A GPU-based Multi-level Algorithm for Boundary Value Problems

A novel and scalable geometric multi-level algorithm is presented for the numerical solution of elliptic partial differential equations, specially designed to run with high occupancy of streaming processors inside Graphics Processing Units(GPUs). The algorithm consists of iterative, superposed operations on a single grid, and it is composed of two simple full-grid routines: a restriction and a coarsened interpolation-relaxation. The restriction is used to collect sources using recursive coarsened averages, and the interpolation-relaxation simultaneously applies coarsened finite-difference operators and interpolations. The routines are scheduled in a saw-like refining cycle. Convergence to machine precision is achieved repeating the full cycle using accumulated residuals and successively collecting the solution. Its total number of operations scale linearly with the number of nodes. It provides an attractive fast solver for Boundary Value Problems (BVPs), specially for simulations running entirely in the GPU. Applications shown in this work include the deformation of two-dimensional grids, the computation of three-dimensional streamlines for a singular trifoil-knot vortex and the calculation of three-dimensional electric potentials in heterogeneous dielectric media.

[1]  Giovanni Russo,et al.  Finite-difference ghost-point multigrid methods on Cartesian grids for elliptic problems in arbitrary domains , 2013, J. Comput. Phys..

[2]  Michael Kazhdan,et al.  Streaming multigrid for gradient-domain operations on large images , 2008, SIGGRAPH 2008.

[3]  Leo Grady,et al.  A Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations Used in Image Analysis , 2008, ECCV.

[4]  William L. Briggs,et al.  A multigrid tutorial , 1987 .

[5]  Peter Thoman,et al.  GPU-Based Multigrid: Real-Time Performance in High Resolution Nonlinear Image Processing , 2008, ICVS.

[6]  Samuel Williams,et al.  Roofline: an insightful visual performance model for multicore architectures , 2009, CACM.

[7]  Gallagher Pryor,et al.  3D nonrigid registration via optimal mass transport on the GPU , 2009, Medical Image Anal..

[8]  B. Oskam,et al.  General relaxation schemes in multigrid algorithms for higher order singularity methods , 1981 .

[9]  Yingjun Jiang,et al.  Multigrid methods for space fractional partial differential equations , 2015, J. Comput. Phys..

[10]  Stefan Turek,et al.  Numerical analysis and implementational aspects of a new multilevel grid deformation method , 2010 .

[11]  Wolfgang Hackbusch,et al.  Multi-grid methods and applications , 1985, Springer series in computational mathematics.

[12]  R. Yates,et al.  General theory of domain decomposition: Beyond Schwarz methods , 2001 .

[13]  Zhilin Li,et al.  The Immersed Interface/Multigrid Methods for Interface Problems , 2002, SIAM J. Sci. Comput..

[14]  Manfred Liebmann,et al.  A Parallel Algebraic Multigrid Solver on Graphics Processing Units , 2009, HPCA.

[15]  Robert Strzodka,et al.  Cyclic Reduction Tridiagonal Solvers on GPUs Applied to Mixed-Precision Multigrid , 2011, IEEE Transactions on Parallel and Distributed Systems.

[16]  Eric Darve,et al.  Large calculation of the flow over a hypersonic vehicle using a GPU , 2008, J. Comput. Phys..

[17]  Robert Strzodka,et al.  AmgX: A Library for GPU Accelerated Algebraic Multigrid and Preconditioned Iterative Methods , 2015, SIAM J. Sci. Comput..

[18]  Stéphane Popinet,et al.  A quadtree-adaptive multigrid solver for the Serre-Green-Naghdi equations , 2015, J. Comput. Phys..

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

[20]  Francisco Mandujano,et al.  Moments Preserving and high-resolution Semi-Lagrangian Advection Scheme , 2014, SIAM J. Sci. Comput..

[21]  Thomas Sangild Sørensen,et al.  An Introduction to GPU Accelerated Surgical Simulation , 2006, ISBMS.

[22]  Yau Shu Wong,et al.  Spectral multigrid methods for elliptic equations II , 1982 .

[23]  Matemática,et al.  Society for Industrial and Applied Mathematics , 2010 .

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

[25]  Peng Li,et al.  Multigrid on GPU: tackling power grid analysis on parallel SIMT platforms , 2008, ICCAD 2008.

[26]  Zbigniew J. Czech,et al.  Introduction to Parallel Computing , 2017 .

[27]  Greg Humphreys,et al.  A multigrid solver for boundary value problems using programmable graphics hardware , 2003, HWWS '03.

[28]  J. Dendy.  Black box multigrid , 1982 .

[29]  Martin Rumpf,et al.  Image Registration by a Regularized Gradient Flow. A Streaming Implementation in DX9 Graphics Hardware , 2004, Computing.

[30]  Hamilton-Jacobi Equations,et al.  Multigrid Methods for , 2011 .