A Proof of Concept for Optimizing Task Parallelism by Locality Queues - Computer Science > PerformanceReport as inadecuate




A Proof of Concept for Optimizing Task Parallelism by Locality Queues - Computer Science > Performance - Download this document for free, or read online. Document in PDF available to download.

Abstract: Task parallelism as employed by the OpenMP task construct, although ideal fortackling irregular problems or typical producer-consumer schemes, bears somepotential for performance bottlenecks if locality of data access is important,which is typically the case for memory-bound code on ccNUMA systems.
We presenta programming technique which ameliorates adverse effects of dynamic taskdistribution by sorting tasks into locality queues, each of which is preferablyprocessed by threads that belong to the same locality domain.
Dynamicscheduling is fully preserved inside each domain, and is preferred overpossible load imbalance even if non-local access is required.
The effectivenessof the approach is demonstrated using a blocked six-point stencil solver as atoy model.



Author: Markus Wittmann, Georg Hager

Source: https://arxiv.org/



DOWNLOAD PDF




Related documents