The design of OpenMP thread affinity

Authors:
Alexandre E. Eichenberger;Christian Terboven;Michael Wong;Dieter an Mey
Affiliations:
IBM T.J. Watson Research Center, New York;Center for Computing and Communication, JARA, RWTH Aachen University, Germany;IBM Software Group, Toronto, Ontario, Canada;Center for Computing and Communication, JARA, RWTH Aachen University, Germany
Venue:
IWOMP'12 Proceedings of the 8th international conference on OpenMP in a Heterogeneous World
Year:
2012

Citing 5
Cited 0

MPI-The Complete Reference, Volume 1: The MPI Core

MPI-The Complete Reference, Volume 1: The MPI Core
Data and thread affinity in openmp programs

Proceedings of the 2008 workshop on Memory access on future processors: a solved problem?
hwloc: A Generic Framework for Managing Hardware Affinities in HPC Applications

PDP '10 Proceedings of the 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing
Enabling locality-aware computations in OpenMP

Scientific Programming - Exploring Languages for Expressing Medium to Massive On-Chip Parallelism
Binding nested OpenMP programs on hierarchical memory architectures

IWOMP'10 Proceedings of the 6th international conference on Beyond Loop Level Parallelism in OpenMP: accelerators, Tasking and more

Quantified Score

Hi-index	0.00

Visualization

Abstract

Exascale machines will employ significantly more threads than today, but even on current architectures controlling thread affinity is crucial to fuel all the cores and to maintain data affinity, but both MPI and OpenMP lack a solution to this problem. In this work, we present a thread affinity model for OpenMP, which will be shown to work well with hybrid use cases, too. It maintains a separation of platform-specific data and algorithm-specific properties, thus offering deterministic behavior and simplicity in use.