Abstract
We investigate opportunities for parallel execution on PowerXCell 8i processors of numerical integration algorithm as it is used in finite element codes. Different kinds of problems and different types of finite element approximations are taken into account. We design and implement several parallelization strategies and test their performance for different situations. The results of analyses and tests can be used as a guideline for choosing the proper parallelization strategy for different problems and finite element discretizations.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Solin, P., Segeth, K., Dolezel, I.: Higher-Order Finite Element Methods. Chapman & Hall/CRC (2003)
Ciarlet, P.: The Finite Element Method for Elliptic Problems. North-Holland, Amsterdam (1978)
Banaś, K.: A model for parallel adaptive finite element software. In: Kornhuber, R., Hoppe, R., Périaux, J., Pironneau, O., Widlund, O., Xu, J. (eds.) Domain Decomposition Methods in Science and Engineering. Lecture Notes in Computational Science and Engineering, vol. 40, pp. 159–166. Springer, Heidelberg (2004)
Cell Broadband Engine Programming Handbook Including the PowerXCell 8i Processor. IBM (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Krużel, F., Banaś, K. (2010). Finite Element Numerical Integration on PowerXCell Processors. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds) Parallel Processing and Applied Mathematics. PPAM 2009. Lecture Notes in Computer Science, vol 6067. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14390-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-642-14390-8_54
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14389-2
Online ISBN: 978-3-642-14390-8
eBook Packages: Computer ScienceComputer Science (R0)