Things to port from CUDA.jl
Open
help wanted
- Dominant language
- Julia
- Stars
- 463
- Forks
- 68
- Avg merge
- 1d 19m
- Merged PRs (30d)
- 32
Description
- fast scalar indexing when using unified memory: https://github.com/JuliaGPU/CUDA.jl/pull/2138
- automatic memory synchronization: https://github.com/JuliaGPU/CUDA.jl/pull/2335
- nonblocking synchronization: https://github.com/JuliaGPU/CUDA.jl/pull/2025
- asynchronous copying, when possible (i.e., between MtlArrays)
Note that I'm pointing to the base PRs here; CUDA.jl#master is likely to have additional fixes to that code.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.