zbMATH — the first resource for mathematics

Aerospace simulations on parallel computers using unstructured grids. (English) Zbl 1021.76030
Summary: If complex simulations on realistic configurations are to be performed, it is critical that the large volume of data that will be produced can be handled efficiently. In our work, we have chosen to parallelize all the steps in the computational cycle: unstructured mesh generation, solvers, adaptation and visualization. In this way, data is distributed at the early stage of mesh generation and is never brought together, thereby preventing data bottlenecks. Using these parallel modules, large-scale simulations have been performed for both computational fluid dynamics and computational electromagnetics. The paper briefly describes the approaches taken to parallelizing the unstructured grid techniques, and examples are given using meshes to a quarter of a billion elements.

76M10 Finite element methods applied to problems in fluid mechanics
78M10 Finite element, Galerkin and related methods applied to problems in optics and electromagnetic theory
65Y05 Parallel numerical computation
Full Text: DOI
[1] Morgan, Computer Methods in Applied Mechanics and Engineering 152 pp 157– (1998)
[2] Said, Computer Methods in Applied Mechanics and Engineering 177 pp 109– (1999)
[3] Morgan, International Journal for Numerical Methods in Fluids 31 pp 159– (1999)
[4] Manzari, Finite Elements in Analysis and Design 30 pp 353– (1998)
[5] Weatherill, Engineering Computations 16 pp 913– (1999)
[6] Weatherill, International Journal for Numerical Methods in Engineering 37 pp 2005– (1994)
[7] Morgan, Computational Methods in Applied Mechanics and Engineering 87 pp 335– (1991)
[8] Using MPI: Portable Parallel Programming with Message Passing Interface. MIT Press: Cambridge, MA, 1994.
[9] PVM3 User’s Guide and Reference Manual. Oak Ridge National Laboratory: Oak Ridge, TN, 1994.
[10] An optimal dynamic load balancing algorithm. PrePrint DL-P-95-011, Daresbury Laboratory, 1995.
[11] Jones, Applied Mathematical Modelling
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.