Steuwer, M. , Kegel, P. and Gorlatch, S. (2011) SkelCL - A Portable Skeleton Library for High-Level GPU Programming. In: 25th IEEE International Symposium on Parallel and Distributed Processing (IPDPS 2011), Anchorage, AK, USA, 16-20 May 2011, pp. 1176-1182. ISBN 9781612844251 (doi: 10.1109/IPDPS.2011.269)
|
Text
148988.pdf - Accepted Version 472kB |
Abstract
While CUDA and OpenCL made general-purpose programming for Graphics Processing Units (GPU) popular, using these programming approaches remains complex and error-prone because they lack high-level abstractions. The especially challenging systems with multiple GPU are not addressed at all by these low-level programming models. We propose SkelCL – a library providing so-called algorithmic skeletons that capture recurring patterns of parallel computation and communication, together with an abstract vector data type and constructs for specifying data distribution. We demonstrate that SkelCL greatly simplifies programming GPU systems. We report the competitive performance results of SkelCL using both a simple Mandelbrot set computation and an industrial-strength medical imaging application. Because the library is implemented using OpenCL, it is portable across GPU hardware of different vendors.
Item Type: | Conference Proceedings |
---|---|
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Steuwer, Dr Michel |
Authors: | Steuwer, M., Kegel, P., and Gorlatch, S. |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
College/School: | College of Science and Engineering > School of Computing Science |
ISSN: | 1530-2075 |
ISBN: | 9781612844251 |
Published Online: | 01 September 2011 |
Copyright Holders: | Copyright © 2011 IEEE |
First Published: | First published in 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW): 1176-1182 |
Publisher Policy: | Reproduced in accordance with the publisher copyright policy |
University Staff: Request a correction | Enlighten Editors: Update this record