Open
Description
See https://rust-gpu.github.io/blog/2025/01/27/rust-cuda-reboot.
@RDambrosio016 has made me a new maintainer (I'm also a maintainer of rust-gpu).
Please comment here if you would like to be involved, or better yet put up some PRs or direct me to what needs to be done from your perspective!
Metadata
Metadata
Assignees
Type
Projects
Milestone
Relationships
Development
No branches or pull requests
Activity
AnubhabB commentedon Jan 27, 2025
This is exciting! I'd love to contribute (if I can). Any areas to dig deep into? That would probably help with figuring out starting points and if at-all I'd be capable enough to contribute!
In any case .. cheers .. will closely follow how this evolves!
LegNeato commentedon Jan 27, 2025
I'm still orienting myself as to the current state. I'd start with just trying to get the examples running on your machine and see if you hit anything I do not! Thank you so much for (potentially) helping. 🍻
David-OConnor commentedon Jan 27, 2025
The big thing is to make it work. Try it on a few different machines (OS, GPUs, CUDA versions etc), make it work on modern RustC and CUDA versions without errors. I switched to Cudarc because that is in a working state, and this isn't.
Dropping support for older versions of CUDA is fine if that makes it easier.
apriori commentedon Jan 27, 2025
That will be quite some work. Rustc changed significantly, so did libNVVM.
@LegNeato As you are a maintainer of rust-gpu, I would be curious to know what in the end lead you to rust-cuda. Afaik rust-gpu did not enter the compute kernel area too much.
LegNeato commentedon Jan 27, 2025
@apriori Actually, Rust-GPU does have pretty good support for Vulkan compute! It's just that Embark and most current contributors are focused on graphics use-cases. I personally care more about GPGPU.
What lead me here is I see a lot of opportunities and overlap between the two projects. As an end user writing GPU code in Rust, what I really want is to not care about Vulkan vs CUDA as the output target at all, similar to how I don't care about linux vs windows when writing CPU rust (or arm vs x86_64 for that matter). Of course, we also need to expose platform-specific stuff for those wanting to get the most out of their hardware or ecosystem (similar to how rust on the CPU exposes platform specific apis or ISA-specific escape hatches), but the progressive disclosure of complexity is key.
This wasn't going to happen as two completely separate projects that only peek over the fence occasionally, or with rust-cuda no longer being developed. So I am involved in both and can hopefully bring them together where they are different for different's sake.
txbm commentedon Jan 27, 2025
Will contribute
buk0vec commentedon Jan 27, 2025
Would definitely love to help out, I think this is a really cool project
Schmiedium commentedon Jan 27, 2025
I'd definitely like to contribute and get involved if I can. I'm currently a Master's Student at Georgia Tech and taking a Parallel algorithms course this semester. I have a few different machines, cards, and Operating systems I can try to put the current iteration on and see what issues pop up
LegNeato commentedon Jan 27, 2025
@Schmiedium Awesome! I think one thing everyone is going to hit is we are on a super old version of rust and cargo automatically upgrading versions will hit issues. I'm trying to untangle that a bit currently.
23 remaining items
igor-semyonov commentedon Feb 25, 2025
I am excited too.
When testing, which version should I use? The latest published one? Or the one from the main branch?
Schmiedium commentedon Feb 27, 2025
So I made some progress, I was able to get the dependencies updated to get a much newer version of rust supported. I played around with CI, and I got it working except for the fact that nvvm_codegen doesn't build. I also updated gpu_rand to be consistent with the newest rand_core api and that crate builds successfully now as well.
The windows part of CI also seems to take forever, it was over 40 minutes and still didn't get past installing CUDA, so that's something to dig into later.
Also the Ubuntu version of CI seems to fail at building the project which makes sense. However, it only succeeds in installing the CUDA toolkit the second time CI is run. I'm not sure what the deal there is, so more stuff to look into.
I think the next thing to work on is getting nvvm_codegen to build, and the rest of the project as well. Once that's done, and the remaining CI kinks are worked out, I think we'll have an updated, functioning project on our hands
Thanks to @juntyr for reviewing my pull request earlier
trigpolynom commentedon Mar 4, 2025
Hi all, looking into building a rust-based simulator with gpu support--needless to say, would love to help contribute to this project.
msharmavikram commentedon Mar 4, 2025
@LegNeato would love this project to run within the GPUMODE community. Interested?
LegNeato commentedon Mar 6, 2025
@msharmavikram not sure what that means.
boardwalkjoe commentedon Mar 21, 2025
@LegNeato what kinda CI machines do you need?
suyashb95 commentedon May 4, 2025
I have basic knowledge about Rust and have contributed to some open source Rust code. I'd love to contribute to open issues here though I have no knowledge about GPU programming frameworks (yet)
giantcow commentedon May 10, 2025
Would love to help out, got experience with Rust and some exp with CUDA (w/ C-bindings at least). Would also be interested in how we can streamline testing/CI/CD
distributedstatemachine commentedon Jun 22, 2025
I have rust experience , and would love to contribute .
Prabhakaran-Gokul commentedon Jul 11, 2025
Beginner in Rust and would love to contribute and learn along the way!