Locality-optimized mixed static/dynamic scheduling for improving load balancing on SMPs

Published

Conference Paper

© ACM 2014. Application performance can be degraded significantly due to node-local load imbalances during application execution. Prior work suggested using a mixed static/dynamic scheduling approach for handling this problem, specifically in the context of fine-grained, transient load imbalances. Here, we consider an alternate strategy for more general load imbalances where fine-grained, transient load imbalance may be coupled with coarse-grained load imbalance. Specifically, we implement a scheduling scheme in which we modify the data layout in mixed static/dynamic scheduling, and add an additional tuned constraint in the dequeue function of our scheduler. Through experimentation of an n-body particle simulation code on modern multi-core architectures, our technique gives a 19.4% performance gain over dynamic scheduling, and an overall 48.6% performance gain over standard static scheduling.

Full Text

Duke Authors

Cited Authors

  • Kale, V; Randles, A; Gropp, WD

Published Date

  • September 9, 2014

Published In

  • Acm International Conference Proceeding Series

Volume / Issue

  • 09-12-September-2014 /

Start / End Page

  • 115 - 116

International Standard Book Number 13 (ISBN-13)

  • 9781450328753

Digital Object Identifier (DOI)

  • 10.1145/2642769.2642788

Citation Source

  • Scopus