Approaches for Task Affinity in OpenMP
Document typeConference lecture
PublisherSpringer International Publishing
Rights accessOpen Access
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
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.
|Approaches for Task Affinity in OpenMP.pdf||173,1Kb||View/Open|