Task-based parallelization of an implicit kinetic scheme

Jayesh Badwaik (1) , Matthieu Boileau (2, 3) , David Coulette (2, 3) , Emmanuel Franck (2, 3) , Philippe Helluy (2, 3) , Laura Mendoza (2, 3) , Herbert Oberlin (4)

1 Institut für Mathematik
2 IRMA - Institut de Recherche Mathématique Avancée
3 TONUS - TOkamaks and NUmerical Simulations
4 IPP - Max-Planck-Institut für Plasmaphysik [Garching]

In this paper we present and implement the Palindromic Discontinuous Galerkin (PDG) method in dimensions higher than one. The method has already been exposed and tested in [4] in the one-dimensional context. The PDG method is a general implicit high order method for approximating systems of conservation laws. It relies on a kinetic interpretation of the conservation laws containing stiff relaxation terms. The kinetic system is approximated with an asymptotic-preserving high order DG method. We describe the parallel implementation of the method, based on the StarPU runtime library. Then we apply it on preliminary test cases.

Mots clés: implicit; Discontinuous Galerkin; Lattice Boltzmann; high order; runtime system; parallelism. 1

Domaines: Equations aux dérivées partielles [math.AP]

Jayesh Badwaik, Matthieu Boileau, David Coulette, Emmanuel Franck, Philippe Helluy, et al.. Task-based parallelization of an implicit kinetic scheme. ESAIM: Proceedings and Surveys, 2018, 63, pp.60-77. ⟨10.1051/proc/201863060⟩. ⟨hal-01451393⟩