Abstract
As introduction, high-performance computing (HPC) technology for finite element analysis is explained. First, general notions, tips and techniques which are useful for the programming on modern HPC and supercomputing environments are introduced. Here, as a supercomputer, the authors assume mainly a distributed memory parallel computer with each computational node having one or more multi-core scalar processors. Both hardware and software aspects are covered, with important concepts such as MPI, OpenMP and other compiler directives, as well as network interconnect, cache, memory bandwidth, SIMD and peak performance ratio. There are also some tips and advices about the software development process specific for the supercomputers, such as software design, testing and debugging, and profiling. Then, some important ideas and techniques for the development of FE-based simulation code running on supercomputers, such as the selection of linear algebraic solvers, domain decomposition method (DDM), element-by-element (EBE), as well as mesh generation and visualization are explained. This~chapter could also serve as the introduction of HPC and supercomputing to the following chapters dealing with more specific problems and schemes.
11th World Congress on Computational Mechanics (WCCM XI)
5th European Conference on Computational Mechanics (ECCM V)
6th European Conference on Computational Fluid Dynamics (ECFD VI)
20–25 July 2014, Barcelona, Spain
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dongarra, J.J., et al.: Numerical Linear Algebra for High-Performance Computers. SIAM, Philadelphia (1998)
Saad, Y.: Iterative Methods for Sparse Linear Systems. SIAM, Philadelphia (2003)
Smith, B., et al.: Domain Decomposition: Parallel Multilevel Methods for Elliptical Partial Differential Equations. Cambridge University Press, Cambridge (2004)
Bhardwaj, M., et al.: Salinas: A scalable software for high-performance structural and solid mechanics simulations. In: Proceedings of SC02 (2002)
Ogino, M., Shioya, R., Kawai, H., Yoshimura, S.: Seismic response analysis of full scale nuclear vessel model with ADVENTURE system on the earth simulator. J. Earth Simul. 2, 41–54 (2005)
Murotani, K., Sugimoto, S., Kawai, H., Yoshimura, S.: Hierarchical domain decomposition with parallel mesh refinement for billions-of-DOF-scale finite element analyses. Int. J. Comput. Methods (2013). doi:10.1142/S0219876213500618
Kawai, H., Ogino, M., Shioya, R., Yoshimura, S.: Vectorization of polygon rendering for off-line visualization of a large scale structural analysis with ADVENTURE system on the earth simulator. J. Earth Simul. 9, 51–63 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Kawai, H., Ogino, M., Shioya, R., Yoshimura, S. (2016). Fundamentals of High-Performance Computing for Finite Element Analysis. In: Yoshimura, S., Hori, M., Ohsaki, M. (eds) High-Performance Computing for Structural Mechanics and Earthquake/Tsunami Engineering. Springer Tracts in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-319-21048-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-21048-3_1
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-21047-6
Online ISBN: 978-3-319-21048-3
eBook Packages: EngineeringEngineering (R0)