Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/FFmpeg/FFmpeg.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/libavcodec/aarch64
AgeCommit message (Expand)Author
2017-03-11aarch64: vp9itxfm: Make the larger core transforms standalone functionsMartin Storsjö
2017-03-11aarch64: vp9itxfm: Restructure the idct32 store macrosMartin Storsjö
2017-02-24aarch64: vp9itxfm: Reorder iadst16 coeffsMartin Storsjö
2017-02-24aarch64: vp9itxfm: Reorder the idct coefficients for better pairingMartin Storsjö
2017-02-24aarch64: vp9itxfm: Avoid reloading the idct32 coefficientsMartin Storsjö
2017-02-24aarch64: vp9lpf: Use dup+rev16+uzp1 instead of dup+lsr+dup+trn1Martin Storsjö
2017-02-24arm/aarch64: vp9lpf: Keep the comparison to E within 8 bitMartin Storsjö
2017-02-12aarch64: vp9lpf: Fix broken indentation/vertical alignmentMartin Storsjö
2017-02-11aarch64: vp9lpf: Interleave the start of flat8in into the calculation aboveMartin Storsjö
2017-02-11arm/aarch64: vp9lpf: Calculate !hev directlyMartin Storsjö
2017-02-11aarch64: vp9itxfm: Optimize 16x16 and 32x32 idct dc by unrollingMartin Storsjö
2017-02-11aarch64: vp9mc: Calculate less unused data in the 4 pixel wide horizontal filterMartin Storsjö
2017-02-11aarch64: vp9mc: Simplify the extmla macro parametersMartin Storsjö
2017-02-10aarch64: vp9itxfm: Fix incorrect vertical alignmentMartin Storsjö
2017-02-10aarch64: vp9itxfm: Update a comment to refer to a register with a different nameMartin Storsjö
2017-02-10aarch64: vp9itxfm: Use the right lane sizes in 8x8 for improved readabilityMartin Storsjö
2017-02-10aarch64: vp9itxfm: Use a single lane ld1 instead of ld1r where possibleMartin Storsjö
2017-02-10aarch64: vp9itxfm: Share instructions for loading idct coeffs in the 8x8 func...Martin Storsjö
2017-02-09aarch64: vp9itxfm: Do separate functions for half/quarter idct16 and idct32Martin Storsjö
2017-02-09aarch64: vp9itxfm: Move the load_add_store macro out from the itxfm16 pass2 f...Martin Storsjö
2017-02-09aarch64: vp9itxfm: Make the larger core transforms standalone functionsMartin Storsjö
2017-02-05aarch64: vp9itxfm: Restructure the idct32 store macrosMartin Storsjö
2017-01-24aarch64: Add NEON optimizations for 10 and 12 bit vp9 loop filterMartin Storsjö
2017-01-24aarch64: Add NEON optimizations for 10 and 12 bit vp9 itxfmMartin Storsjö
2017-01-24aarch64: Add NEON optimizations for 10 and 12 bit vp9 MCMartin Storsjö
2017-01-24aarch64: vp9dsp: Restructure the bpp checksMartin Storsjö
2017-01-14aarch64: vp9mc: Fix a comment to refer to a register with the right nameMartin Storsjö
2017-01-14aarch64: vp9dsp: Fix vertical alignment in the init fileMartin Storsjö
2017-01-14aarch64: vp9itxfm: Skip empty slices in the first pass of idct_idct 16x16 and...Martin Storsjö
2017-01-14aarch64: vp9itxfm: Don't repeatedly set x9 when nothing overwrites itMartin Storsjö
2017-01-14arm/aarch64: vp9itxfm: Fix indentation of macro argumentsMartin Storsjö
2017-01-14aarch64: vp9itxfm: Use w3 instead of x3 for the int eob parameterMartin Storsjö
2017-01-14aarch64: vp9: loop filter: replace 'orr; cbn?z' with 'adds; b.{eq,ne};Janne Grunau
2017-01-14aarch64: vp9: use alternative returns in the core loop filter functionJanne Grunau
2017-01-06imdct15: remove the AArch64 assemblyRostislav Pehlivanov
2017-01-03aarch64: vp9mc: Fix a comment to refer to a register with the right nameMartin Storsjö
2017-01-03aarch64: vp9dsp: Fix vertical alignment in the init fileMartin Storsjö
2016-12-19aarch64: vp9itxfm: Use the offset parameter to movrelMartin Storsjö
2016-12-14arm64: replace 'bic' with immediate with 'and' with inverted immediateJanne Grunau
2016-12-08aarch64: h264idct: Use the offset parameter to movrelMartin Storsjö
2016-12-01aarch64: vp9itxfm: Skip empty slices in the first pass of idct_idct 16x16 and...Martin Storsjö
2016-11-24aarch64: vp9itxfm: Don't repeatedly set x9 when nothing overwrites itMartin Storsjö
2016-11-24arm/aarch64: vp9itxfm: Fix indentation of macro argumentsMartin Storsjö
2016-11-19aarch64: vp9itxfm: Use w3 instead of x3 for the int eob parameterMartin Storsjö
2016-11-16aarch64: vp9: loop filter: replace 'orr; cbn?z' with 'adds; b.{eq,ne};Janne Grunau
2016-11-16aarch64: vp9: use alternative returns in the core loop filter functionJanne Grunau
2016-11-15aarch64: vp9: Implement NEON loop filtersMartin Storsjö
2016-11-15aarch64: vp9: Add NEON itxfm routinesMartin Storsjö
2016-11-15aarch64: vp9: Add NEON optimizations of VP9 MC functionsMartin Storsjö
2016-11-14aarch64: vp9: loop_filter: fix typo in skip flatout8 checkJanne Grunau
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-21 18:28:09 +0300