A package for OpenCL based heterogeneous computing on clusters with many GPU devices

Amnon Barak*, Tal Ben-Nun, Ely Levy, Amnon Shiloh

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

77 Scopus citations

Abstract

Heterogeneous systems provide new opportunities to increase the performance of parallel applications on clusters with CPU and GPU architectures. Currently, applications that utilize GPU devices run their device-executable code on local devices in their respective hosting-nodes. This paper presents a package for running OpenMP, C++ and unmodified OpenCL applications on clusters with many GPU devices. This Many GPUs Package (MGP) includes an implementation of the OpenCL specifications and extensions of the OpenMP API that allow applications on one hosting-node to transparently utilize cluster-wide devices (CPUs and/or GPUs). MGP provides means for reducing the complexity of programming and running parallel applications on clusters, including scheduling based on task dependencies and buffer management. The paper presents MGP and the performance of its internals.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010
DOIs
StatePublished - 2010
Event2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010 - Heraklion, Crete, Greece
Duration: 20 Sep 201024 Sep 2010

Publication series

Name2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010

Conference

Conference2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010
Country/TerritoryGreece
CityHeraklion, Crete
Period20/09/1024/09/10

Keywords

  • GPGPU computing
  • HPC cluster
  • Open CL
  • OpenMP
  • Parallel applications

Fingerprint

Dive into the research topics of 'A package for OpenCL based heterogeneous computing on clusters with many GPU devices'. Together they form a unique fingerprint.

Cite this