A High-Performance Implementation of a Robust Preconditioner for Heterogeneous Problems

We present an efficient implementation of the highly robust and scalable GenEO preconditioner in the high-performance PDE framework DUNE. The GenEO coarse space is constructed by combining low energy solutions of a local generalised eigenproblem using a partition of unity. In this paper we demonstrate both weak and strong scaling for the GenEO solver on over 15,000 cores by solving an industrially motivated problem with over 200 million degrees of freedom. Further, we show that for highly complex parameter distributions arising in certain real-world applications, established methods become intractable while GenEO remains fully effective. The purpose of this paper is two-fold: to demonstrate the robustness and high parallel efficiency of the solver and to document the technical details that are crucial to the efficiency of the code.

[1]  Frédéric Nataf,et al.  Spillane, N. and Dolean Maini, Victorita and Hauret, P. and Nataf, F. and Pechstein, C. and Scheichl, R. (2013) Abstract robust coarse spaces for systems of PDEs via generalized eigenproblems in the overlaps , 2018 .

[2]  I. Babuska,et al.  Special finite element methods for a class of second order elliptic problems with rough coefficients , 1994 .

[3]  Chao Yang,et al.  ARPACK users' guide - solution of large-scale eigenvalue problems with implicitly restarted Arnoldi methods , 1998, Software, environments, tools.

[4]  Robert Scheichl,et al.  High-performance dune modules for solving large-scale, strongly anisotropic elliptic problems with applications to aerospace composites , 2020, Comput. Phys. Commun..

[5]  Timothy Dodwell,et al.  A Bayesian framework for assessing the strength distribution of composite structures with random defects , 2018 .

[6]  Yalchin Efendiev,et al.  Generalized multiscale finite element methods for space-time heterogeneous parabolic equations , 2016, Comput. Math. Appl..

[7]  Andrea Toselli,et al.  Domain decomposition methods : algorithms and theory , 2005 .

[8]  Richard Butler,et al.  dune-composites – A New Framework for High-Performance Finite Element Modelling of Laminates , 2017, 1707.04228.

[9]  David Wells,et al.  The deal.II library, Version 9.0 , 2018, J. Num. Math..

[10]  Andreas Dedner,et al.  A generic grid interface for parallel and adaptive scientific computing. Part I: abstract framework , 2008, Computing.

[11]  Anders Logg,et al.  The FEniCS Project Version 1.5 , 2015 .

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

[13]  Andreas Dedner,et al.  A generic grid interface for parallel and adaptive scientific computing. Part II: implementation and tests in DUNE , 2008, Computing.

[14]  Peter Bastian,et al.  On the generic parallelisation of iterative solvers for the finite element method , 2008, Int. J. Comput. Sci. Eng..

[15]  Robert Scheichl,et al.  A robust two-level domain decomposition preconditioner for systems of PDEs , 2011 .

[16]  V. E. Henson,et al.  BoomerAMG: a parallel algebraic multigrid solver and preconditioner , 2002 .

[17]  Peter Bastian,et al.  Generic implementation of finite element methods in the Distributed and Unified Numerics Environment (DUNE) , 2010, Kybernetika.

[18]  Frédéric Nataf,et al.  Scalable domain decomposition preconditioners for heterogeneous elliptic problems , 2013, 2013 SC - International Conference for High Performance Computing, Networking, Storage and Analysis (SC).