Workshops Archive

OpenSHMEM MLIR: A Dialect for Compile-Time Optimization of One-Sided Communications

Workshop: LLVM-HPC2025: The 11th Workshop on the LLVM Compiler Infrastructure in HPC

Authors: Michael Beebe (Texas Tech University), Benjamin Michalowicz (Ohio State University), Andrew McNamara (New Mexico Consortium), Yash Kumar (Texas Tech University), Dhabaleswar K. Panda (Ohio State University), Yong Chen (Texas Tech University), and Wendy Poole and Steve Poole (Los Alamos National Laboratory (LANL))

Abstract: Communication increasingly limits performance in high-performance computing (HPC), yet mainstream compilers focus on computation because communication intent is lost early in compilation. OpenSHMEM offers a one-sided Partitioned Global Address Space (PGAS) model with symmetric memory and explicit synchronization, but lowering to opaque runtime calls hides these semantics from analysis.

We present an OpenSHMEM dialect for Multi-Level Intermediate Representation (MLIR) that preserves one-sided communication, symmetric memory, and team/context structure as first-class intermediate representation (IR) constructs. Retaining these semantics prior to lowering enables precise, correctness-preserving optimizations that are difficult to recover from LLVM IR. The dialect integrates with existing MLIR/LLVM passes while directly representing communication and synchronization intent.

We demonstrate four transformations: recording the number of processing elements, fusing compatible atomics, converting blocking operations to non-blocking forms when safe, and aggregating small messages. These examples show how explicit OpenSHMEM semantics enable communication-aware optimization and lay the groundwork for richer cross-layer analyses.

Back to LLVM-HPC2025: The 11th Workshop on the LLVM Compiler Infrastructure in HPC Archive Listing Back to Full Workshop Archive Listing