Abstract
Recently, graphics processing units (GPUs) have had great success in accelerating many numerical computations. We present their application to computations on unstructured meshes such as those in finite element methods. Multiple approaches in assembling and solving sparse linear systems with NVIDIA GPUs and the Compute Unified Device Architecture (CUDA) are created and analyzed. Multiple strategies for efficient use of global, shared, and local memory, methods to achieve memory coalescing, and optimal choice of parameters are introduced. We find that with appropriate preprocessing and arrangement of support data, the GPU coprocessor using single-precision arithmetic achieves speedups of 30 or more in comparison to a well optimized double-precision single core implementation. We also find that the optimal assembly strategy depends on the order of polynomials used in the finite element discretization. © 2010 John Wiley & Sons, Ltd.
Original language | English (US) |
---|---|
Pages (from-to) | 640-669 |
Number of pages | 30 |
Journal | International Journal for Numerical Methods in Engineering |
Volume | 85 |
Issue number | 5 |
DOIs | |
State | Published - Aug 23 2010 |
Externally published | Yes |
Bibliographical note
KAUST Repository Item: Exported on 2020-10-01Acknowledgements: This work was partially supported by a research grant from the Academic Excellence Alliance program between King Abdullah University of Science and Technology (KAUST) and the Stanford University.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.