Paper
4 May 2012 Dealing with performance/portability and performance/accuracy trade-offs in heterogeneous computing systems: a case study with matrix multiplication modulo primes
Matthew Wezowicz, B. David Saunder, Michela Taufer
Author Affiliations +
Abstract
We present the study of two important trade-offs in heterogeneous systems (i.e., between performance versus portability and between performance and accuracy) for a relevant linear algebra problem, matrix multiplication modulo primes. Integer matrix linear algebra methods rely heavily on matrix multiplication modulo primes. Double precision is necessary for exact representation of sufficiently many primes. We examine the performance losses due to the use of OpenCL versus CUDA and the use of double versus single precision. Our results indicate that performance losses from the former are minimal with the benefit of cross-platform portability and from the latter are acceptable when double precision is required.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Matthew Wezowicz, B. David Saunder, and Michela Taufer "Dealing with performance/portability and performance/accuracy trade-offs in heterogeneous computing systems: a case study with matrix multiplication modulo primes", Proc. SPIE 8403, Modeling and Simulation for Defense Systems and Applications VII, 840308 (4 May 2012); https://doi.org/10.1117/12.919323
Lens.org Logo
CITATIONS
Cited by 2 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Matrix multiplication

Linear algebra

Matrices

Computing systems

Computer programming

Computer programming languages

Visualization

RELATED CONTENT


Back to Top