Abstract
As a powerful and flexible processor, the Graphic Processing Unit (GPU) can offer great faculty in solving many high-performance computing applications. Sweep3D, which simulates a single group time-independent discrete ordinates (S n ) neutron transport deterministically on 3D Cartesian geometry space, represents the key part of a real ASCI application. The wavefront process for parallel computation in Sweep3D limits the concurrent threads on the GPU. In this paper, we present multi-dimensional optimization methods for Sweep3D, which can be efficiently implemented on the fine grained parallel architecture of the GPU. Our results show that the performance of overall Sweep3D on CPU-GPU hybrid platform can be improved up to 2.25 times as compared to the CPU-based implementation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nguyen, H.: GPU Gems 3. Addison Wesley, Reading (2007)
Kirk, D.: Innovation in graphics technology. In: Talk in Canadian Undergraduate Technology Conference (2004)
AMD Corporation: ATI Radeon HD 5870 Feature Summary, http://www.amd.com/
NVIDIA Corporation: CUDA Programming Guide Version 2.1 (2008)
AMD Corporation: ATI Stream Computing User Guide Version 1.4.0a (2009)
Munshi, A.: The OpenCL Specification Version: 1.0. Khronos OpenCL Working Group (2009)
NVIDIA Corporation: Vertical solutions on CUDA, http://www.nvidia.com/object/vertical_solutions.html
Mathis, M.M., Amato, N., Adams, M., Zhao, W.: A General Performance Model for Parallel Sweeps on Orthogonal Grids for Particle Transport Calculations. In: Proc. ACM Int. Conf. Supercomputing, pp. 255–263. ACM, New York (2000)
Hoisie, A., Lubeck, O., Wasserman, H.: Scalability analysis of multidimensional wavefront algorithms on large-scale SMP clusters. In: The 7th Symposium on the Frontiers of Massively Parallel Computation, pp. 4–15. IEEE Computer Society, Los Alamitos (1999)
Hoisie, A., Lubeck, O., Wasserman, H.: Performance and scalability analysis of teraflop- scale parallel architectures using multidimensional wavefront applications. International Journal of High Performance Computing Applications 14(4), 330–346 (2000)
Los Alamos National Laboratory: Sweep3D, http://wwwc3.lanl.gov/pal/software/sweep3d/
Davis, K., Hoisie, A., Johnson, G., Kerbyson, D.J., Lang, M., Pakin, M., Petrini, F.: A Performance and Scalability Analysis of the BlueGene/L Architecture. In: Proceedings of the 2004 ACM/IEEE conference on Supercomputing, pp. 41–50 (2004)
Barker, K.J., Davis, K., Hoisie, A., Kerbyson, D.J., Lang, M., Pakin, S., Sancho, J.C.: Entering the petaflop era: the architecture and performance of Roadrunner. In: Proceedings of the 2008 ACM/IEEE conference on Supercomputing (2008)
Lewis, E.E., Miller, W.F.: Computational Methods of Neutron Transport. American Nuclear Society, LaGrange Park (1993)
Koch, K., Baker, R., Alcouffe, R.: Solution of the First-Order Form of Three-Dimensional Discrete Ordinates Equations on a Massively Parallel Machine. Transactions of American Nuclear Society 65, 198–199 (1992)
Mathis, M.M., Kerbyson, D.J.: A General Performance Model of structured and Unstructured Mesh Particle Transport Computations. Journal of Supercomputing 34, 181–199 (2005)
Kerbyson, D.J., Hoisie, A.: Analysis of Wavefront Algorithms on Large-scale Two-level Heterogeneous Processing Systems. In: Workshop on Unique Chips and Systems, pp. 259–279 (2006)
Petrini, F., Fossum, G., Fernandez, J., Varbanescu, A.L., Kistler, N., Perrone, M.: Multicore Surprises: Lessons Learned from Optimizing Sweep3D on the Cell Broadband Engine. In: The 21th International Parallel and Distributed Processing Symposium (2007)
NVIDIA Corporation: NVIDIA Tesla S1070 1U Computing System, http://www.nvidia.com/object/product_tesla_s1070_us.html
Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebra. In: Proceedings of the 2008 ACM/IEEE conference on Supercomputing (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gong, C., Liu, J., Gong, Z., Qin, J., Xie, J. (2010). Optimizing Sweep3D for Graphic Processor Unit. In: Hsu, CH., Yang, L.T., Park, J.H., Yeo, SS. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2010. Lecture Notes in Computer Science, vol 6081. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13119-6_36
Download citation
DOI: https://doi.org/10.1007/978-3-642-13119-6_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13118-9
Online ISBN: 978-3-642-13119-6
eBook Packages: Computer ScienceComputer Science (R0)