Introducing CUDA Rust: Two Tracks for Writing GPU Kernels

8 relevance

New CUDA Rust integration for GPU kernels, highly novel and directly relevant to AI/ML infrastructure.

Languages developer.nvidia.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For a platform engineer building AI inference or agent runtimes, this removes the friction of mixing Rust host code with C++/Python kernels, enabling a unified Rust stack that catches memory bugs at compile time without sacrificing GPU performance.

Key Takeaways

Evaluate Tile first for new GPU kernels in Rust to decouple source from architecture-specific choices, dropping to SIMT only when you need fine-grained memory and thread control.

Summary

NVIDIA announced CUDA Rust, enabling GPU kernels written natively in Rust and compiled to PTX, closing the gap where kernels previously required other languages. Two tracks are offered: SIMT (cuda-oxide, a custom rustc codegen backend) for thread-level control, and Tile for a higher-level, architecture-agnostic approach where the compiler handles mapping. The move aligns with NVIDIA's broader Rust adoption, including the Nova Linux driver and Dynamo's Rust core, targeting systems-level AI infrastructure.

Author

Elizabeth Goodman