Co-processor acceleration of an unmodified parallel solid mechanics code with FEASTGPU
Institute of Applied Mathematics, TU Dortmund, Dortmund, Germany
Int. J. Computational Science and Engineering, Vol. 4, No. 4, 2009
@article{GoWoSt_09FEASTSolid,
author={Dominik G{“o}ddeke and Hilmar Wobker and Robert Strzodka and Jamaludin Mohd-Yusof and Patrick McCormick and Stefan Turek},
title={Co-Processor Acceleration of an Unmodified Parallel Solid Mechanics Code with {FEASTGPU}},
journal={International Journal of Computational Science and Engineering (IJCSE)},
year={2009},
month={nov},
volume={4},
pages={254–269},
number={4},
publisher={Inderscience}
}
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.
March 1, 2011 by hgpu
