Triton
Triton is a language and compiler for writing GPU kernels using blocks of values and compiler-managed mapping to execution resources.
How it works
A program instance operates on a chosen tile, while the compiler lowers vector operations and layouts to device instructions. Tile sizes, masks and launch configuration determine both correctness and performance.
Work through an example
A fused elementwise kernel can load values, apply several operations and store only the final result. A mask protects the final partial tile when the input size is not divisible by the block size.
Where the term can mislead
High-level tile code still needs numerical validation, race checks and target-specific measurements. Fewer source lines do not prove less GPU work.
Connect the idea
Take it into practice
Continue with the existing concept, apply it to an interview problem, or follow a course lesson. Access requirements are shown before you open a page.
New to GPUs? Start with the free execution-model concept.
Sources and scope
Examples here are teaching calculations, not measured GPU performance. Consult the linked documentation for the exact device, instruction and tool version. Source review: 25 October 2026.