A new parallel sparse direct solver : presentation and numerical experiments in large-scale structural mechanics parallel computing - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal for Numerical Methods in Engineering Année : 2011

A new parallel sparse direct solver : presentation and numerical experiments in large-scale structural mechanics parallel computing

Résumé

The main purpose of this work is to present a new parallel direct solver : Dissection solver. It is based on a LU factorization of the sparse matrix of the linear system and allows to detect automatically and handle properly the zero-energy modes which is important when dealing with DDM. A performance evaluation and comparisons with other direct solvers (MUMPS, DSCPACK), are also given for both sequential and parallel computations. Results of numerical experiments with a two-levels parallelization of large-scale structural analysis problems are also presented : FETI is used for the global problem parallelization and Dissection for the local multithreading. In this framework, the largest problem we have solved is of an elastic solid composed of 400 subdomains running on 400 computation nodes (3200 cores) and containing about 165 millions dof. The computation of one single iteration consumes less than 20 minutes of CPU time. Several comparisons to MUMPS are given for the numerical computaion of large-scale linear systems on a massively parallel cluster : performances and weaknesses of this new solver are highlighted.

Dates et versions

hal-00598056 , version 1 (03-06-2011)

Identifiants

Citer

Ibrahima Gueye, Saber El Arem, Frédéric Feyel, François-Xavier Roux, Georges Cailletaud. A new parallel sparse direct solver : presentation and numerical experiments in large-scale structural mechanics parallel computing. International Journal for Numerical Methods in Engineering, 2011, 88, pp.370-384. ⟨10.1002/nme.3179⟩. ⟨hal-00598056⟩
152 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More