summaryrefslogtreecommitdiffstats
path: root/libavcodec/x86
Commit message (Expand)AuthorAgeFilesLines
* lavc: Remove deprecated XvMC support hacksDiego Biurrun2017-03-231-14/+2
* x86: fft: Port to cpuflagsDiego Biurrun2017-03-141-51/+43
* x86: h264: Simplify DEQUANT macro with cpuflagsDiego Biurrun2017-03-141-24/+28
* x86: vp8dsp: port FILTER_BILINEAR macro to cpuflagsDiego Biurrun2017-03-141-77/+66
* x86util: Port all macros to cpuflagsDiego Biurrun2017-03-141-4/+1
* x86: Merge align directives into SECTION_RODATA declarations where possibleDiego Biurrun2017-03-054-10/+5
* build: Generalize yasm/nasm-related variable namesDiego Biurrun2017-03-0112-77/+77
* x86: hevc: Add missing colons after assembly labelsDiego Biurrun2017-03-011-3/+3
* asm: Consistently uppercase SECTION markersDiego Biurrun2017-02-033-3/+3
* Mark some arrays that never change as const.Anton Khirnov2017-02-013-16/+16
* mpegvideoenc: make a table constAnton Khirnov2017-01-191-5/+6
* cabac: x86: Give optimizations header a more meaningful nameDiego Biurrun2016-12-011-5/+1
* h264_qpel: x86: Move function with only one instance out of template macroDiego Biurrun2016-11-081-9/+11
* x86: Drop stray semicolons after function definitionsDiego Biurrun2016-11-052-11/+11
* vp9: Flip the order of arguments in MC functionsMartin Storsjö2016-11-032-27/+27
* hevc: x86: Add add_residual() SIMD optimizationsPierre Edouard Lepere2016-10-223-3/+415
* audiodsp: x86: Remove pointless header fileDiego Biurrun2016-10-192-26/+3
* x86: videodsp: Add parentheses to expression to work around warningDiego Biurrun2016-10-191-1/+1
* x86: Add missing colons after assembly labelsDiego Biurrun2016-10-176-13/+13
* hevc: Add SSE2 and AVX IDCTAlexandra Hájková2016-10-112-30/+811
* Revert "hevc: x86: Refactor IDCT macro declarations"Anton Khirnov2016-10-061-11/+23
* h264_intrapred: x86: Update comments left behind in 95c89da36ebeeb96b7146c0d7...Diego Biurrun2016-10-062-66/+76
* hevc: x86: Refactor IDCT macro declarationsDiego Biurrun2016-10-061-23/+11
* vp9lpf/x86: make filter_16_h work on 32-bit.Ronald S. Bultje2016-10-042-41/+154
* vp9lpf/x86: make filter_48/84/88_h work on 32-bit.Ronald S. Bultje2016-10-042-26/+48
* vp9lpf/x86: make filter_44_h work on 32-bit.Ronald S. Bultje2016-10-042-66/+78
* vp9lpf/x86: make filter_16_v work on 32-bit.Ronald S. Bultje2016-10-042-40/+99
* vp9lpf/x86: make filter_48/84_v work on 32-bit.Ronald S. Bultje2016-10-042-7/+9
* vp9lpf/x86: make filter_88_v work on 32-bit.Ronald S. Bultje2016-10-042-48/+109
* vp9lpf/x86: make filter_44_v work on 32-bit.Ronald S. Bultje2016-10-042-59/+100
* vp9lpf/x86: save one register in SIGN_ADD/SUB.Ronald S. Bultje2016-10-041-14/+14
* vp9lpf/x86: store unpacked intermediates for filter6/14 on stack.Ronald S. Bultje2016-10-041-72/+79
* vp9lpf/x86: move variable assigned inside macro branch.Ronald S. Bultje2016-10-041-1/+1
* vp9lpf/x86: simplify ABSSUM_CMP by inverting the comparison meaning.Ronald S. Bultje2016-10-041-51/+52
* vp9lpf/x86: remove unused register from ABSSUB_CMP macro.Ronald S. Bultje2016-10-041-21/+21
* vp9lpf/x86: slightly simplify 44/48/84/88 h stores.Ronald S. Bultje2016-10-041-48/+40
* vp9lpf/x86: make cglobal statement more conservative in register allocation.Ronald S. Bultje2016-10-041-5/+16
* vp9lpf/x86: save one register in loopfilter surface coverage.Ronald S. Bultje2016-10-041-28/+28
* vp9lpf/x86: add ff_vp9_loop_filter_[vh]_44_16_{sse2,ssse3,avx}.Clément Bœsch2016-10-042-27/+99
* vp9lpf/x86: add ff_vp9_loop_filter_h_{48,84}_16_{sse2,ssse3,avx}().Clément Bœsch2016-10-042-48/+53
* vp9lpf/x86: add an SSE2 version of vp9_loop_filter_[vh]_88_16James Almer2016-10-042-3/+20
* vp9lpf/x86: add ff_vp9_loop_filter_[vh]_88_16_{ssse3,avx}.Clément Bœsch2016-10-042-27/+163
* vp9lpf/x86: add ff_vp9_loop_filter_[vh]_16_16_sse2().James Almer2016-10-042-10/+23
* vp9lpf/x86: add x86 SSSE3/AVX SIMD for vp9_loop_filter_[vh]_16_16.Clément Bœsch2016-10-043-1/+618
* ac3dsp: x86: Replace inline asm for in-decoder downmixing with standalone asmJustin Ruggles2016-10-013-134/+230
* ac3dsp: Reverse matrix in/out order in downmix()Justin Ruggles2016-10-011-17/+19
* x86/h264_weight: use appropriate register size for weight parametersHendrik Leppkes2016-09-301-6/+6
* mpegaudiodsp: Change type of array stride parameters to ptrdiff_tDiego Biurrun2016-09-291-1/+1
* h264chroma: Change type of stride parameters to ptrdiff_tDiego Biurrun2016-09-295-50/+31
* idct: Change type of array stride parameters to ptrdiff_tDiego Biurrun2016-09-298-52/+55
OpenPOWER on IntegriCloud