Decomposição de Domínio Automática de Malhas do Método de Elementos Finitos no Hipercubo Intel iPSC/860
Resumo
Apresenta-se um algoritmo heurístico de decomposição de domínio automática de malhas do método de elementos finitos, dirigido para métodos diretos de solução esparsos. O presente algoritmo produz carga computacional equilibrada entre processadores de um arquitetura com memória distribuída, com reduzido custo de comunicação para transferência de mensagens. Resultados numéricos da decomposição de domínio são apresentados para demonstrar a precisão e eficiência do algoritmo no supercomputador hipercubo Intel iPSC/860.Referências
Al-Nasra, M. and Nguyen, D. T. (1991), "An algorithm for domain decomposition in finite element analysis", Computer & Srtuctures, Vol. 39, No. 3/4, pp. 277-289.
Ashcraft, C. (1987), "A vector implementation of the multifrontal method for large symmetric positive definite linear systems", Technical Report ETA-TR-51, Engineering Technology Applications Division, Boeing Computer Services, Seattle, Washington.
Farhat, C. (1988), "A simple and efficient automatic FEM domain decomposer", Computer & Structures, Vol. 28, No. 5, pp. 579-602.
Flower, J., Otto, S. and Salama, M. (1987), "Optimal mapping of irregular finite element domains to parallel processors", in Parallel Computations and Their Impact on Mechanics, presented at the Winter Annual Society of Mechanical Engineers, AMD, Vol. 86, pp. 239-250, Boston, Massachusetts.
Intel Corporation (1989), "i860 64-bit microprocessor programmer's reference manual", Intel Corporation, Santa Clara, California.
Intel Corporation (1991a), "iPSC/2 and iPSC/860 programmer's reference manual", Intel Corporation, Santa Clara, California.
Intel Corporation (1991b), "iPSC/2 and iPSC/860 user's guide", Intel Corporation, Santa Clara, California.
Intel Corporation (1992), "iPSC i860 Fortran compiler user's guide", Intel Corporation, Santa Clara, California.
Justino Filho, M. R. and Ebecken, N. F. F. (1992), "Ultimate strength analysis of offshore structures on the Intel iPSC/860 hypercube", International Conference on Parallel Computing and Transputers Applications, IOS Press/CIMNE, Barcelona, Part II, pp. 1089-1097.
Justino Filho, M. R. (1993),"Análise do colapso de estruturas offshore no supercomputador hpercubo Intel iPSC/860", Tese de Doutorado, Programa de Engenharia Civil, COPPE/UFRI, Rio de Janeiro, RJ, Maio.
Kirkpatrick, S., Gelatt Jr, C. D. and Vecchi, P. (1983), "Optimization by simulated annealing", Science, Vol. 220, No. 4598, pp. 671-680.
Malone, J. G. (1987), "Automated decomposition of finite element meshes for hypercube computers", In Parallel Processing for Scientific Computing, Proceedings of the Third SIAM Conference on Parallel Processing for Scientific Computing, Los Angeles, California.
Meaurant, G. (1992), "The evolution of scientific computing on paralled computers", I Escola de Computação Científica de Alto Desempenho, LNCC/CNPq, Rio de Janeiro, Março.
Ashcraft, C. (1987), "A vector implementation of the multifrontal method for large symmetric positive definite linear systems", Technical Report ETA-TR-51, Engineering Technology Applications Division, Boeing Computer Services, Seattle, Washington.
Farhat, C. (1988), "A simple and efficient automatic FEM domain decomposer", Computer & Structures, Vol. 28, No. 5, pp. 579-602.
Flower, J., Otto, S. and Salama, M. (1987), "Optimal mapping of irregular finite element domains to parallel processors", in Parallel Computations and Their Impact on Mechanics, presented at the Winter Annual Society of Mechanical Engineers, AMD, Vol. 86, pp. 239-250, Boston, Massachusetts.
Intel Corporation (1989), "i860 64-bit microprocessor programmer's reference manual", Intel Corporation, Santa Clara, California.
Intel Corporation (1991a), "iPSC/2 and iPSC/860 programmer's reference manual", Intel Corporation, Santa Clara, California.
Intel Corporation (1991b), "iPSC/2 and iPSC/860 user's guide", Intel Corporation, Santa Clara, California.
Intel Corporation (1992), "iPSC i860 Fortran compiler user's guide", Intel Corporation, Santa Clara, California.
Justino Filho, M. R. and Ebecken, N. F. F. (1992), "Ultimate strength analysis of offshore structures on the Intel iPSC/860 hypercube", International Conference on Parallel Computing and Transputers Applications, IOS Press/CIMNE, Barcelona, Part II, pp. 1089-1097.
Justino Filho, M. R. (1993),"Análise do colapso de estruturas offshore no supercomputador hpercubo Intel iPSC/860", Tese de Doutorado, Programa de Engenharia Civil, COPPE/UFRI, Rio de Janeiro, RJ, Maio.
Kirkpatrick, S., Gelatt Jr, C. D. and Vecchi, P. (1983), "Optimization by simulated annealing", Science, Vol. 220, No. 4598, pp. 671-680.
Malone, J. G. (1987), "Automated decomposition of finite element meshes for hypercube computers", In Parallel Processing for Scientific Computing, Proceedings of the Third SIAM Conference on Parallel Processing for Scientific Computing, Los Angeles, California.
Meaurant, G. (1992), "The evolution of scientific computing on paralled computers", I Escola de Computação Científica de Alto Desempenho, LNCC/CNPq, Rio de Janeiro, Março.
Publicado
07/09/1993
Como Citar
JUSTINO FILHO, Manoel Rodrigues; EBECKEN, Nelson Francisco Favilla.
Decomposição de Domínio Automática de Malhas do Método de Elementos Finitos no Hipercubo Intel iPSC/860. In: INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD), 5. , 1993, Florianópolis/SC.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
1993
.
p. 432-443.
DOI: https://doi.org/10.5753/sbac-pad.1993.23050.
