Scaling Up Multiphysics

Abstract

The present paper summarizes trends in supercomputing and the consequences they will have on coupled problems in computational mechanics. The appearance of parallel machines with more than Failed to parse (MathML with SVG or PNG fallback (recommended for modern browsers and accessibility tools): Invalid response ("Math extension cannot connect to Restbase.") from server "https://mathoid.scipedia.com/localhost/v1/":): 10^6

cores implies that the prevalent ‘scalar-pre, simple parallel solve, scalar-post’ environment will have to give way to a completely scalable simulation pipeline. The grid size alone will force distributed parallelization of meshing, domain splitting, load balancing and post-processing. Possible ways of addressing parallel meshing and dynamic load balancing for multiphysics are treated, and examples shown.