aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86
Commit message (Expand)AuthorAgeFilesLines
* SSE version of clear_blocksJason Garrett-Glaser2009-06-161-2/+26
* idct_dc for VC-1/WMV3 decoder; ~11% faster decoding overall.Jason Garrett-Glaser2009-06-161-0/+203
* Replace more uses of __attribute__((aligned)) by DECLARE_ALIGNED.Ramiro Polla2009-06-042-2/+2
* Use fewer macros in x86-optimized mlpdsp.Ramiro Polla2009-06-031-19/+10
* H264: Fix out of bounds reads in SSSE3 MCAlexander Strange2009-05-301-38/+38
* mlp: Use LABEL_MANGLE() to export label symbols from inside asm block.Ramiro Polla2009-05-251-5/+5
* MLP DSP functions x86-optimized.Ramiro Polla2009-05-231-0/+190
* avg_ pixel functions need to use (dst+pix+1)>>1 to average with existingDavid Conrad2009-04-152-16/+22
* VC1: extend MMX qpel MC to include MMX2 avg qpelDavid Conrad2009-04-152-133/+187
* VC1: add and use avg_no_rnd chroma MC functionsDavid Conrad2009-04-142-0/+11
* Rename put_no_rnd_h264_chroma* to reflect its usage in VC1 onlyDavid Conrad2009-04-142-4/+4
* Do not use SSE2 SAD for snow as it requires more alignment than can beMichael Niedermayer2009-04-091-1/+1
* Rename FF_MM_MMXEXT to FF_MM_MMX2, for both clarity and consistencyStefano Sabatini2009-04-045-14/+14
* Mark line_skip3 asm argument as output-only instead of using av_uninit.Reimar Döffinger2009-04-031-2/+2
* Mark put_signed_pixels_clamped_mmx output operands as early-clobber becauseReimar Döffinger2009-04-031-1/+1
* Use DECLARE_ASM_CONST for non-global ff_vector128 constant used via MANGLEReimar Döffinger2009-04-031-1/+1
* Rewrite put_signed_pixels_clamped_mmx() to eliminate mmx.h from dsputil_mmx.c.Alex Converse2009-04-021-13/+31
* Add SSE4 detection supportDavid Conrad2009-04-011-2/+8
* Remove useless casting in asm "m" operand.Matthieu Castet2009-03-191-2/+2
* Remove CPUID availability check on AMD64 as it's architectural.Zuxy Meng2009-02-231-11/+6
* Convert x264 asm files to proper unix line breaksJason Garrett-Glaser2009-02-222-808/+808
* Remove (incorrect) filenames from x264 asm files, add descriptions.Jason Garrett-Glaser2009-02-222-2/+2
* Put dispatch_tab in the rodata section for macho64.Alexander Strange2009-02-131-0/+6
* add SSE2 version of vp6_filter_diagZuxy Meng2009-02-133-0/+133
* add MMX version of vp6_filter_diagSebastien Lucas2009-02-123-0/+143
* convert ff_pw_64 into an xmm_reg for future use in vp6 sse codeAurelien Jacobs2009-02-123-3/+3
* Fix wrong file name in header, noticed by David DeHaven, dave sagetv com.Diego Biurrun2009-02-111-1/+1
* Add check whether the compiler/assembler supports 10 or more operands.Diego Biurrun2009-02-111-2/+2
* avoid duplicating dsputil's clear_blockStefan Gehrer2009-02-101-22/+0
* Remove svn:executable property from source file.Diego Biurrun2009-02-091-0/+0
* ff_add_hfyu_median_prediction_mmx2Loren Merritt2009-02-082-0/+104
* re-enable mid_pred asm on x86_64. (broke in r16681)Loren Merritt2009-02-081-0/+2
* fix typo in h264dsp_mmx (no effect currently as the function is not used), ap...Baptiste Coudurier2009-02-081-1/+1
* Use full internal pathname in doxygen @file directives.Diego Biurrun2009-02-015-5/+5
* Workaround for gcc 3.4 to align sh properlyDavid Conrad2009-01-261-2/+2
* cosmetics: Remove pointless period after copyright statement non-sentences.Diego Biurrun2009-01-196-6/+6
* moves mid_pred() into mathops.h (with arch specific code split by directory)Aurelien Jacobs2009-01-182-0/+25
* replace all occurrence of ENABLE_ by the corresponding CONFIG_, HAVE_ or ARCH_Aurelien Jacobs2009-01-142-10/+10
* Change semantic of CONFIG_*, HAVE_* and ARCH_*.Aurelien Jacobs2009-01-1311-45/+49
* configure: allow to disable sse code.Ramiro Polla2009-01-071-1/+1
* Add missing 'void' keyword to parameterless function declarations.Diego Biurrun2009-01-052-2/+3
* Use H264 MMX chroma functions to accelerate RV40 decoding.Mathieu Velten2009-01-044-21/+104
* Add x264 SSE2 iDCT functions to H.264 decoder.Jason Garrett-Glaser2009-01-034-2/+378
* Fix h264 decoding on SSE2 cores with icc compilation.Carl Eugen Hoyos2008-12-281-0/+2
* Fix compilation without optimization under 64-bit with x264 deblock asm enabled.Jason Garrett-Glaser2008-12-261-0/+2
* Rename libavcodec/i386/ --> libavcodec/x86/.Diego Biurrun2008-12-2238-0/+19354