summaryrefslogtreecommitdiff
path: root/libavcodec/x86/vp9lpf.asm
Commit message (Expand)AuthorAgeFilesLines
* vp9/x86: add myself to copyright holders for loopfilter assembly.Ronald S. Bultje2014-12-271-0/+1
* vp9/x86: make filter_16_h work on 32-bit.Ronald S. Bultje2014-12-271-38/+153
* vp9/x86: make filter_48/84/88_h work on 32-bit.Ronald S. Bultje2014-12-271-17/+45
* vp9/x86: make filter_44_h work on 32-bit.Ronald S. Bultje2014-12-271-63/+77
* vp9/x86: make filter_16_v work on 32-bit.Ronald S. Bultje2014-12-271-39/+96
* vp9/x86: make filter_48/84_v work on 32-bit.Ronald S. Bultje2014-12-271-5/+3
* vp9/x86: make filter_88_v work on 32-bit.Ronald S. Bultje2014-12-271-47/+108
* vp9/x86: make filter_44_v work on 32-bit.Ronald S. Bultje2014-12-271-58/+96
* vp8/x86: save one register in SIGN_ADD/SUB.Ronald S. Bultje2014-12-271-14/+14
* vp9/x86: store unpacked intermediates for filter6/14 on stack.Ronald S. Bultje2014-12-271-72/+79
* vp8/x86: move variable assigned inside macro branch.Ronald S. Bultje2014-12-271-1/+1
* vp9/x86: simplify ABSSUM_CMP by inverting the comparison meaning.Ronald S. Bultje2014-12-271-51/+52
* vp8/x86: remove unused register from ABSSUB_CMP macro.Ronald S. Bultje2014-12-271-21/+21
* vp9/x86: slightly simplify 44/48/84/88 h stores.Ronald S. Bultje2014-12-271-48/+40
* vp9/x86: make cglobal statement more conservative in register allocation.Ronald S. Bultje2014-12-271-5/+16
* vp9/x86: save one register in loopfilter surface coverage.Ronald S. Bultje2014-12-271-28/+28
* avcodec/x86/vp9lpf: Always include x86util.asmMichael Niedermayer2014-09-171-2/+2
* x86: vpx/h264/hevc/mpeg2: share constantsChristophe Gisquet2014-08-061-2/+2
* x86/vp9lpf: use fewer instructions in SPLATB_MIXJames Almer2014-08-051-3/+2
* avcodec/x86/vp9lpf: add a comment above a bunch of SWAP.Clément Bœsch2014-04-201-0/+2
* avcodec/x86/vp9lpf: merge a few movs with other instructions.Clément Bœsch2014-04-201-42/+37
* vp9/x86: simplify FILTER_INIT.Clément Bœsch2014-04-191-6/+2
* vp9/x86: clarify mixed splatb.Clément Bœsch2014-04-191-5/+6
* x86/vp9lpf: simplify 2nd transpose in 44/48/88/84.Clément Bœsch2014-02-081-66/+48
* x86/vp9lpf: remove 8 SWAPs in 84/48 transpose.Clément Bœsch2014-02-051-23/+10
* x86/vp9lpf: remove braindead double pxor.Clément Bœsch2014-02-051-5/+5
* x86/vp9lpf: save a few mov in flat8in/hev masks calc.Clément Bœsch2014-02-051-7/+5
* x86/vp9lpf: add ff_vp9_loop_filter_[vh]_44_16_{sse2,ssse3,avx}.Clément Bœsch2014-02-051-27/+100
* x86/vp9lpf: add ff_vp9_loop_filter_h_{48,84}_16_{sse2,ssse3,avx}().Clément Bœsch2014-01-301-28/+31
* x86/vp9lpf: add ff_vp9_loop_filter_[vh]_88_16_sse2()James Almer2014-01-281-3/+17
* x86/vp9lpf: add ff_vp9_loop_filter_[vh]_88_16_{ssse3,avx}.Clément Bœsch2014-01-281-27/+182
* x86/vp9lpf: add a preload system in FILTER_UPDATE.Clément Bœsch2014-01-271-27/+20
* x86/vp9lpf: refactor v/h using common macros for P7 to Q7.Clément Bœsch2014-01-271-136/+80
* x86/vp9lpf: faster P7..Q7 accesses.Clément Bœsch2014-01-271-113/+114
* vp9/x86: add ff_vp9_loop_filter_[vh]_16_16_sse2().James Almer2014-01-171-6/+8
* vp9/x86: add AVX for itxfm and lpf.Clément Bœsch2014-01-151-1/+6
* vp9/x86: add ff_vp9_loop_filter_[vh]_16_16_ssse3().Clément Bœsch2014-01-121-0/+666