• Citer

On the performance of a parallel direct solver used within a hybrid spectral/finite element solver for incompressible flows

par Dechamps, Xavier ;Rasquin, Michel ;Degrez, Gérard
Référence (September 10-14 2012: Vienna (Austria)), 6th European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2012)
Publication Publié, 2012-09-10

Publication dans des actes

• Accès en ligne
• Détails
• Contenu
• Statistiques

Résumé :

The development of parallel direct solvers enabled many CFD codes to apply on finer and finer meshes. Since a decade, our department has expanded the capacities of an in-house hybrid spectral / finite element solver for 3D unsteady incompressible flow problems with a direction of periodicity. The use of a spectral development along the direction of periodicity leads to a set of 2D decoupled systems of equations within each time step to determine the modal components of the nodal unknowns. The parallelization within the code is made both in physical and spectral domains, trying to keep as few communications between the processors as possible. We chose to couple the parallel direct solver MUMPS to our CFD code in order to solve each mode by several processors. Doing so, we can now perform computations on meshes containing tens of millions of nodes, which is now a standard in the CFD community. We first present the nature of the parallelization made in our code. Then, on the basis of a magnetohydrodynamic flow encountered in axisymmetric geometries, we compare the time and memory requirements between our former direct solver and the new one.