A Cost-Aware Parallel Workload Allocation Approach Based on Machine Learning Techniques

Shun Long, Grigori Fursin, Bjoern Franke

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Parallelism is one of the main sources for performance improvement in modern computing environment, but the efficient exploitation of the available parallelism depends on a number of parameters. Determining the optimum number of threads for a given data parallel loop, for example, is a difficult problem and dependent on the specific parallel platform. This paper presents a learning-based approach to parallel workload allocation in a cost-aware manner. This approach uses static program features to classify programs, before deciding the best workload allocation scheme based on its prior experience with similar programs. Experimental results on 12 Java benchmarks (76 test cases with different workloads in total) show that it can efficiently allocate the parallel workload among Java threads and achieve an efficiency of 86% on average.
Original languageEnglish
Title of host publicationNetwork and Parallel Computing
Subtitle of host publicationIFIP International Conference, NPC 2007, Dalian, China, September 18-21, 2007. Proceedings
EditorsKeqiu Li, Chris Jesshope, Hai Jin, Jean-Luc Gaudiot
PublisherSpringer
Pages506-515
Number of pages10
ISBN (Electronic)978-3-540-74784-0
ISBN (Print)978-3-540-74783-3
DOIs
Publication statusPublished - Sept 2007

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume4672

Keywords / Materials (for Non-textual outputs)

  • parallelism
  • workload allocation
  • cost
  • instance-based learning

Fingerprint

Dive into the research topics of 'A Cost-Aware Parallel Workload Allocation Approach Based on Machine Learning Techniques'. Together they form a unique fingerprint.

Cite this