Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | x86: Put COPY3_IF_LT under HAVE_6REGS | Luca Barbato | 2015-03-17 |
| | | | | | | | It uses 6 registers, unbreaks building on hardened x86 system. Bug-Id: gentoo/541930 CC: libav-stable@libav.org | ||
* | lavc: do not compile fmtconvert unconditionally | Anton Khirnov | 2015-02-28 |
| | | | | Only ac3dec and dcadec use it. | ||
* | fmtconvert: drop unused functions | Anton Khirnov | 2015-02-28 |
| | |||
* | hevc_deblock: Fix compilation with nasm | Carl Eugen Hoyos | 2015-02-22 |
| | | | | | | CC: libav-stable@libav.org Bug-Id: 795 Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com> | ||
* | v210enc: Add SIMD optimised 8-bit and 10-bit encoders | Kieran Kunhya | 2014-12-05 |
| | | | | | Signed-off-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com> | ||
* | motion_est: convert stride to ptrdiff_t | Vittorio Giovara | 2014-11-24 |
| | | | | | CC: libav-stable@libav.org Bug-Id: CID 700556 / CID 700557 / CID 700558 | ||
* | x86: h264_intrapred: Don't treat 32-bit integers as 64-bit | Henrik Gramner | 2014-10-08 |
| | | | | | | The upper halves are not guaranteed to be zero in x86-64. Signed-off-by: Anton Khirnov <anton@khirnov.net> | ||
* | xvid: Add C IDCT | Pascal Massimino | 2014-09-02 |
| | | | | | | Thanks to Pascal Massimino and Michael Militzer for relicensing as LGPL. Signed-off-by: Diego Biurrun <diego@biurrun.de> | ||
* | idctdsp: Add global function pointers for {add|put}_pixels_clamped functions | Diego Biurrun | 2014-09-02 |
| | | | | | | These function pointers already existed in the ARM code. Adding them globally allows calls to the function pointers to access arch-optimized versions of the functions transparently. | ||
* | x86: xvid: K&R formatting cosmetics | Diego Biurrun | 2014-08-27 |
| | |||
* | cosmetics: Make naming scheme of Xvid IDCT consistent with other IDCTs | Diego Biurrun | 2014-08-27 |
| | |||
* | x86: xvid_idct: Drop unused definitions | Diego Biurrun | 2014-08-27 |
| | |||
* | build: Add explanatory comments to (optimization) blocks in the Makefiles | Diego Biurrun | 2014-08-15 |
| | |||
* | mpegvideo: cosmetics: Lowercase ugly uppercase MPV_ function name prefixes | Diego Biurrun | 2014-08-15 |
| | |||
* | avcodec: Rename xvidmmx IDCT to xvid | Diego Biurrun | 2014-08-08 |
| | | | | The Xvid IDCT is not MMX-specific. | ||
* | xvididct: Ensure that the scantable permutation is always set correctly | Diego Biurrun | 2014-08-08 |
| | | | | | This fixes cases where the scantable permuation would get overwritten by the general idctdsp initialization. | ||
* | idct: Split off Xvid IDCT | Diego Biurrun | 2014-08-01 |
| | | | | | The Xvid IDCT is only required to decode some Xvid-encoded MPEG-4 files, so there is no point in having it as an unconditional part of idctdsp. | ||
* | x86: build: Restore ordering of OBJS lines | Diego Biurrun | 2014-07-28 |
| | |||
* | hevc: SSE2 and SSSE3 loop filters | Pierre Edouard Lepere | 2014-07-26 |
| | | | | | | | | Additional contributions by James Almer <jamrial@gmail.com>, Carl Eugen Hoyos <cehoyos@ag.or.at>, Fiona Glaser <fiona@x264.com> and Anton Khirnov <anton@khirnov.net> Signed-off-by: Anton Khirnov <anton@khirnov.net> | ||
* | qpeldsp: Mark source pointer in qpel_mc_func function pointer const | Diego Biurrun | 2014-07-25 |
| | |||
* | dct-test: Move arch-specific bits into arch-specific subdirectories | Diego Biurrun | 2014-07-21 |
| | |||
* | simple_idct: Move x86-specific declarations to a header in the x86 directory | Diego Biurrun | 2014-07-19 |
| | |||
* | fdct: Move x86-specific declarations to a header in the x86 directory | Diego Biurrun | 2014-07-19 |
| | |||
* | x86: dnxhdenc: Eliminate some unnecessary ifdefs | Diego Biurrun | 2014-07-18 |
| | |||
* | idctdsp: prettyprinting cosmetics | Diego Biurrun | 2014-07-18 |
| | |||
* | idct: Convert IDCT permutation #defines to an enum | Diego Biurrun | 2014-07-18 |
| | | | | Also rename the enum values to be consistent with other DCT permutations. | ||
* | dsputil: Split motion estimation compare bits off into their own context | Diego Biurrun | 2014-07-17 |
| | |||
* | x86: dsputil: Coalesce all init files | Diego Biurrun | 2014-07-17 |
| | | | | This makes the init files match the structure of the dsputil split. | ||
* | x86: dsputil: Avoid pointless CONFIG_ENCODERS indirection | Diego Biurrun | 2014-07-13 |
| | | | | The remaining dsputil bits are encoding-specific anyway. | ||
* | dsputil: Drop unused bit_depth parameter from all init functions | Diego Biurrun | 2014-07-11 |
| | |||
* | dsputil: Split off pixel block routines into their own context | Diego Biurrun | 2014-07-09 |
| | |||
* | dsputil: Split off FDCT bits into their own context | Diego Biurrun | 2014-07-07 |
| | |||
* | dsputil: Move draw_edges() to mpegvideoencdsp | Diego Biurrun | 2014-07-06 |
| | |||
* | dsputil: Move pix_sum, pix_norm1, shrink function pointers to mpegvideoenc | Diego Biurrun | 2014-07-06 |
| | |||
* | dsputil: Split off *_8x8basis to a separate context | Diego Biurrun | 2014-07-06 |
| | |||
* | x86: build: Only compile FDCT code if MMX is enabled | Diego Biurrun | 2014-07-05 |
| | | | | All other files containing purely inline assembly are treated the same way. | ||
* | x86: Unconditionally compile blockdsp and svq1enc init files | Diego Biurrun | 2014-07-05 |
| | | | | | This avoids a link failure with MMX disabled as the init functions are referenced unconditionally. | ||
* | x86: huffyuvdsp: Move inline assembly to init file | Diego Biurrun | 2014-07-05 |
| | | | | | This avoids a link failure with MMX disabled as now code and initialization are compiled under the same condition. | ||
* | x86: mpegvideoenc: Change SIMD optimization name suffixes to lowercase | Diego Biurrun | 2014-07-03 |
| | |||
* | Update Fiona's name in copyright statements. | Diego Biurrun | 2014-07-01 |
| | |||
* | dsputil: Split off IDCT bits into their own context | Diego Biurrun | 2014-06-30 |
| | |||
* | dsputil: Move MMX/SSE2-optimized IDCT bits to the x86 subdirectory | Diego Biurrun | 2014-06-26 |
| | |||
* | x86: h264dsp: Fix link failure with optimizations disabled | Diego Biurrun | 2014-06-25 |
| | | | | | | | | With optimzations disabled compilers have trouble doing dead code elimination on 'if (foo && 0)' expressions, while 'if (0 && foo)' still works, so use the latter to avoid problems. Bug-Id: 707 | ||
* | dsputil: Split off global motion compensation bits into a separate context | Diego Biurrun | 2014-06-23 |
| | |||
* | dsputil: Split bswap*_buf() off into a separate context | Diego Biurrun | 2014-06-22 |
| | |||
* | dsputil: Split audio operations off into a separate context | Diego Biurrun | 2014-06-22 |
| | |||
* | dsputil: Split clear_block*/fill_block* off into a separate context | Diego Biurrun | 2014-06-18 |
| | |||
* | x86: h264: Don't keep data in the redzone across function calls on 64 bit unix | Martin Storsjö | 2014-06-10 |
| | | | | | | | | | | | | | | | | | | We know that the called function (ff_chroma_inter_body_mmxext) doesn't touch the redzone, and thus will be kept intact - thus, this doesn't fix any bug per se. However, valgrind's memcheck tool intentionally assumes that the redzone is clobbered on every function call and function return (see a long comment in valgrind/memcheck/mc_main.c). This avoids false positives in that tool, at the cost of an extra stack pointer adjustment. The other alternative would be a valgrind suppression for this issue, but that's an extra burden for everybody that wants to run libavcodec within valgrind. Signed-off-by: Martin Storsjö <martin@martin.st> | ||
* | dsputil: Split off quarterpel bits into their own context | Diego Biurrun | 2014-05-29 |
| | |||
* | dsputil: Move APE-specific bits into apedsp | Diego Biurrun | 2014-05-29 |
| |