Abstract
Parallel iterative linear solvers for unstructured grids in FEM applications, originally developed for the Earth Simulator (ES), are ported to various types of parallel computer. The performance of flat MPI and hybrid parallel programming models is compared for the ES, Hitachi SR8000, IBM SP-3 and IBM p5-model 595 supercomputers. The effect of coloring and of different storage methods for coefficient matrices are evaluated in various types of application. Performance for more than 104 processors is estimated using measured data for up to 103 processors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Earth Simulator Center: http://www.es.jamstec.go.jp/
Rabenseifner, R.: Communication Bandwidth of Parallel Programming Models on Hybrid Architectures. In: Zima, H.P., et al. (eds.) ISHPC 2002. LNCS, vol. 2327, pp. 437–448. Springer, Heidelberg (2002)
Nakajima, K.: Parallel Iterative Solvers of GeoFEM with Selective Blocking Preconditioning for Nonlinear Contact Problems on the Earth Simulator. In: ACM/IEEE Proceedings of SC2003, ACM, New York (2003)
Nakajima, K.: Preconditioned Iterative Linear Solvers for Unstructured Grids on the Earth Simulator. In: IEEE Proceedings of HPC Asia 2004, pp. 150–169. IEEE, Los Alamitos (2004)
GeoFEM: http://geofem.tokyo.rist.or.jp/
Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. SIAM, Philadelphia (2003)
Doi, S., Washio, T.: Using Multicolor Ordering with Many Colors to Strike a Better Balance between Parallelism and Convergence. In: Proceedings of RIKEN Symposium on Linear Algebra and its Applications, pp. 19–26 (1999)
Kerbyson, D.J., Hoisie, A., Wasserman, H.: A Comparison Between the Earth Simulator and AlphaServer Systems using Predictive Application Performance Models. LA-UR-02-5222, Los Alamos National Laboratory (2002)
Information Technology Center, The University of Tokyo: http://www.cc.u-tokyo.ac.jp/
National Energy Research Scientific Computing Center, Lawrence Berkeley National Laboratory: http://www.nersc.gov/
Computing and Communication Center, Kyushu University: http://www.cc.kyushu-u.ac.jp/
Adams, M.F., et al.: Applications of Algebraic Multigrid to Large-Scale Finite Element Analysis of Whole Bone Micro-Mechanics on the IBM SP. In: ACM/IEEE Proceedings of SC2003, ACM, New York (2003)
Oliker, L., et al.: Scientific Computations on Modern Parallel Vector Systems. In: ACM/IEEE Proceedings of SC2004, ACM, New York (2004)
Uehara, H., et al.: MPI Performance Evaluation on the Earth Simulator (in Japanese). IPSJ Transactions on High-Performance Computing System, 44 SIG 1 (HPS 6), 24-34 (2003)
HLRS (High Performance Computing Center Stuttgart): http://www.hlrs.de/
Nakajima, K., Okuda, H.: Parallel Iterative Solvers with Selective Blocking Preconditioning for Simulations of Fault Zone Contact. Journal of Numerical Algebra with Applications 11, 831–852 (2004)
Hatazaki, T.: Lessons from porting vector computer applications onto Non-Uniform Memory Access scalar machines. In: IEEE Proceedings of HPC Asia 2004, pp. 236–243. IEEE, Los Alamitos (2004)
STREAM (Sustainable Memory Bandwidth in High Performance Computers): http://www.cs.virginia.edu/stream/
Nakajima, K.: Three-Level Hybrid vs. Flat MPI on the Earth Simulator: Parallel Iterative Solvers for Finite-Element Method. Applied Numerical Mathematics 54, 237–255 (2005)
Nakajima, K.: Parallel programming models for finite-element method using preconditioned iterative solvers with multicolor ordering on various types of SMP cluster supercomputers. In: IEEE Proceedings of HPC Asia 2005, pp. 83–90. IEEE, Los Alamitos (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Nakajima, K. (2007). The Impact of Parallel Programming Models on the Performance of Iterative Linear Solvers for Finite Element Applications. In: Daydé, M., Palma, J.M.L.M., Coutinho, Á.L.G.A., Pacitti, E., Lopes, J.C. (eds) High Performance Computing for Computational Science - VECPAR 2006. VECPAR 2006. Lecture Notes in Computer Science, vol 4395. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71351-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-71351-7_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-71350-0
Online ISBN: 978-3-540-71351-7
eBook Packages: Computer ScienceComputer Science (R0)