JuliaGPU / JuliaGPU/Metal.jl

Things to port from CUDA.jl

Open
#443 1 comment 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.