Merge requests · VideoLAN / dav1d · GitLab

arm32: looprestoration: Rewrite the SGR functions

!1765 · created Nov 19, 2024 by Martin Storsjö 1.5.1
ARM performance
- Merged
- Approved
updated Nov 20, 2024
arm64: looprestoration: Apply simplifications to align with C code

!1757 · created Nov 13, 2024 by Martin Storsjö 1.5.1
ARM performance
- Merged
- 2
- Approved
updated Nov 14, 2024
riscv64/mc16: Keep blend and blend_v operations in 16-bits

!1754 · created Nov 09, 2024 by Nathan E. Egge
RISC-V performance
- 1
updated Jan 06, 2025
Add mmx support to dav1d

!1753 · created Nov 07, 2024 by Nathan E. Egge
performance x86
- Closed
- 3
updated Jan 10, 2025
riscv64/mc: Only process w*3/4 elements in blend_v

!1752 · created Nov 04, 2024 by Nathan E. Egge 1.5.1
RISC-V performance
- Merged
- 1
- Approved
updated Nov 05, 2024
riscv64/mc16: Add 16bpc RVV blend_v function

!1751 · created Nov 04, 2024 by Nathan E. Egge 1.5.1
RISC-V performance
- Merged
- 2
- Approved
updated Nov 04, 2024
blend, blend_h, blend_v pwr9 implementation

!1750 · created Oct 29, 2024 by Luca Barbato 1.5.1
PowerPC performance
- Merged
- 6
- Approved
updated Nov 10, 2024
mc: Add 6-tap put/prep implementation to C code

!1745 · created Oct 25, 2024 by Nathan E. Egge
ARM PowerPC RISC-V loongarch performance x86
- 8
- Approved
updated Jan 06, 2025
x86: Improve SSSE3 SGR asm

!1744 · created Oct 18, 2024 by Henrik Gramner 1.5.1
performance x86
- Merged
- Approved
updated Nov 05, 2024
riscv64/itx: Replace vwadd+vnsra with vnclip

!1740 · created Oct 14, 2024 by Nathan E. Egge 1.5.0
RISC-V performance
- Merged
- 1
- Approved
updated Oct 16, 2024
x86: Make AVX2 SGR gatherless

!1733 · created Oct 04, 2024 by Henrik Gramner 1.5.0
performance x86
- Merged
- 5
- Approved
updated Oct 11, 2024
Loongarch： multiple SIMD optimization functions are added

!1723 · created Sep 06, 2024 by Hecai Yuan 1.5.0
loongarch performance
- Merged
- 15
- Approved
updated Oct 12, 2024
AArch64: Optimize lane load/store in MC functions

!1722 · created Sep 04, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 11
- Approved
updated Sep 30, 2024
AArch64: Optimize Armv8.0 Neon path of SBD H/HV 6-tap filters

!1718 · created Sep 02, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 1
- Approved
updated Sep 30, 2024
AArch64: Optimize Armv8.0 Neon path of HBD HV 6-tap filters

!1717 · created Sep 02, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 1
- Approved
updated Sep 30, 2024
AArch64: Optimize Armv8.0 Neon path of HBD horizontal filters

!1715 · created Aug 30, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 17
- Approved
updated Sep 30, 2024
AArch64: SVE MS armasm64 fix of HBD subpel filters

!1700 · created Aug 22, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 1
- Approved
updated Sep 02, 2024
Improve density of group context setting macros

!1698 · created Aug 19, 2024 by Kyle Siefring 1.5.0
performance
- Merged
- 19
- 1
- Approved
updated Sep 30, 2024
AArch64: Add HBD subpel filters using 128-bit SVE2

!1697 · created Aug 15, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 18
- Approved
updated Sep 02, 2024
AArch64: Add USMMLA impl. for SBD 6-tap H/HV filters

!1695 · created Aug 12, 2024 by Arpad Panyik 1.5.0
ARM performance
- Merged
- 6
- Approved
updated Sep 02, 2024

Prev
1
2
3
4
5
…
21
Next

VideoLAN code repository instance