Discontinuous Galerkin methods on graphics processing units for nonlinear hyperbolic conservation laws

We present a novel implementation of the modal discontinuous Galerkin (DG) method for hyperbolic conservation laws in two dimensions on graphics processing units (GPUs) using NVIDIA's Compute Unified Device Architecture (CUDA). Both flexible and highly accurate, DG methods accommodate parallel architectures well as their discontinuous nature produces element-local approximations. High performance scientific computing suits GPUs well, as these powerful, massively parallel, cost-effective devices have recently included support for double-precision floating point numbers. Computed examples for Euler equations over unstructured triangle meshes demonstrate the effectiveness of our implementation on an NVIDIA GTX 580 device. Profiling of our method reveals performance comparable to an existing nodal DG-GPU implementation for linear problems.

[1]  George Em Karniadakis,et al.  The Development of Discontinuous Galerkin Methods , 2000 .

[2]  T. Koornwinder.  Two-Variable Analogues of the Classical Orthogonal Polynomials , 1975 .

[3]  Martin Siebenborn,et al.  A curved-element unstructured discontinuous Galerkin method on GPUs for the Euler equations , 2012, Comput. Vis. Sci..

[4]  Claus-Dieter Munz,et al.  Efficient Implementation of the CPR Formulation for the Navier-Stokes Equations on GPUs , 2012 .

[5]  Timothy C. Warburton,et al.  High-Order Discontinuous Galerkin Methods by GPU Metaprogramming , 2012, ArXiv.

[6]  Timothy C. Warburton,et al.  Solving Wave Equations on Unstructured Geometries , 2013, ArXiv.

[7]  Ben J. Zimmerman,et al.  The Efficient Implementation of Correction Procedure via Reconstruction with GPU Computing , 2013 .

[8]  Lilia Krivodonova,et al.  High-order accurate implementation of solid wall boundary conditions in curved geometries , 2006 .

[9]  Jacob Waltz.  Performance of a three‐dimensional unstructured mesh compressible flow solver on NVIDIA Fermi‐class graphics processing unit hardware , 2013 .

[10]  Markus Clemens,et al.  Scalability of Higher-Order Discontinuous Galerkin FEM Computations for Solving Electromagnetic Wave Propagation Problems on GPU Clusters , 2010, IEEE Transactions on Magnetics.

[11]  R Gandham,et al.  GPU Accelerated Discontinuous Galerkin Methods for Shallow Water Equations , 2014, 1403.1661.

[12]  Jostein R. Natvig,et al.  Solving the Euler Equations on Graphics Processing Units , 2006, International Conference on Computational Science.

[13]  Rainald Löhner,et al.  Running unstructured grid‐based CFD solvers on modern graphics hardware , 2009 .

[14]  M. Clemens,et al.  GPU accelerated Discontinuous Galerkin FEM for electromagnetic radio frequency problems , 2009, 2009 IEEE Antennas and Propagation Society International Symposium.

[15]  Graham Pullan,et al.  Acceleration of a two-dimensional Euler flow solver using commodity graphics hardware , 2007 .

[16]  Kyriakos C. Giannakoglou,et al.  Unsteady CFD computations using vertex‐centered finite volumes for unstructured grids on Graphics Processing Units , 2011 .

[17]  Timothy C. Warburton,et al.  A Low-Storage Curvilinear Discontinuous Galerkin Method for Wave Problems , 2013, SIAM J. Sci. Comput..

[18]  Jan S. Hesthaven,et al.  High-performance high-order simulation of wave and plasma phenomena , 2010 .

[19]  Timothy C. Warburton,et al.  Nodal discontinuous Galerkin methods on graphics processors , 2009, J. Comput. Phys..

[20]  M. F.,et al.  Bibliography , 1985, Experimental Gerontology.

[21]  D. A. Dunavant.  High degree efficient symmetrical Gaussian quadrature rules for the triangle , 1985 .

[22]  S. Rebay,et al.  High-Order Accurate Discontinuous Finite Element Solution of the 2D Euler Equations , 1997 .

[23]  Dimitri Komatitsch,et al.  Accelerating a three-dimensional finite-difference wave propagation code using GPU graphics cards , 2010 .

[24]  Graham Pullan,et al.  Acceleration of a 3D Euler solver using commodity graphics hardware , 2008 .

[25]  Martin Siebenborn,et al.  GPU accelerated discontinuous Galerkin methods for Euler equations and its adjoint , 2013, SpringSim.

[26]  Massimiliano Fatica,et al.  CUDA Fortran for Scientists and Engineers: Best Practices for Efficient CUDA Fortran Programming , 2013 .

[27]  Antony Jameson,et al.  On the Development of a High-Order, Multi-GPU Enabled, Compressible Viscous Flow Solver for Mixed Unstructured Grids , 2011 .

[28]  J. Hesthaven,et al.  Nodal Discontinuous Galerkin Methods: Algorithms, Analysis, and Applications , 2007 .

[29]  Jostein R. Natvig,et al.  Simulation and visualization of the Saint-Venant system using GPUs , 2010, Comput. Vis. Sci..

[30]  Timothy J. Barth,et al.  The design and application of upwind schemes on unstructured meshes , 1989 .

[31]  J. Peraire,et al.  Sub-Cell Shock Capturing for Discontinuous Galerkin Methods , 2006 .