Methods for compressible fluid simulation on GPUs using high-order finite differences

Show full item record



Permalink

http://hdl.handle.net/10138/308145

Citation

Pekkila , J , Vaisala , M S , Käpylä , M J , Käpylä , P J & Anjum , O 2017 , ' Methods for compressible fluid simulation on GPUs using high-order finite differences ' , Computer Physics Communications , vol. 217 , pp. 11-22 . https://doi.org/10.1016/j.cpc.2017.03.011

Title: Methods for compressible fluid simulation on GPUs using high-order finite differences
Author: Pekkila, Johannes; Vaisala, Miikka S.; Käpylä, Maarit J.; Käpylä, Petri J.; Anjum, Omer
Contributor: University of Helsinki, Department of Physics
Date: 2017-08
Language: eng
Number of pages: 12
Belongs to series: Computer Physics Communications
ISSN: 0010-4655
URI: http://hdl.handle.net/10138/308145
Abstract: We focus on implementing and optimizing a sixth-order finite-difference solver for simulating compressible fluids on a GPU using third-order Runge-Kutta integration. Since graphics processing units perform well in data-parallel tasks, this makes them an attractive platform for fluid simulation. However, high-order stencil computation is memory-intensive with respect to both main memory and the caches of the GPU. We present two approaches for simulating compressible fluids using 55-point and 19-point stencils. We seek to reduce the requirements for memory bandwidth and cache size in our methods by using cache blocking and decomposing a latency-bound kernel into several bandwidth-bound kernels. Our fastest implementation is bandwidth-bound and integrates 343 million grid points per second on a Tesla K40t GPU, achieving a 3.6x speedup over a comparable hydrodynamics solver benchmarked on two Intel Xeon E5-2690v3 processors. Our alternative GPU implementation is latency-bound and achieves the rate of 168 million updates per second. (C) 2017 Elsevier B.V. All rights reserved.
Subject: Computational techniques
Fluid dynamics
Finite difference methods in fluid dynamics
Hydrodynamics
Astrophysical applications
Computer science and technology
CODE
TURBULENCE
115 Astronomy, Space science
114 Physical sciences
113 Computer and information sciences
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
1707.08900.pdf 345.8Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record