An adaptive methodology for multi-GPU programming in OpenCL

Andre Luis Cavalcanti Bueno (Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil)
Noemi de La Rocque Rodriguez (Department of Information Technology, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil)
Elisa Dominguez Sotelino (Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil)

Engineering Computations

ISSN: 0264-4401

Publication date: 12 June 2017

Abstract

Purpose

The purpose of this work is to present a methodology that harnesses the computational power of multiple graphics processing units (GPUs) and hides the complexities of tuning GPU parameters from the users.

Design/methodology/approach

A methodology for auto-tuning OpenCL configuration parameters has been developed.

Findings

This described process helps simplify coding and generates a significant gain in time for each method execution.

Originality/value

Most authors develop their GPU applications for specific hardware configurations. In this work, a solution is offered to make the developed code portable to any GPU hardware.

Keywords

Citation

Cavalcanti Bueno, A.L., de La Rocque Rodriguez, N. and Dominguez Sotelino, E. (2017), "An adaptive methodology for multi-GPU programming in OpenCL", Engineering Computations, Vol. 34 No. 4, pp. 1277-1292. https://doi.org/10.1108/EC-12-2015-0392

Publisher

:

Emerald Publishing Limited

Copyright © 2017, Emerald Publishing Limited

To read the full version of this content please select one of the options below

You may be able to access this content by logging in via Shibboleth, Open Athens or with your Emerald account.
To rent this content from Deepdyve, please click the button.
If you think you should have access to this content, click the button to contact our support team.