Authors: Dominik Goddeke, Hilmar Wobker, Robert Strzodka, Jamaludin Mohd-Yusof, Patrick McCormick, Stefan Turek
Addresses: Institute of Applied Mathematics, TU Dortmund, Dortmund, Germany. ' Institute of Applied Mathematics, TU Dortmund, Dortmund, Germany. ' Max Planck Center, Max Planck Institut Informatik, Saarbrucken, Germany. ' Computer, Computational and Statistical Sciences Division, Los Alamos National Laboratory, USA. ' Computer, Computational and Statistical Sciences Division, Los Alamos National Laboratory, USA. ' Institute of Applied Mathematics, TU Dortmund, Dortmund, Germany
Abstract: We have previously presented an approach to include graphics processing units as co-processors in a parallel Finite Element multigrid solver called FEAST. In this paper we show that the acceleration transfers to real applications built on top of FEAST, without any modifications of the application code. The chosen solid mechanics code is well suited to assess the practicability of our approach due to higher accuracy requirements and a more diverse CPU/co-processor interaction. We demonstrate in detail that the single precision execution of the co-processor does not affect the final accuracy, and analyse how the local acceleration gains of factors 5.5-9.0 translate into 1.6- to 2.6-fold total speed-up.
Keywords: heterogeneous computing; parallel scientific computing; CSM; computational solid mechanics; GPUs; graphic processor units; co-processor integration; multigrid solvers; domain decomposition; finite element method; FEM.
International Journal of Computational Science and Engineering, 2009 Vol.4 No.4, pp.254 - 269
Published online: 08 Nov 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article