skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A lightweight approach to performance portability with targetDP

Abstract

Leading high performance computing systems achieve their status through use of highly parallel devices such as NVIDIA graphics processing units or Intel Xeon Phi many-core CPUs. The concept of performance portability across such architectures, as well as traditional CPUs, is vital for the application programmer. In this paper we describe targetDP, a lightweight abstraction layer which allows grid-based applications to target data parallel hardware in a platform agnostic manner. We demonstrate the effectiveness of our pragmatic approach by presenting performance results for a complex fluid application (with which the model was co-designed), plus separate lattice quantum chromodynamics particle physics code. For each application, a single source code base is seen to achieve portable performance, as assessed within the context of the Roofline model. TargetDP can be combined with Message Passing Interface (MPI) to allow use on systems containing multiple nodes: we demonstrate this through provision of scaling results on traditional and graphics processing unit-accelerated large scale supercomputers.

Authors:
 [1];  [1]
  1. EPCC, University of Edinburgh, UK
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF); UT-Battelle LLC/ORNL, Oak Ridge, TN (Unted States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1565706
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Journal Article
Journal Name:
International Journal of High Performance Computing Applications
Additional Journal Information:
Journal Volume: 32; Journal Issue: 2; Journal ID: ISSN 1094-3420
Publisher:
SAGE
Country of Publication:
United States
Language:
English
Subject:
Computer Science

Citation Formats

Gray, Alan, and Stratford, Kevin. A lightweight approach to performance portability with targetDP. United States: N. p., 2016. Web. doi:10.1177/1094342016682071.
Gray, Alan, & Stratford, Kevin. A lightweight approach to performance portability with targetDP. United States. doi:10.1177/1094342016682071.
Gray, Alan, and Stratford, Kevin. Wed . "A lightweight approach to performance portability with targetDP". United States. doi:10.1177/1094342016682071.
@article{osti_1565706,
title = {A lightweight approach to performance portability with targetDP},
author = {Gray, Alan and Stratford, Kevin},
abstractNote = {Leading high performance computing systems achieve their status through use of highly parallel devices such as NVIDIA graphics processing units or Intel Xeon Phi many-core CPUs. The concept of performance portability across such architectures, as well as traditional CPUs, is vital for the application programmer. In this paper we describe targetDP, a lightweight abstraction layer which allows grid-based applications to target data parallel hardware in a platform agnostic manner. We demonstrate the effectiveness of our pragmatic approach by presenting performance results for a complex fluid application (with which the model was co-designed), plus separate lattice quantum chromodynamics particle physics code. For each application, a single source code base is seen to achieve portable performance, as assessed within the context of the Roofline model. TargetDP can be combined with Message Passing Interface (MPI) to allow use on systems containing multiple nodes: we demonstrate this through provision of scaling results on traditional and graphics processing unit-accelerated large scale supercomputers.},
doi = {10.1177/1094342016682071},
journal = {International Journal of High Performance Computing Applications},
issn = {1094-3420},
number = 2,
volume = 32,
place = {United States},
year = {2016},
month = {6}
}

Works referenced in this record:

Legion: Expressing locality and independence with logical regions
conference, November 2012

  • Bauer, Michael; Treichler, Sean; Slaughter, Elliott
  • 2012 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, 2012 International Conference for High Performance Computing, Networking, Storage and Analysis
  • DOI: 10.1109/SC.2012.71

High-Precision Lattice QCD Confronts Experiment
journal, January 2004


The Physics of Liquid Crystals
journal, May 1995

  • de Gennes, P. G.; Prost, J.; Pelcovits, Robert
  • Physics Today, Vol. 48, Issue 5
  • DOI: 10.1063/1.2808028

LUDWIG: A parallel Lattice-Boltzmann code for complex fluids
journal, March 2001

  • Desplat, Jean-Christophe; Pagonabarraga, Ignacio; Bladon, Peter
  • Computer Physics Communications, Vol. 134, Issue 3
  • DOI: 10.1016/S0010-4655(00)00205-8

Manycore Performance-Portability: Kokkos Multidimensional Array Library
journal, January 2012

  • Edwards, H. Carter; Sunderland, Daniel; Porter, Vicki
  • Scientific Programming, Vol. 20, Issue 2
  • DOI: 10.1155/2012/917630

Scaling soft matter physics to thousands of graphics processing units in parallel
journal, March 2015

  • Gray, Alan; Hart, Alistair; Henrich, Oliver
  • The International Journal of High Performance Computing Applications, Vol. 29, Issue 3
  • DOI: 10.1177/1094342015576848

Regent: a high-productivity programming language for HPC with logical regions
conference, January 2015

  • Slaughter, Elliott; Lee, Wonchan; Treichler, Sean
  • Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '15
  • DOI: 10.1145/2807591.2807629

Roofline: an insightful visual performance model for multicore architectures
journal, April 2009

  • Williams, Samuel; Waterman, Andrew; Patterson, David
  • Communications of the ACM, Vol. 52, Issue 4
  • DOI: 10.1145/1498765.1498785