Merge Requests · VideoLAN / dav1d · GitLab

x86: Add high bitdepth AVX2 asm

!1195 · created May 04, 2021 by Henrik Gramner 0.9.0 performance
- MERGED
- Approved
- 2
- 6
updated May 11, 2021
arm64: filmgrain: Add NEON implementation of the generate_grain_uv functions

!1190 · created Apr 27, 2021 by Martin Storsjö performance
- MERGED
- Approved
- 0
updated May 04, 2021
arm64: filmgrain: Add NEON implementation of the generate_grain_y function

!1185 · created Apr 08, 2021 by Martin Storsjö performance
- MERGED
- 1
updated Apr 28, 2021
arm64: filmgrain: Add NEON implementation of the fguv function

!1182 · created Mar 22, 2021 by Martin Storsjö 0.9.0 performance
- MERGED
- Approved
- 3
updated Apr 22, 2021
arm64: Add NEON implementation of fgy_32x32xn

!1180 · created Mar 12, 2021 by Martin Storsjö 0.9.0 performance
- MERGED
- Approved
- 8
updated Mar 16, 2021
arm32: itx: Add a NEON implementation of itx for 10 bpc

!1175 · created Feb 18, 2021 by Martin Storsjö 0.8.2 performance
- MERGED
- Approved
- 2
updated Feb 21, 2021
x86: Rewrite SGR AVX2 asm

!1163 · created Feb 10, 2021 by Henrik Gramner 0.8.2 performance
- MERGED
- Approved
- 4
updated Feb 11, 2021
arm64: itx16: Use usqadd to avoid separate clamping of negative values

!1162 · created Feb 10, 2021 by Martin Storsjö 0.8.2 performance
- MERGED
- Approved
- 0
updated Feb 11, 2021
Port rav1e HBD cdef_dir to dav1d

!1161 · created Feb 09, 2021 by Nathan Egge 0.8.2 performance
- MERGED
- Approved
- 13
updated Feb 17, 2021
Port rav1e HBD AVX2 wiener filter to dav1d

!1160 · created Feb 09, 2021 by Nathan Egge 0.8.2 performance
- MERGED
- Approved
- 1
- 12
updated Feb 19, 2021
arm64: mc: Improve first tap for inorder cores

!1159 · created Feb 08, 2021 by Kyle Siefring 0.8.2 performance
- MERGED
- Approved
- 1
updated Feb 09, 2021
arm32: mc: Optimize warp by doing horz filtering in 8 bit

!1155 · created Feb 08, 2021 by Martin Storsjö 0.8.2 performance
- MERGED
- Approved
- 0
updated Feb 08, 2021
arm64: looprestoration: Rewrite the wiener functions

!1154 · created Feb 08, 2021 by Martin Storsjö 0.8.2 performance
- MERGED
- Approved
- 0
updated Feb 09, 2021
Shrink some wedge initialization tables

!1150 · created Feb 06, 2021 by Henrik Gramner 0.8.2 performance
- MERGED
- Approved
- 0
updated Feb 06, 2021
arm32: loopfilter16: Remove an extra immediate move

!1149 · created Feb 05, 2021 by Martin Storsjö 0.8.2 performance
- MERGED
- Approved
- 0
updated Feb 06, 2021
arm: Move the sub_sp and sub_sp_aligned macros to the shared util file

!1143 · created Feb 02, 2021 by Martin Storsjö 0.8.2 buildsystem performance
- MERGED
- Approved
- 1
- 0
updated Feb 07, 2021
Coefficient decoding optimizations

!1140 · created Jan 30, 2021 by Henrik Gramner 0.8.2 performance
- MERGED
- Approved
- 12
updated Feb 16, 2021
arm: looprestoration: Clean up right edge padding, exploit wiener filter symmetry

!1138 · created Jan 27, 2021 by Martin Storsjö 0.8.2 performance
- MERGED
- Approved
- 2
updated Feb 06, 2021
arm64: cdef 8bpc: Accumulate sum in bytes

!1137 · created Jan 26, 2021 by Kyle Siefring 0.8.2 performance
- MERGED
- Approved
- 8
updated Feb 06, 2021
cli: Optimize md5 checksum calculation

!1118 · created Jan 06, 2021 by Henrik Gramner 0.8.2 performance tools
- MERGED
- Approved
- 1
- 1
updated Feb 06, 2021

Prev
1
2
3
4
5
…
11
Next