Abstract
As the processor has entered the multi-core/many-core era, the parallel processing capability of a single processor can be improved in scale with increasing cores. However, for the high performance computation (HPC) clusters, the improvement of inter-node communication latency is far behind of the performance improvement of processors. As a result, communication latency often becomes the performance bottleneck of most HPC applications. This paper focuses on solving the communication latency problem of adjacent inter-action simulation on multi-core/many-core clusters, and pro-poses an optimized algorithm for adjacent interaction simula-tion on modern general purpose graphic many-core architec-tures and an O(B+2R) algorithm for inter-node latency-hiding. The theoretical analysis and experimental result show that the techniques proposed in this paper can effectively improve the performance of adjacent interaction simulation on multi-core/many-core clusters.
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.
Similar content being viewed by others
References
Tu, B.B., Zou, M., Zhan, J.F., Zhao, X.F., Fan, J.: Research on Parallel Computation Model with Memory Hierarchy on Multi-Core Clusters. Chinese Journal of Computers 11 (2008) (in Chinese with English abstract)
Tang, Y.: Research on the Communication Problem of Large Scale Scientific Computing on High Performance Cluster Environment (Ph.D. Thesis). Chinese Academy of Sciences, Beijing (2004) (in Chinese with English abstract)
Chen, S., Doolean, G.D.: Lattice Boltzman Method for Fluid Flows. Annual Review of Fluid Mechanics 30, 329–364 (1998)
Stam, J.: Stable Fluids. In: Proceedings of SIGGRAPH 1999, pp. 121–128 (1999)
Harris, M.J.: Fast Fluid Dynamics Simulation on the GPU. In: Fernando, R. (ed.) GPU Gems, pp. 637–665. Addison-Wesley (2004)
North, M.J., et al.: Experiences Creating Three Implementations of the Repast Agent Modeling Toolkit. ACM Transactions on Modeling and Computer Simulation 16, 1–25 (2006)
Walter, B., et al.: UAV Swarm Control: Calculating Digital Phermone Fields with the GPU. In: Interservice/Industry Training, Simulation and Education Conference (IITSEC), Orlando, FL (2005)
Uhrmacher, A.M., Gugler, K.: Distributed, parallel simulation of multiple, deliberative agents. In: Proceedings of the Fourteenth Workshop on Parallel and Distributed Simulation, Bologna, Italy (2000)
Chaturvedi, A., et al.: Bridging Kinetic and Non-kinetic Interactions over Time and Space Continua. In: Interservice/Industry Training, Simulation and Education Conference, Orlando, FL, USA (2005)
Parker, J.: A Flexible, Large-scale, Distributed Agent-based Epidemic Model. In: Winter Simulation Conference, Piscataway, NJ (2007)
Armstrong, R.C., et al.: Parallel Computing in Enterprise Modeling. Sandia National Laboratory. Techincal Report SAND2008-6172, 2008/08/01 (2008)
Aaby, B.G., Perumalla, K.S., Seal, S.K.: Efficient Simulation of Agent-Based Models on Multi-GPU and Multi-Core Clusters. In: Proceedings of the 3rd International ICST Conference on Simulation Tools and Techniques, vol. (29), ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), Brussels (2010)
Krishnamoorthy, S., et al.: Effective Automatic Parallelization of Stencil Computations. In: Programming Languages Design and Implementation (PLDI), San Diego, California, USA (2007)
Datta, K., et al.: Stencil Computation Optimization and Auto-tuning on State-of-the-Art Multicore Architectures. In: Supercomputing, Austin, Texas (2008)
NVIDIA Corporation. NVIDIA CUDA SDK code samples, http://developer.download.nvidia.com/compute/cuda/sdk/website/samples.html
Khronos. Opencl - the open standard for parallel programming of heterogeneous systems, http://www.khronos.org/opencl/
Fujimoto, R.M.: Parallel and Distributed Simulation Systems. John Wiley&Sons, Inc. (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li-li, C., Wei, L., Jing, Z., Shuai, S., Jian-xin, H. (2013). A Latency-Hiding Scheme for Adjacent Interaction Simulation on Multi-core/Many-Core Clusters. In: Tan, G., Yeo, G.K., Turner, S.J., Teo, Y.M. (eds) AsiaSim 2013. AsiaSim 2013. Communications in Computer and Information Science, vol 402. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-45037-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-45037-2_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-45036-5
Online ISBN: 978-3-642-45037-2
eBook Packages: Computer ScienceComputer Science (R0)