Comparison of Semi-Implicit and Explicit Finite Difference Algorithms on Highly Parallel Processing Architectures

Nicholas J. Stewart; David W. Holmes; Wen Xian Lin; Steven W. Armfield; Michael P. Kirkpatrick

doi:10.4028/www.scientific.net/AMM.553.193

Paper Titles

Numerical Simulation of Tank Discharge Using Smoothed Particle Hydrodynamics
p.168

CFD Flow Model and its Effects on the Calculations of High Pressure Sprays
p.174

Development of an Effective FVLBM Code for the Study of Turbulent and Multiphase Flows
p.180

A Numerical Solution Based on the Fokker-Planck Equation for Dilute Polymer Solutions Using High Order RBF Methods
p.187

Comparison of Semi-Implicit and Explicit Finite Difference Algorithms on Highly Parallel Processing Architectures
p.193

Investigation into the Existence of Cavitation within Haemodialysis Needles
p.199

The Aerodynamics of a Cornering Inverted Wing in Ground Effect
p.205

Fundamental Studies of Vortices Induced by a Vortex-Generator for Automotive Applications
p.211

Application of Kriging to Motorsport Aerodynamic Analysis
p.217

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 553Comparison of Semi-Implicit and Explicit Finite...

Comparison of Semi-Implicit and Explicit Finite Difference Algorithms on Highly Parallel Processing Architectures

Abstract:

Modern GPUs (graphical processing units) are a common source of processing power inmany supercomputers. Their performance derives from the highly parallel architecture that is em-ployed and have the benefit of low cost, temperature and power consumption. Two finite differencemodels have been implemented on GPU, a semi-implicit and an explicit algorithm, to numericallymodel a stratified shear layer, that needs fine meshes to be modelled accurately. The GPU modelswere shown to improve performance by factors of around 50x and 20x for the semi-implicit and ex-plicit models respectively.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 553)

Pages:

193-198

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.553.193

Citation:

Cite this paper

Online since:

May 2014

Authors:

Nicholas J. Stewart, David W. Holmes, Wen Xian Lin, Steven W. Armfield, Michael P. Kirkpatrick

Keywords:

Boundary Layer, CUDA, GPGPU, High Performance Computing

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] J.R. Conzemius, E. Fedorovich, Dynamics of shear convective boundary layer entrainment, J. Atmospheric Sci., 66, (2006) 1151-1178.

DOI: 10.1175/jas3691.1

Google Scholar

[2] L.S. Caretto, A.D. Gosman, S.V. Patankar, Two calculation procedures for steady, threedimensional flows with recirculation, Proc. of the 3rd Int. Conf. on Numerical Methods in Fluid Mechanics, Lecture Notes in Physics, Vol. 19, 1972, Pages 60-68.

DOI: 10.1007/bfb0112677

Google Scholar

[3] R.W. MacCormack: The effect of viscosity in hypervelocity impact cratering, AIAA Paper, 1969, Pages 69-354.

Google Scholar

[4] Nvidia: CUDA Programming Guide on http: /www. nvidia. com/cuda.

Google Scholar

[5] R.S. Bernard, A MacCormack scheme for incompressible flow, Computers & Mathematics with Applications, 24, (Issues 5-6), (1992) 151-168.

DOI: 10.1016/0898-1221(92)90046-k

Google Scholar

[6] R.H. Pletcher, J.C. Tannehill, D.A. Anderson: Computational Fluid Mechanics and Heat Transfer, third ed., CRC Press, Boca Raton, (2012).

Google Scholar