AuthorAgeFilesLines
* Globally rename the header inclusion guard names.Stefano Sabatini2008-08-311-3/+3
| | | | | | | | | Consistently apply this rule: the guard name is obtained from the filename by stripping the leading "lib", converting '/' and '.' to '_' and uppercasing the resulting name. Guard names in the root directory have to be prefixed by "FFMPEG_". Originally committed as revision 15120 to svn://svn.ffmpeg.org/ffmpeg/trunk
* ARM: set STRIDE_ALIGN and DECLARE_ALIGNED_8 to 16 for NEONMåns Rullgård2008-08-251-0/+5
| | | | Originally committed as revision 14961 to svn://svn.ffmpeg.org/ffmpeg/trunk
* document some dsp alignmentsLoren Merritt2008-08-241-4/+4
| | | | Originally committed as revision 14935 to svn://svn.ffmpeg.org/ffmpeg/trunk
* document some dsp alignmentsLoren Merritt2008-08-151-6/+7
| | | | Originally committed as revision 14771 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add declarations for the sine tables used in wma.c (half window sizes: 128,Robert Swain2008-08-141-0/+6
| | | | | | | 256, 512, 1024 and 2048) to mdct.c. Make them accessible via dsputil.h. Make wma.c use these shared tables. Originally committed as revision 14758 to svn://svn.ffmpeg.org/ffmpeg/trunk
* simd int->floatLoren Merritt2008-08-131-0/+2
| | | | | | 20% faster ac3 if downmixing, 15% if not Originally committed as revision 14743 to svn://svn.ffmpeg.org/ffmpeg/trunk
* simd downmixLoren Merritt2008-08-131-0/+1
| | | | | | 13% faster ac3 if downmixing Originally committed as revision 14742 to svn://svn.ffmpeg.org/ffmpeg/trunk
* mdct wrapper function to match fftLoren Merritt2008-08-121-2/+11
| | | | Originally committed as revision 14703 to svn://svn.ffmpeg.org/ffmpeg/trunk
* remove mdct tmp bufferLoren Merritt2008-08-121-14/+7
| | | | Originally committed as revision 14702 to svn://svn.ffmpeg.org/ffmpeg/trunk
* optimize imdct_half:Loren Merritt2008-08-121-7/+7
| | | | | | | | remove tmp buffer. skip fft reinterleave pass, leaving data in a format more convenient for simd. merge post-rotate with post-reorder. Originally committed as revision 14700 to svn://svn.ffmpeg.org/ffmpeg/trunk
* split-radix FFTLoren Merritt2008-08-121-1/+8
| | | | | | c is 1.9x faster than previous c (on various x86 cpus), sse is 1.6x faster than previous sse. Originally committed as revision 14698 to svn://svn.ffmpeg.org/ffmpeg/trunk
* r14205 broke vorbis float_to_int on ppcLoren Merritt2008-07-291-0/+1
| | | | Originally committed as revision 14466 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix h264_loop_filter_strength_mmx2() so it works with PAFF.Michael Niedermayer2008-07-191-1/+1
| | | | | | | | | fixed at least: CVFI1_Sony_D.jsv CVFI1_SVA_C.264 MR6_BT_B.h264 Originally committed as revision 14310 to svn://svn.ffmpeg.org/ffmpeg/trunk
* float_to_int16_interleave: change src to an array of pointers instead of ↵Loren Merritt2008-07-161-1/+1
| | | | | | | | assuming it's contiguous. this has no immediate effect, but will allow it to be used in more codecs. Originally committed as revision 14252 to svn://svn.ffmpeg.org/ffmpeg/trunk
* exploit mdct symmetryLoren Merritt2008-07-131-0/+8
| | | | | | 2% faster vorbis on conroe, k8. 7% on celeron. Originally committed as revision 14207 to svn://svn.ffmpeg.org/ffmpeg/trunk
* simplify vorbis windowingLoren Merritt2008-07-131-0/+5
| | | | Originally committed as revision 14205 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Monkey's Audio decoder vector functions work on input with lengthKostya Shishkov2008-07-101-3/+3
| | | | | | a multiple of 16. Reflect that fact in the documentation for them. Originally committed as revision 14148 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix x86-64Michael Niedermayer2008-07-071-2/+2
| | | | Originally committed as revision 14103 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add several vector functions used by Monkey's Audio decoder to dsputilKostya Shishkov2008-07-061-0/+17
| | | | Originally committed as revision 14081 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Define mm_flags/support to be 0 on architectures where they don't exist.Alexander Strange2008-06-241-0/+5
| | | | | | | Make sure we don't try to set them if that's the case. This lets dct-test and fft-test build with --disable-mmx on x86, but not yet on ARM. Originally committed as revision 13957 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add generic ff_sine_window_init function and implement in codecs appropriatelyRobert Swain2008-06-221-0/+7
| | | | Originally committed as revision 13888 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add a new IDCT permutation, used in xvid_sse2 and possibly future similar IDCTs.Alexander Strange2008-04-161-0/+1
| | | | Originally committed as revision 12842 to svn://svn.ffmpeg.org/ffmpeg/trunk
* typo fixesDiego Biurrun2008-03-121-1/+1
| | | | Originally committed as revision 12428 to svn://svn.ffmpeg.org/ffmpeg/trunk
* misc spelling fixesDiego Biurrun2008-03-101-5/+8
| | | | Originally committed as revision 12410 to svn://svn.ffmpeg.org/ffmpeg/trunk
* move EDGE_WIDTH definition allong with draw_edges where it belongsAurelien Jacobs2008-03-051-0/+1
| | | | Originally committed as revision 12322 to svn://svn.ffmpeg.org/ffmpeg/trunk
* move ff_emulated_edge_mc() to dsputilAurelien Jacobs2008-03-041-0/+4
| | | | Originally committed as revision 12318 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix compilation on powerpc.Aurelien Jacobs2008-03-041-1/+1
| | | | | | | DECLARE_ALIGNED_8 is not defined at that point, but this code is powerpc only, so it's really equivalent to DECLARE_ALIGNED(16... Originally committed as revision 12313 to svn://svn.ffmpeg.org/ffmpeg/trunk
* move ff_init_scantable() into dsputilAurelien Jacobs2008-03-041-0/+15
| | | | Originally committed as revision 12311 to svn://svn.ffmpeg.org/ffmpeg/trunk
* move draw_edges() into dsputilAurelien Jacobs2008-03-041-0/+2
| | | | Originally committed as revision 12309 to svn://svn.ffmpeg.org/ffmpeg/trunk
* __asm __volatile -> asm volatile, improves code consistency and worksReimar Döffinger2008-02-241-1/+1
| | | | | | (as far as that is possible) with the Sun C compiler. Originally committed as revision 12188 to svn://svn.ffmpeg.org/ffmpeg/trunk
* simd and unroll png_filter_rowLoren Merritt2008-02-211-0/+3
| | | | | | | | | | | | cycles per 1000 pixels on core2: left: 9211->5170 top: 9283->2138 avg: 12215->7611 paeth: 64024->17360 overall rgb png decoding speed: +45% overall greyscale png decoding speed: +6% Originally committed as revision 12164 to svn://svn.ffmpeg.org/ffmpeg/trunk
* clean up definition of DECLARE_ALIGNED_8 and STRIDE_ALIGNMåns Rullgård2008-02-161-39/+6
| | | | Originally committed as revision 12126 to svn://svn.ffmpeg.org/ffmpeg/trunk
* const src for bswapMichael Niedermayer2008-02-011-1/+1
| | | | Originally committed as revision 11732 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add variable alpha and size of half window for Kaiser-Bessel Derived windowRobert Swain2008-01-131-1/+3
| | | | | | | | | | generation. Hard code Bessel I0 approximation iterations to 50. See thread for discussion: [FFmpeg-devel] [PATCH] Move Kaiser-Bessel Derived window to mdct.c Started on the 2008/01/10 Originally committed as revision 11520 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Make the Kaiser-Bessel window generator a common functionRobert Swain2008-01-121-0/+6
| | | | | | Patch by Robert Swain, robert d swain a gmail d com Originally committed as revision 11514 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Fix typo in macro name: WARPER8_16_SQ --> WRAPPER8_16_SQ.Diego Biurrun2007-12-211-2/+2
| | | | Originally committed as revision 11296 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Switch VC-1 decoder to output decoded residual immediately.Kostya Shishkov2007-12-081-3/+3
| | | | Originally committed as revision 11188 to svn://svn.ffmpeg.org/ffmpeg/trunk
* cosmetics: Fix spacial --> spatial typo in function names.Diego Biurrun2007-11-101-2/+2
| | | | Originally committed as revision 10993 to svn://svn.ffmpeg.org/ffmpeg/trunk
* intrax8 decoder patch by "someone"Michael Niedermayer2007-11-091-0/+10
| | | | Originally committed as revision 10971 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Add FFMPEG_ prefix to all multiple inclusion guards.Diego Biurrun2007-10-171-3/+3
| | | | Originally committed as revision 10765 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Sanitize altivec code so it can be built with runtime check properlyLuca Barbato2007-10-021-6/+0
| | | | Originally committed as revision 10640 to svn://svn.ffmpeg.org/ffmpeg/trunk
* sse2 version of compute_autocorr().Loren Merritt2007-09-291-0/+2
| | | | | | | 4x faster than c (somehow, even though doubles only allow 2x simd). overal flac encoding: 15-50% faster on core2, 4-11% on k8, 3-13% on p4. Originally committed as revision 10621 to svn://svn.ffmpeg.org/ffmpeg/trunk
* cosmetics: typosPanagiotis Issaris2007-09-271-2/+2
| | | | Originally committed as revision 10602 to svn://svn.ffmpeg.org/ffmpeg/trunk
* VIS-specific code should be enabled conditional to HAVE_VIS, not ARCH_SPARC.Diego Biurrun2007-09-231-1/+1
| | | | Originally committed as revision 10559 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Do not wrongly mark Apple gcc workarounds as being specific to Darwin.Diego Biurrun2007-08-261-1/+1
| | | | Originally committed as revision 10239 to svn://svn.ffmpeg.org/ffmpeg/trunk
* use 16bit IDWT (a SIMD implementation of it should be >2x faster then withMichael Niedermayer2007-08-251-2/+3
| | | | | | | the old 32bit code) disable mmx/sse2 optimizations as they need a rewrite now Originally committed as revision 10218 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Rename CONFIG_DARWIN to SYS_DARWIN, it is not configurable (in FFmpeg).Diego Biurrun2007-08-221-1/+1
| | | | Originally committed as revision 10190 to svn://svn.ffmpeg.org/ffmpeg/trunk
* * renaming (ST|LD)(16|32|64) -> AV_(R|W)N(16|32|64)Roman Shaposhnik2007-08-091-14/+14
| | | | Originally committed as revision 10023 to svn://svn.ffmpeg.org/ffmpeg/trunk
* revert commit 9603Ivan Kalvachev2007-07-111-1/+0
| | | | Originally committed as revision 9605 to svn://svn.ffmpeg.org/ffmpeg/trunk
* Integrate reference mpeg IDCT into dsputil.Ivan Kalvachev2007-07-111-0/+1
| | | | Originally committed as revision 9603 to svn://svn.ffmpeg.org/ffmpeg/trunk