We're excited to announce the reboot of the Rust CUDA project. Rust CUDA enables you to write and run CUDA kernels in Rust, executing directly on NVIDIA GPUs using NVVM IR.

Our immediate focus is on modernizing the project and integrating with other GPU-related efforts in the Rust ecosystem.

To follow along or get involved, check out the rust-cuda repo on GitHub.

I read the excellent post Optimizing a WebGPU Matmul Kernel for 1TFLOP+ Performance by Zach Nussbaum and thought it might be fun to reimplement it with Rust GPU.

We'll follow Zach's original post closely, comparing and contrasting using Rust vs the WGSL and Typescript from his post.

At the end, I'll show some unique benefits of using Rust on the GPU.

We’re thrilled to introduce two new maintainers for the Rust GPU project: Schell Scivally and Firestar99.

Both bring experience in graphics programming, a deep understanding of Rust, and a passion for advancing GPU computing.

We are excited to announce that as of today the Rust GPU project will be transitioning from Embark Studios to community ownership under the Rust GPU GitHub organization. This move marks the beginning of a broader strategy aimed at revitalizing, unifying, and standardizing GPU programming in Rust. We are eager to share more details in the near future but in the meantime if you are a maintainer of a GPU-related Rust project, please reach out!