Approaches for Task Affinity in OpenMP

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder

ProjectCOMPUTACION DE ALTAS PRESTACIONES VII (MINECO-TIN2015-65316-P)

Abstract

OpenMP tasking supports parallelization of irregular algorithms. Recent OpenMP specifications extended tasking to increase functionality and to support optimizations, for instance with the taskloop construct. However, task scheduling remains opaque, which leads to inconsistent performance on NUMA architectures. We assess design issues for task affinity and explore several approaches to enable it. We evaluate these proposals with implementations in the Nanos++ and LLVM OpenMP runtimes that improve performance up to 40 % and significantly reduce execution time variation.

CitationTerboven, Christian [et al.]. Approaches for Task Affinity in OpenMP. A: 12th International Workshop on OpenMP, IWOMP 2016, Nara, Japan, October 5-7, 2016, Proceedings. "OpenMP: Memory, Devices, and Tasks". Springer International Publishing, 2016, p. 102-115.

URIhttp://hdl.handle.net/2117/90912

DOI10.1007/978-3-319-45550-1_8

ISBN978-3-319-45549-5

Publisher versionhttp://link.springer.com/chapter/10.1007%2F978-3-319-45550-1_8

Collections

Computer Sciences - Ponències/Comunicacions de congressos [500]

View Usage Statistics

Show full item record

Files	Description	Size	Format	View
Approaches for Task Affinity in OpenMP.pdf		173,1Kb	PDF	View/Open

UPCommons. Global access to UPC knowledge

Approaches for Task Affinity in OpenMP

View/Open

Browse