OpenSHMEM MLIR: A Dialect for Compile-Time Optimization of One-Sided Communications
Open Access
- 15 November 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1075-1087
Abstract
No abstract availableFunding Information
- National Science Foundation (CNS-1939140)
- Los Alamos National Laboratory (19537)
This publication has 14 references indexed in Scilit:
- Retargeting and Respecializing GPU Workloads for Performance Portability2024
- Extending OpenSHMEM with Aggregation Support for Improved Message Rate Performance2023
- High-Performance GPU-to-CPU Transpilation and Optimization via High-Level Parallel Constructs2023
- OpenSHMEM over MPI as a Performance Contender: Thorough Analysis and Optimizations2022
- Integrating Asynchronous Task Parallelism with OpenSHMEM2016
- Increasing Computational Asynchrony in OpenSHMEM with Active Messages2016
- OWN: Optical and Wireless Network-on-Chip for Kilo-core Architectures2015
- Flat combining and the synchronization-parallelism tradeoff2010
- Design and evaluation of Nemesis, a scalable, low-latency, message-passing communication subsystem2006
- The NYU Ultracomputer—Designing an MIMD Shared Memory Parallel ComputerIEEE Transactions on Computers, 1983