Pure: Evolving Message Passing To Better Leverage Shared Memory Within Nodes
Name
3627535.3638503.pdf
Size
979.89 KB
Format
Adobe PDF
Checksum (MD5)
a0dfe1802208b932f85ed927eda7cc13
Author(s)
Psota, James
Solar-Lezama, Armando
Date Issued
February 20, 2024
Publisher
ACM
Citation
Psota, James and Solar-Lezama, Armando. 2024. "Pure: Evolving Message Passing To Better Leverage Shared Memory Within Nodes."
Version
Final published version
Abstract
Pure is a new programming model and runtime system explicitly designed to take advantage of shared memory within nodes in the context of a mostly message passing interface enhanced with the ability to use tasks to make use of idle cores. Pure leverages shared memory in two ways: (a) by allowing cores to steal work from each other while waiting on messages to arrive, and, (b) by leveraging efficient lock-free data structures in shared memory to achieve high-performance messaging and collective operations between the ranks within nodes. We use microbenchmarks to evaluate Pure's key messaging and collective features and also show application speedups up to 2.1× on the CoMD molecular dynamics and the miniAMR adaptive mesh refinement applications scaling up to 4,096 cores.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3627535.3638503
