OpenCL-based implementation of an unstructured edge-based finite element convection-diffusion solver on graphics hardware

• Published in: International journal for numerical methods in engineering Vol. 89; no. 13; pp. 1635 - 1651
• Main Authors: Mossaiby, F., Rossi, R., Dadvand, P., Idelsohn, S.
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Ltd 30.03.2012; Wiley
• Subjects: Applied sciences; Computational methods in fluid dynamics; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Convection and heat transfer; convection diffusion; edge-based; Exact sciences and technology; Fluid dynamics; Fundamental areas of phenomenology (including applications); GPU; OpenCL; OpenMP; Physics; Software; Turbulent flows, convection, and heat transfer; unstructured grids; Similarity; Smoothed particle hydrodynamics method; Convection diffusion equation; Non conservative system; Parallel algorithms; Distributed computing; GPU; Convection; Finite volume methods; Multiprocessor; Finite element method; Discretization; Graphic processing unit; unstructured grids; Modelling; Regularity; convection diffusion; Mesh generation; Fluid mechanics; edge-based; Computational fluid dynamics; Hydrodynamic method; OpenMP; Data structures; Particle method; Meshless method; OpenCL; Edge detection; Lattice Boltzmann model; Heat transfer; Finite difference method
• ISSN: 0029-5981; 1097-0207
• DOI: 10.1002/nme.3302

SUMMARY The solution of problems in computational fluid dynamics (CFD) represents a classical field for the application of advanced numerical methods. Many different approaches were developed over the years to address CFD applications. Good examples are finite volumes, finite differences (FD), and finite elements (FE) but also newer approaches such as the lattice‐Boltzmann (LB), smooth particle hydrodynamics or the particle finite element method. FD and LB methods on regular grids are known to be superior in terms of raw computing speed, but using such regular discretization represents an important limitation in dealing with complex geometries. Here, we concentrate on unstructured approaches which are less common in the GPU world. We employ a nonstandard FE approach which leverages an optimized edge‐based data structure allowing a highly parallel implementation. Such technique is applied to the ‘convection‐diffusion’ problem, which is often considered as a first step towards CFD because of similarities to the nonconservative form of the Navier–Stokes equations. In this regard, an existing highly optimized parallel OpenMP solver is ported to graphics hardware based on the OpenCL platform. The optimizations performed are discussed in detail. A number of benchmarks prove that the GPU‐accelerated OpenCL code consistently outperforms the OpenMP version. Copyright © 2011 John Wiley & Sons, Ltd.