FEAST—realization of hardware-oriented numerics for HPC simulations with finite elements

FEAST (Finite Element Analysis and Solutions Tools) is a Finite Element-based solver toolkit for the simulation of PDE problems on parallel HPC systems, which implements the concept of ‘hardware-oriented numerics’, a holistic approach aiming at optimal performance for modern numerics. In this paper, we describe this concept and the modular design that enables applications built on top of FEAST to execute efficiently, without any code modifications, on commodity-based clusters, the NEC SX 8 and GPU-accelerated clusters. We demonstrate good performance and weak and strong scalability for the prototypical Poisson problem and more challenging applications from solid mechanics and fluid dynamics. Copyright © 2010 John Wiley & Sons, Ltd.

[1]  Samuel Williams,et al.  Optimization of sparse matrix-vector multiplication on emerging multicore platforms , 2009, Parallel Comput..

[2]  Dominik Göddeke,et al.  Fast and accurate finite-element multigrid solvers for PDE simulations on GPU clusters , 2011 .

[3]  Julien Langou,et al.  The Impact of Multicore on Math Software , 2006, PARA.

[4]  D. Braess.  Finite Elements: Theory, Fast Solvers, and Applications in Solid Mechanics , 1995 .

[5]  Robert Strzodka,et al.  Exploring weak scalability for FEM calculations on a GPU-enhanced cluster , 2007, Parallel Comput..

[6]  Timothy A. Davis,et al.  A column pre-ordering strategy for the unsymmetric-pattern multifrontal method , 2004, TOMS.

[7]  Hilmar Wobker,et al.  Efficient multilevel solvers and high performance computing techniques for the finite element simulation of large-scale elasticity problems , 2010 .

[8]  Owe Axelsson,et al.  On iterative solvers in structural mechanics; separate displacement orderings and mixed variable methods , 1999 .

[9]  T. Hughes,et al.  A new finite element formulation for computational fluid dynamics: V. Circumventing the Babuscka-Brezzi condition: A stable Petrov-Galerkin formulation of , 1986 .

[10]  T. Hughes,et al.  Streamline upwind/Petrov-Galerkin formulations for convection dominated flows with particular emphasis on the incompressible Navier-Stokes equations , 1990 .

[11]  Barry F. Smith,et al.  Domain Decomposition: Parallel Multilevel Methods for Elliptic Partial Differential Equations , 1996 .

[12]  Stefan Turek,et al.  Efficient Solvers for Incompressible Flow Problems - An Algorithmic and Computational Approach , 1999, Lecture Notes in Computational Science and Engineering.

[13]  Ulrich Rüde,et al.  Is 1.7 x 10^10 Unknowns the Largest Finite Element System that Can Be Solved Today? , 2005, ACM/IEEE SC 2005 Conference (SC'05).

[14]  Christian Becker,et al.  Hardware-oriented numerics and concepts for PDE software , 2006, Future Gener. Comput. Syst..

[15]  Robert Strzodka,et al.  Co-processor acceleration of an unmodified parallel solid mechanics code with FEASTGPU , 2009, Int. J. Comput. Sci. Eng..

[16]  Ulrich Rüde,et al.  Fixed and Adaptive Cache Aware Algorithms for Multigrid Methods , 2000 .

[17]  Ulrich Rüde,et al.  Cache Optimization for Structured and Unstructured Grid Multigrid , 2000 .

[18]  Robert Strzodka,et al.  Using GPUs to improve multigrid solver performance on a cluster , 2008, Int. J. Comput. Sci. Eng..

[19]  P. Hanrahan,et al.  Sequoia: Programming the Memory Hierarchy , 2006, ACM/IEEE SC 2006 Conference (SC'06).

[20]  Gene H. Golub,et al.  A Note on Preconditioning for Indefinite Linear Systems , 1999, SIAM J. Sci. Comput..