Author: LLVM - Bewertung: 0x - Views:1
2026 EuroLLVM Developers' Meeting
https://llvm.org/devmtg/2026-04/
------
Title: rocMLIR: High-Performance ML Compilation for AMD GPUs with MLIR
Speaker: Pablo Antonio Martinez
------
Slides: https://llvm.org/devmtg/2026-04/slides/technical_talk/technical_talk_martinez.pdf
-----
This talk presents rocMLIR, a kernel generator for AMD GPUs using MLIR. We present the compilation flow from high-level IR (TOSA and Linalg dialects) to low-level code generation using downstream and upstream MLIR dialects (AMDGPU and ROCDL). We focus on implementing MI300X/MI350X features in MLIR, including double-rate MFMAs, DirectToLDS, and support for MXFP4/FP4 data types. We also cover application-specific optimizations such as SplitK for GEMMs and KV Cache for attention, along with fusion strategies.
-----
Videos Edited by Bash Films: http://www.BashFilms.com
SOCIAL SHARE CARD GENERATOR