Menu

1 / 3

Translating CUDA Tile Operations from Python to Rust Using Agentic AI

NVIDIA Technical Blog·Tanya Lenz·5 days ago
#1Tm6DnRB
#developer#kernel#cutile#rust#tile
Reading 0:00
15s threshold

cuTile Rust ( cutile-rs ) is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to tile-based GPU kernels, it splits mutable outputs into disjoint pieces and preserves the host-side ownership contract across kernel launches. It also allows programmers to opt out locally when they need lower-level control, enabling direct execution of Tile IR operations.

The TileGym CUDA tile kernel library has accumulated a large library of production kernels written in CUDA Tile Python ( cuTile Python ) and Triton-TileIR ( nvtriton ). To make all of these kernels available in Rust as well, our team built an AI agent skill that translates cuTile Python and Triton-TileIR kernels into cuTile Rust.

Using this skill, we ported all 24 public TileGym operators to cuTile Rust and reached 99.5% of cuTile Python performance on average.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.