Speeding up the MATLAB complex networks package using graphic processors

doi:10.1088/1674-1056/20/9/098901

中国物理B ›› 2011, Vol. 20 ›› Issue (9): 98901-098901.doi: 10.1088/1674-1056/20/9/098901

Speeding up the MATLAB complex networks package using graphic processors

唐玉华¹, 张百达², 吴俊杰², 李鑫²

(1)Department of Computer Science and Technology, School of Computer, National University of Defense Technology, Changsha 410073, China; (2)National laboratory for Parallel and Distributed Processing, School of Computer, National University of Defense Technology, Changsha 410073, China

收稿日期:2011-03-18 修回日期:2011-05-04 出版日期:2011-09-15 发布日期:2011-09-15

Speeding up the MATLAB complex networks package using graphic processors

Zhang Bai-Da(张百达)^a)†, Tang Yu-Hua(唐玉华)^b), Wu Jun-Jie(吴俊杰)^a), and Li Xin(李鑫)^a)

^a National laboratory for Parallel and Distributed Processing, School of Computer, National University of Defense Technology, Changsha 410073, China; ^b Department of Computer Science and Technology, School of Computer, National University of Defense Technology, Changsha 410073, China

Received:2011-03-18 Revised:2011-05-04 Online:2011-09-15 Published:2011-09-15

摘要/Abstract

摘要： The availability of computers and communication networks allows us to gather and analyse data on a far larger scale than previously. At present, it is believed that statistics is a suitable method to analyse networks with millions, or more, of vertices. The MATLAB language, with its mass of statistical functions, is a good choice to rapidly realize an algorithm prototype of complex networks. The performance of the MATLAB codes can be further improved by using graphic processor units (GPU). This paper presents the strategies and performance of the GPU implementation of a complex networks package, and the Jacket toolbox of MATLAB is used. Compared with some commercially available CPU implementations, GPU can achieve a speedup of, on average, 11.3×. The experimental result proves that the GPU platform combined with the MATLAB language is a good combination for complex network research.

关键词: complex networks, graphic processors unit, MATLAB, Jacket Toolbox

Abstract: The availability of computers and communication networks allows us to gather and analyse data on a far larger scale than previously. At present, it is believed that statistics is a suitable method to analyse networks with millions, or more, of vertices. The MATLAB language, with its mass of statistical functions, is a good choice to rapidly realize an algorithm prototype of complex networks. The performance of the MATLAB codes can be further improved by using graphic processor units (GPU). This paper presents the strategies and performance of the GPU implementation of a complex networks package, and the Jacket toolbox of MATLAB is used. Compared with some commercially available CPU implementations, GPU can achieve a speedup of, on average, 11.3×. The experimental result proves that the GPU platform combined with the MATLAB language is a good combination for complex network research.

Key words: complex networks, graphic processors unit, MATLAB, Jacket Toolbox

中图分类号: (Networks and genealogical trees)

89.75.Hc

87.23.Ge (Dynamics of social systems) 89.20.Hh (World Wide Web, Internet) 89.75.-k (Complex systems)

张百达, 唐玉华, 吴俊杰, 李鑫. Speeding up the MATLAB complex networks package using graphic processors[J]. 中国物理B, 2011, 20(9): 98901-098901.

Zhang Bai-Da(张百达), Tang Yu-Hua(唐玉华), Wu Jun-Jie(吴俊杰), and Li Xin(李鑫) . Speeding up the MATLAB complex networks package using graphic processors[J]. Chin. Phys. B, 2011, 20(9): 98901-098901.

参考文献 29

[1]	Watts D J and Strogatz S H 1998 Nature 393 440
[2]	Barab A L and Albert R 1999 Science 286 509
[3]	Newman M E and Girvan M 2004 Phys. Rev. E 69 26113
[4]	Barrat A, Barthelemy M and Vespignani A 2004 Phys. Rev. Lett. 22 228701
[5]	Albert R and Barab A L 2002 Rev. Mod. Phys. 74 47
[6]	Newman M E 2003 SIAM Rev. 45 167
[7]	Cui D, Gao Z Y and Zhao X M 2008 Chin. Phys. B 17 1703
[8]	Zhang C X, Li H and Lin P 2008 Chin. Phys. B 17 4458
[9]	NVIDIA 2003 SIAM Review 45 167
[10]	The AccelerEyes 2011 Jacket User Guide http://www.accelereyes.com
[11]	Nickolls J 2010 Stanford CS 193G Lecture 15 56 72
[12]	Hennessy J L, Patterson D A and Goldberg D 2003 Computer Architecture: A Quantitative Approach 3rd edn. (San Francisco: Morgan Kaufmann) pp. 128—132
[13]	Newman M 2002 Phys. Rev. Lett. 89 208701
[14]	Pei W D, Chen Z Q and Yuan Z Z 2008 Chin. Phys. B 17 373
[15]	Rodrigues F, Travieso G and Boas V 2007 Adv. Phys. 56 167
[16]	Shen Y 2011 Chin. Phys. B 20 511
[17]	Tang Y, Wong W K, Fang J A and Miao Q Y 2011 Chin. Phys. B 20 513
[18]	Wang S J, Wu Z X, Dong H R and Chen G R 2011 Chin. Phys. B 20 903
[19]	Ryoo S, Rodrigues C I, Stone S S, Stratton J A, Ueng S Z, Baghsorkhi S S and Hwu W W 2008 Journal of Parallel and Distributed Computing 68 1389
[20]	Ryoo S, Rodrigues C I, Stone S S, Baghsorkhi S S, Ueng S Z, Stratton J A and Hwu W W 2008 newblock Program Optimization Space Pruning for a Multithreaded GPU
[21]	Shane R, Ryoo S, Rodrigues C I, Baghsorkhi S S, Stone S S, Kirk D B, et al. 2007 Parallel Comput. 33 663
[22]	Messmer P, Mullowney P J and Granger B E 2008 Computing in Science and Engineering 10 70
[23]	The GP-you group 2011 GPUmat User Guide
[24]	Choy R and Edelman A 2005 Proc. IEEE 93 331
[25]	Kong J, Dimitrov M, Yang Y, Liyanage J, Cao L, Staples J, Mantor M and Zhou H 2010 Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units pp. 78—85
[26]	Szafaryn L G, Skadron K and Saucerman J J 2009 Biomedicine in Computing: Systems, Architectures, and Circuits 32 1
[27]	Moore N and Leeser M 2009 High Performance Embedded Computing Workshop
[28]	Brodtkorb A R 2008 Scientific Computing on Heterogeneous Architectures 12 109
[29]	Fatica M and Jeong W K 2007 Proceedings of the Eleventh Annual High Performance Embedded Computing Workshop, Lexington, Massachusetts 2007 pp. 18—20

Speeding up the MATLAB complex networks package using graphic processors

Speeding up the MATLAB complex networks package using graphic processors

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献 29

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	Jie Zhou(周洁), Cheng Yuan(袁诚), Zu-Yu Qian(钱祖燏), Bing-Hong Wang(汪秉宏), and Sen Nie(聂森). Analysis of cut vertex in the control of complex networks[J]. 中国物理B, 2023, 32(2): 28902-028902.
[2]	Pengli Lu(卢鹏丽) and Wei Chen(陈玮). Vertex centrality of complex networks based on joint nonnegative matrix factorization and graph embedding[J]. 中国物理B, 2023, 32(1): 18903-018903.
[3]	Ai-Xia Feng(冯爱霞), Qi-Guang Wang(王启光), Shi-Xuan Zhang(张世轩), Takeshi Enomoto(榎本刚), Zhi-Qiang Gong(龚志强), Ying-Ying Hu(胡莹莹), and Guo-Lin Feng(封国林). Characteristics of vapor based on complex networks in China[J]. 中国物理B, 2022, 31(4): 49201-049201.
[4]	Yahan Deng(邓雅瀚), Zhongkai Mo(莫中凯), and Hongqian Lu(陆宏谦). Robust H_∞ state estimation for a class of complex networks with dynamic event-triggered scheme against hybrid attacks[J]. 中国物理B, 2022, 31(2): 20503-020503.
[5]	Hongwei Zhang(张红伟), Ran Cheng(程然), and Dawei Ding(丁大为). Finite-time synchronization of uncertain fractional-order multi-weighted complex networks with external disturbances via adaptive quantized control[J]. 中国物理B, 2022, 31(10): 100504-100504.
[6]	Gui-Qiong Xu(徐桂琼), Lei Meng(孟蕾), Deng-Qin Tu(涂登琴), and Ping-Le Yang(杨平乐). LCH: A local clustering H-index centrality measure for identifying and ranking influential nodes in complex networks[J]. 中国物理B, 2021, 30(8): 88901-088901.
[7]	Tong-Feng Weng(翁同峰), Xin-Xin Cao(曹欣欣), and Hui-Jie Yang(杨会杰). Complex network perspective on modelling chaotic systems via machine learning[J]. 中国物理B, 2021, 30(6): 60506-060506.
[8]	杨远志, 胡敏, 黄泰愚. Influential nodes identification in complex networks based on global and local information[J]. 中国物理B, 2020, 29(8): 88903-088903.
[9]	闫小丽, 崔亚鹏, 倪顺江. Identifying influential spreaders in complex networks based on entropy weight method and gravity law[J]. 中国物理B, 2020, 29(4): 48902-048902.
[10]	石勇, 李博, 龙文. Pyramid scheme model for consumption rebate frauds[J]. 中国物理B, 2019, 28(7): 78901-078901.
[11]	朱世钊, 王玉青, 汪秉宏. Theoretical analyses of stock correlations affected by subprime crisis and total assets: Network properties and corresponding physical mechanisms[J]. 中国物理B, 2019, 28(10): 108901-108901.
[12]	庞明宝, 黄玉满. Coordinated chaos control of urban expressway based on synchronization of complex networks[J]. 中国物理B, 2018, 27(11): 118902-118902.
[13]	王兴元, 王宇, 秦小蒙, 李睿, Justine Eustace. Detecting overlapping communities based on vital nodes in complex networks[J]. 中国物理B, 2018, 27(10): 100504-100504.
[14]	郑志刚, 钱郁. Dominant phase-advanced driving analysis of self-sustained oscillations in biological networks[J]. 中国物理B, 2018, 27(1): 18901-018901.
[15]	孙昱, 姚佩阳, 万路军, 申健, 钟赟. Ranking important nodes in complex networks by simulated annealing[J]. 中国物理B, 2017, 26(2): 20201-020201.