Task-parallel programming on NUMA architectures

Authors:
Christian Terboven;Dirk Schmidl;Tim Cramer;Dieter an Mey
Affiliations:
Center for Computing and Communication, JARA, RWTH Aachen University, Germany;Center for Computing and Communication, JARA, RWTH Aachen University, Germany;Center for Computing and Communication, JARA, RWTH Aachen University, Germany;Center for Computing and Communication, JARA, RWTH Aachen University, Germany
Venue:
Euro-Par'12 Proceedings of the 18th international conference on Parallel Processing
Year:
2012

Citing 7
Cited 1

Support for OpenMP tasks in Nanos v4

CASCON '07 Proceedings of the 2007 conference of the center for advanced studies on Collaborative research
Features for image retrieval: an experimental comparison

Information Retrieval
Data and thread affinity in openmp programs

Proceedings of the 2008 workshop on Memory access on future processors: a solved problem?
An Experimental Evaluation of the New OpenMP Tasking Model

Languages and Compilers for Parallel Computing
The Design of OpenMP Tasks

IEEE Transactions on Parallel and Distributed Systems
Nested parallelization with OpenMP

International Journal of Parallel Programming
Scheduling task parallelism on multi-socket multicore systems

Proceedings of the 1st International Workshop on Runtime and Operating Systems for Supercomputers

Assessing the performance of OpenMP programs on the intel xeon phi

Euro-Par'13 Proceedings of the 19th international conference on Parallel Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The multicore era has led to a renaissance of shared memory parallel programming models. Moreover, the introduction of task-level parallelization raises the level of abstraction compared to thread-centric expression of parallelism. However, tasks might exhibit poor performance on NUMA systems if locality cannot be controlled and non-local data is accessed. This work investigates various approaches to express task-parallelism using the OpenMP tasking model, from a programmer's point of view. We describe and compare task creation strategies and devise methods to preserve locality on NUMA architectures while optimizing the degree of parallelism. Our proposals are evaluated on reasonably large NUMA systems with both important application kernels as well as real-world simulation codes.