Abstract
Parallelization promises to allow increasing performance demand from users of scientific computation codes. In this article we discuss implementation of parallelization techniques in industrial computation codes for applications in Fluid Mechanics (N3S) and Structural Mechanics (Code_ASTER). We outline the gains afforded by parallelization on a Cray C98 machine in production mode, using a single version of the program running in sequential or in parallel mode, with minimum modifications to the initial code. Parallelization is applied at the discretion of the user, for whom no specialist knowledge of this technique is assumed.
Similar content being viewed by others
References
P. Amestoy and I. Duff, Memory managementissues in sparse multifrontal methods on multiprocessors, Internat. J. Supercomputer Appl. 7(1) (1993) 64–82.
J.P. Chabard, B. Metivet, G. Pot and B. Thomas, An efficient finite element method for the computation of 3D turbulent incompressible flows, in: Finite Elements in Fluids, Vol. 8 (1992).
CodeASTER, Présentation du code analyse des structures et thermo-mécanique pour des études et des recherches, Brochure, version 3.
I. Duff, Parallel implementation of a multifrontalscheme, Parallel Comput. 3 (1986) 193–201.
J.P. Gregoire, B. Nitrosso, Y. Souffez and G. Roth, Speed-up of parallelized N3S code on Cray C98 in production mode, in: '95, Venice, Italy (1995).
J.P. Gregoire and G. Pot, Speedup of CFD codes using analytical finite-element calculations, in: Proceedings of 14th Int. Conf. on Numerical Methods for Fluid Dynamics, Bangalore, India (July 1994).
C. Rose, Implémentation de laméthode multifrontale dans le code ASTER, in: Workshop on Sparse Matrix Processing, INPG, Grenoble (December 13-14, 1995).
Y. Souffez, Parallelization of the method ofcharacteristics on a Cray YMP, ERCOFTAC Bulletin 7 (1992) 15–18.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Gregoire, J., Rose, C. & Thomas, B. Direct and iterative solvers for finite-element problems. Numerical Algorithms 16, 39–53 (1997). https://doi.org/10.1023/A:1019174710859
Issue Date:
DOI: https://doi.org/10.1023/A:1019174710859