The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.03 - May/June (2012 vol.14)
pp: 10-19
Ali Khajeh-Saeed , University of Massachusetts, Amherst
J. Blair Perot , University of Massachusetts, Amherst
ABSTRACT
<p>In this scenario, computational fluid dynamics simulations of turbulence are performed with 64 GPUs and an optimized CFD algorithm using communication/computation overlapping. Detailed timings reveal that the GPUs' internal calculations are so efficient that operations related to data exchange between compute nodes now cause a scaling bottleneck on all but the largest problems.</p>
INDEX TERMS
Computational fluid dynamics, CFD, multi-GPU, conjugate gradient, Laplacian, scientific computing
CITATION
Ali Khajeh-Saeed, J. Blair Perot, "Computational Fluid Dynamics Simulations Using Many Graphics Processors", Computing in Science & Engineering, vol.14, no. 3, pp. 10-19, May/June 2012, doi:10.1109/MCSE.2011.117
REFERENCES
1. J.B. Perot and J. Gadebusch, "A Stress Transport Equation Model for Simulating Turbulence at Any Mesh Resolution," Theoretical and Computational Fluid Dynamics, vol. 23, no. 4, 2009, pp. 271–286.
2. J.B. Perot, "An Analysis of the Fractional Step Method," J. Computational Physics, vol. 108, no. 1, 1993, pp. 183–199.
3. W. Chang, F. Giraldo, and J.B. Perot, "Analysis of an Exact Fractional Step Method," J. Computational Physics, vol. 180, no. 1, 2002, pp. 183–189.
4. J.B. Perot and V. Subramanian, "Discrete Calculus Methods for Diffusion," J. Computational Physics, vol. 224, no. 1, 2007, pp. 59–81.
5. J.B. Perot, "Conservation Properties of Unstructured Staggered Mesh Schemes," J. Computational Physics, vol. 159, no. 1, 2000, pp. 58–89.
6. J.B. Perot, "Discrete Conservation Properties of Unstructured Mesh Schemes," Ann. Rev. Fluid Mechanics, vol. 43, 2011, pp. 299–318.
7. J.B. Perot, "Determination of the Decay Exponent in Mechanically Stirred Isotropic Turbulence," AIP Advances, vol. 1, no. 2, 2011; doi:10.1063/1.3582815.
8. P. Micikevicius, "3D Finite Difference Computation on GPUs Using CUDA," Proc. 2nd Workshop General Purpose Processing on Graphics Processing Units, ACM, 2009, pp. 79–84.
29 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool