The importance of dynamic load balancing among openmp thread teams for irregular workloads

Xiong Xiao, Shoichi Hirasawa, Hiroyuki Takizawa, Hiroaki Kobayashi

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

3 Citations (Scopus)

Abstract

Recently, massively-parallel many-core processors such as Intel Xeon Phi coprocessors have attracted researchers' attentions because various applications are significantly accelerated with those processors. In the field of high-performance computing, OpenMP is a standard programming model commonly used to parallelize a kernel loop for many-core processors. For hierarchical parallel processing, OpenMP version 4.0 or later allows programmers to group threads into multiple thread teams. In this paper, we first show the performance gain of using multiple thread teams even for one many-core processor. Then, we demonstrate that dynamic load balancing among those thread teams has a potential of significantly improving the performance of irregular workloads on a many-core processor. Although the current OpenMP specification does not offer such a dynamic load balancing mechanism, we discuss possible benefits of dynamic load balancing among thread teams through experiments using the Intel Xeon Phi coprocessor.

Original languageEnglish
Title of host publicationProceedings - 2016 4th International Symposium on Computing and Networking, CANDAR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages529-535
Number of pages7
ISBN (Electronic)9781509026555
DOIs
Publication statusPublished - 2017 Jan 13
Event4th International Symposium on Computing and Networking, CANDAR 2016 - Hiroshima, Japan
Duration: 2016 Nov 222016 Nov 25

Publication series

NameProceedings - 2016 4th International Symposium on Computing and Networking, CANDAR 2016

Other

Other4th International Symposium on Computing and Networking, CANDAR 2016
CountryJapan
CityHiroshima
Period16/11/2216/11/25

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Signal Processing
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'The importance of dynamic load balancing among openmp thread teams for irregular workloads'. Together they form a unique fingerprint.

Cite this