Introducing and implementing the allpairs skeleton for programming multi-GPU systems

Steuwer, M. , Friese, M., Albers, S. and Gorlatch, S. (2014) Introducing and implementing the allpairs skeleton for programming multi-GPU systems. International Journal of Parallel Programming, 42(4), pp. 601-618. (doi:10.1007/s10766-013-0265-6)

148973.pdf - Accepted Version



Algorithmic skeletons simplify software development: they abstract typical patterns of parallelism and provide their efficient implementations, allowing the application developer to focus on the structure of algorithms, rather than on implementation details. This becomes especially important for modern parallel systems with multiple graphics processing units (GPUs) whose programming is complex and error-prone, because state-of-the-art programming approaches like CUDA and OpenCL lack high-level abstractions. We define a new algorithmic skeleton for allpairs computations which occur in real-world applications, ranging from bioinformatics to physics. We develop the skeleton’s generic parallel implementation for multi-GPU Systems in OpenCL. To enable the automatic use of the fast GPU memory, we identify and implement an optimized version of the allpairs skeleton with a customizing function that follows a certain memory access pattern. We use matrix multiplication as an application study for the allpairs skeleton and its two implementations and demonstrate that the skeleton greatly simplifies programming, saving up to 90 % of lines of code as compared to OpenCL. The performance of our optimized implementation is up to 6.8 times higher as compared with the generic implementation and is competitive to the performance of a manually written optimized OpenCL code.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Steuwer, Dr Michel
Authors: Steuwer, M., Friese, M., Albers, S., and Gorlatch, S.
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Science and Engineering > School of Computing Science
Journal Name:International Journal of Parallel Programming
ISSN (Online):1573-7640
Published Online:24 August 2014
Copyright Holders:Copyright © 2013 Springer Science+Business Media
First Published:First published in International Journal of Parallel Programming 42(4): 601-618
Publisher Policy:Reproduced in accordance with the publisher copyright policy

University Staff: Request a correction | Enlighten Editors: Update this record