High-Order Discontinuous Galerkin Methods by GPU Metaprogramming

Discontinuous Galerkin (DG) methods for the numerical solution of par- tial differential equations have enjoyed considerable success because they are both flexible and robust: They allow arbitrary unstructured geometries and easy control of accuracy without compromising simulation stability. In a recent publication, we have shown that DG methods also adapt readily to execution on modern, massively parallel graphics processors (GPUs). A number of qualities of the method contribute to this suitability, reaching from locality of reference, through regularity of access patterns, to high arithmetic intensity. In this article, we illuminate a few of the more practical aspects of bringing DG onto a GPU, including the use of a Python-based metaprogramming infrastructure that was created specifically to support DG, but has found many uses across all disciplines of computational science.


Editor(s):
Wang, Jianfeng
Yuen, David
Johnsson, Lennart
Chi, Chi-Hung
Wang, Long
Shi, Yaolin
Chi, Xuebin
Ge, Wei
Published in:
GPU Solutions to Multi-scale Problems in Science and Engineering
Year:
2012
Publisher:
Springer Verlag
ISBN:
978-3-64216-404-0
Laboratories:




 Record created 2014-03-11, last modified 2018-03-17

Preprint:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)