Scalable large-scale fluid–structure interaction solvers in the Uintah framework via hybrid task-based parallelism algorithms

摘要

Uintah is a software framework that provides an environment for solving fluid–structure interaction problemsrnon structured adaptive grids for large-scale science and engineering problems involving the solution of partialrndifferential equations. Uintah uses a combination of fluid flow solvers and particle-based methods for solids,rntogether with adaptive meshing and a novel asynchronous task-based approach with fully automated loadrnbalancing. When applying Uintah to fluid–structure interaction problems, the combination of adaptive meshingrnand the movement of structures through space present a formidable challenge in terms of achievingrnscalability on large-scale parallel computers. The Uintah approach to the growth of the number of corerncounts per socket together with the prospect of less memory per core is to adopt a model that uses MPI torncommunicate between nodes and a shared memory model on-node so as to achieve scalability on large-scalernsystems. For this approach to be successful, it is necessary to design data structures that large numbers ofrncores can simultaneously access without contention. This scalability challenge is addressed here for Uintah,rnby the development of new hybrid runtime and scheduling algorithms combined with novel lock-free datarnstructures, making it possible for Uintah to achieve excellent scalability for a challenging fluid–structurernproblem with mesh refinement on as many as 260K cores. Copyright © 2013 John Wiley & Sons, Ltd.