International Journal of Parallel Programming

, Volume 42, Issue 4, pp 601–618

Introducing and Implementing the Allpairs Skeleton for Programming Multi-GPU Systems

  • Michel Steuwer
  • Malte Friese
  • Sebastian Albers
  • Sergei Gorlatch
Article

DOI: 10.1007/s10766-013-0265-6

Cite this article as:
Steuwer, M., Friese, M., Albers, S. et al. Int J Parallel Prog (2014) 42: 601. doi:10.1007/s10766-013-0265-6

Abstract

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.

Keywords

High-level programming models Algorithmic skeletons   GPU computing Allpairs computation SkelCL 

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Michel Steuwer
    • 1
  • Malte Friese
    • 1
  • Sebastian Albers
    • 1
  • Sergei Gorlatch
    • 1
  1. 1.Department of Mathematics and Computer ScienceUniversity of MuensterMünsterGermany

Personalised recommendations