Performance comparison of various parallel incomplete LU factorization preconditioners for domain decomposition method
- 12 Downloads
A finite element code is parallelized by vertex-oriented domain decomposition method which utilizes one- or multi-dimensional partitioning in structured mesh and METIS Library in unstructured mesh. For obtaining the domain-decomposed solution, iterative solvers like conjugate gradient method are used. To accelerate the convergence of iterative solvers, parallel incomplete LU factorization preconditioners are employed, and their performances are compared. For the communication between processors, Message Passing Interface Library is used. The speedups of parallel preconditioned iterative solvers are estimated through computing 2- and 3-dimensional Laplace equations. The effects of mesh and partitioning method on the speedup of parallel preconditioners are also examined.
KeywordsFinite element method Domain decomposition method Preconditioned conjugate gradient Parallel ILU preconditioner
Unable to display preview. Download preview PDF.
- M. Snir, S. W. Otto, S. Huss–Lederman, D. Walker and J. Dongarra, MPI: The complete reference, The MIT Press: London, England (1996).Google Scholar
- http://www–users.cs.umn.edu/~karypis/metis.Google Scholar
- K. A. Hoffmann and S. T. Chiang, Computational fluid dynamics for engineers, A Publication of Engineering Education System: Wichita, Kansas, USA, 1 (1993).Google Scholar