Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for CUDA arrays #10

Open
bheisler opened this issue Nov 25, 2018 · 2 comments
Open

Add support for CUDA arrays #10

bheisler opened this issue Nov 25, 2018 · 2 comments
Labels
Bigger Project A larger project, typically involving designing a safe, Rust-y wrapper around a CUDA api concept. New CUDA Feature Expose a new CUDA feature through RustaCUDA

Comments

@bheisler
Copy link
Owner

CUDA supports complex strided, multidimensional arrays when performing memory transfers. I'm not really sure what they're used for or how they work, but RustaCUDA should support them.

It may also be nice to support copying to/from ndarray, if that's feasible.

See the Memory module for more.

@bheisler bheisler added New CUDA Feature Expose a new CUDA feature through RustaCUDA Bigger Project A larger project, typically involving designing a safe, Rust-y wrapper around a CUDA api concept. labels Nov 25, 2018
@AndrewGaspar
Copy link
Contributor

I've got some familiarity with ndarray, but I'm not super familiar with CUDA arrays. I could perhaps take a look at this, but it may take a little bit to get up to speed.

@bheisler
Copy link
Owner Author

bheisler commented Dec 5, 2018

That would be great! I haven't dug into CUDA arrays yet myself. The official documentation is here: https://docs.nvidia.com/cuda/archive/8.0/cuda-driver-api/group__CUDA__MEM.html#group__CUDA__MEM

If you do end up adding integration to ndarray, it should have a feature flag.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Bigger Project A larger project, typically involving designing a safe, Rust-y wrapper around a CUDA api concept. New CUDA Feature Expose a new CUDA feature through RustaCUDA
Projects
None yet
Development

No branches or pull requests

2 participants