This talk presents CUDA Tile IR, a tile-based CUDA dialect for MLIR, focusing on the design trade-offs that differentiate it from upstream dialects such as arith, tensor, memref, linalg, and async. Using concrete examples (e.g., matrix multiplication, TMA?friendly load/store patterns, and token-based ordering), the talk contrasts CUDA Tile IR?s type system, operations, and overall dialect design with existing MLIR abstractions, and highlights practical lessons for developers designing their own vendor-specific dialects.

Speakers: Matthias Springer (NVIDIA Switzerland), Lorenzo Chelini (NVIDIA Switzerland)