Hostname: page-component-586b7cd67f-t8hqh Total loading time: 0 Render date: 2024-11-25T18:57:02.153Z Has data issue: false hasContentIssue false
  • English
  • Français

Astrophysical Supercomputing with GPUs: Critical Decisions for Early Adopters*

Published online by Cambridge University Press:  02 January 2013

Christopher J. Fluke ,
David G. Barnes ,
Benjamin R. Barsdell  and
Amr H. Hassan
Christopher J. Fluke*
Affiliation:
Centre for Astrophysics and Supercomputing, Swinburne University of Technology, PO Box 218, Hawthorn, VIC 3122, Australia
David G. Barnes
Affiliation:
Centre for Astrophysics and Supercomputing, Swinburne University of Technology, PO Box 218, Hawthorn, VIC 3122, Australia
Benjamin R. Barsdell
Affiliation:
Centre for Astrophysics and Supercomputing, Swinburne University of Technology, PO Box 218, Hawthorn, VIC 3122, Australia
Amr H. Hassan
Affiliation:
Centre for Astrophysics and Supercomputing, Swinburne University of Technology, PO Box 218, Hawthorn, VIC 3122, Australia
*
BCorresponding author. Email: [email protected]
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

General-purpose computing on graphics processing units (GPGPU) is dramatically changing the landscape of high performance computing in astronomy. In this paper, we identify and investigate several key decision areas, with a goal of simplifying the early adoption of GPGPU in astronomy. We consider the merits of OpenCL as an open standard in order to reduce risks associated with coding in a native, vendor-specific programming environment, and present a GPU programming philosophy based on using brute force solutions. We assert that effective use of new GPU-based supercomputing facilities will require a change in approach from astronomers. This will likely include improved programming training, an increased need for software development best practice through the use of profiling and related optimisation tools, and a greater reliance on third-party code libraries. As with any new technology, those willing to take the risks and make the investment of time and effort to become early adopters of GPGPU in astronomy, stand to reap great benefits.

Keywords

methods: numericalmethods: n-body simulationsgravitational lensing
Type
Research Article
Information
Publications of the Astronomical Society of Australia , Volume 28 , Issue 1 , 2011 , pp. 15 - 27
Copyright
Copyright © Astronomical Society of Australia 2011

Footnotes

*

Research undertaken as part of the Commonwealth Cosmology Initiative (CCI: www.thecci.org), an international collaboration supported by the Australian Research Council.

References

Aarseth, S. J., 1999, PASP, 111, 1333CrossRefGoogle Scholar
Aubert, D. & Teyssier, R., 2010, arXiv:1004.2503 [astro-ph]Google Scholar
Aubert, D., Amini, M. & David, R., 2009, Lecture Notes in Computer Science, 5544/2009, 874CrossRefGoogle Scholar
Barsdell, B. R., Fluke, C. J. & Barnes, D. G., 2010, MNRAS, accepted June 2010, arXiv:1007.1660 [astro-ph]Google Scholar
Bate, N. F., Fluke, C. J., Barsdell, B. R., Garsden, H. & Lewis, G. F., 2010, New Astronomy, 15, 726CrossRefGoogle Scholar
Belleman, R. G., Bédorf, J. & Portegies Zwart, S. F., 2008, NewA, 13, 103CrossRefGoogle Scholar
Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J. & Skadron, K., 2008, Journal of Parallel and Distributed Computing, 68, 1370CrossRefGoogle Scholar
Christadler, I. & Weinberg, V., 2010, arXiv:1001.1902 [cs.PF]Google Scholar
Elsen, E., Vishal, V., Houston, M., Pande, V., Hanrahan, P. & Darve, E., 2007, arXiv:0706.3060v1 [cs.CE]Google Scholar
Ford, E. B., 2008, NewA, 14, 406CrossRefGoogle Scholar
Fournier, A. & Fussell, D., 1988, ACM Transactions on Graphics, 7, 103CrossRefGoogle Scholar
Gaburov, E., Harfst, S. & Portegies Zwart, S., 2009, NewA, 14, 630CrossRefGoogle Scholar
Hamada, T. & Iitaka, T., 2007, arXiv:astro-ph/0703100v1Google Scholar
Harris, C., Haines, K. & Staveley-Smith, L., 2008, ExA, 22, 129Google Scholar
Karimi, K., Dickson, N. G. & Hamaz, F., 2010, arXiv:1005.2581v1 [cs.PF]Google Scholar
Khanna, G. & McKennon, J., 2010, arXiv:1001.3631v1 [astro-ph]Google Scholar
Kirk, D. B. & Hwu, W.-m. W., 2010, Programming Massively Parallel Processors (Burlington: Morgan Kauffman Publishers)Google Scholar
Larus, J. & Gannon, D., 2010, in The Fourth Paradigm: Data-Intensive Scientific Discovery, Eds. Hey, T., Tansley, S. & Tolle, K. (Microsoft Research), 125Google Scholar
Moore, A. J., Quillen, A. C. & Edgar, R. G., 2008, arXiv:0809.2855v1 [astro-ph]Google Scholar
Nelder, J. A. & Mead, R., 1965, Computer Journal, 7, 308CrossRefGoogle Scholar
Nyland, L., Harris, M. & Prins, J. F., 2004, in ACM Workshop on General-Purpose Computing on Graphics Processors (Poster), C-37Google Scholar
Nyland, L., Harris, M. & Prins, J. F., 2008, GPU Gems 3, Addison-Wesley, ch. 31, 677Google Scholar
Ord, S., Greenhil, L., Wayth, R., Mitchell, D., Dale, K., Pfister, H. & Edgar, R. G., 2009, arXiv:0902.0915 [astro-ph.IM]Google Scholar
Owens, J. D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A. E. & Purcell, T. J., 2005, Computer Graphics Forum, 26, 80CrossRefGoogle Scholar
Portegies Zwart, S. F., Belleman, R. G. & Geldof, P. M., 2007, NewA, 12, 641CrossRefGoogle Scholar
Schaaf, K. V. D. & Overeem, R., 2004, ExA, 17, 287Google Scholar
Schive, H.-Y., Chien, C.-H., Wong, S.-K., Tsai, Y.-C. & Chiueh, T., 2007, NewA, 13, 418CrossRefGoogle Scholar
Schroeder, B., Pinheiro, E. & Weber, W.-D., 2009, in SIGMETRICS '09: Proceedings of the eleventh international joint conference on Measurement and modeling of computer systems, 193CrossRefGoogle Scholar
Simpson, A., Bull, M. & Hill, J., 2008, PRACE Deliverable D6.1, available from http://www.prace-project.eu/documents/public-deliverables-1/Google Scholar
Szalay, T., Springel, V. & Lemson, G., 2008, arXiv:0811.2055v2 [cs.GR]Google Scholar
Thompson, A. C., Fluke, C. J., Barnes, D. G. & Barsdell, B. R., 2010, NewA, 15, 16CrossRefGoogle Scholar
Tomov, S., McGuigan, M., Bennett, R., Smith, G. & Spiletic, J., 2003, arXiv:cs/0312006Google Scholar
Venkatasubramanian, S., 2003, in SIGMOD Workshop on Management and Processing of Massive Data, arXiv:cs/0310002Google Scholar
Wayth, R., Dale, K., Greenhill, L. J., Mitchell, D. A., Ord, S. & Pfister, H., 2007, AAS, 211, 1104Google Scholar