Hierarchical Tori Connected Mesh Network M.M. Hafizur Rahman 1 , Asadullah Shah 1 , Masaru Fukushi 2 , and Yasushi Inoguchi 3 1 Dept. of Computer Science, KICT, International Islamic University Malaysia (IIUM), P.O. Box. 10, 50728, Kuala Lumpur, Malaysia 2 Graduate School of Science and Engineering, Yamaguchi University, Tokiwadai 2-16-1, Ube, 755-8611, Japan 3 Research Center for Advanced Computing Infrastructure, Japan Advanced Institute of Science and Technology (JAIST), Ishikawa 923-1292, Japan {hafizur,asadullah}@iium.edu.my, mfukushi@yamaguchi-u.ac.jp, inoguchi@jaist.ac.jp Abstract. Hierarchical interconnection networks provide high perfor- mance at low cost by exploring the locality that exists in the commu- nication patterns of massively parallel computers. A Hierarchical Tori connected Mesh Network (HTM) is a 2D-torus network of multiple basic modules, in which the basic modules are 3D-mesh networks that are hier- archically interconnected for higher-level networks. This paper addresses the architectural details of the HTM and explores aspects such as degree, diameter, cost, average distance, arc connectivity, bisection width, and wiring complexity. We also present a deadlock-free routing algorithm for the HTM using two virtual channels and evaluate the network’s dynamic communication performance using the proposed routing algorithm un- der uniform traffic and bit-flip traffic patterns. We evaluate the dynamic communication performance of HTM, H3DM, mesh, and torus networks by computer simulation. It is shown that the HTM possesses several attractive features, including constant node degree, small diameter, low cost, small average distance, moderate (neither too low, nor too high) bi- section width, small wiring complexity, and high throughput per link and very low zero load latency, which provide better dynamic communication performance than that of H3DM, mesh, and torus networks. Keywords: Interconnection network, HTM network, Deadlock-free routing algorithm, Static network performance, Uniform traffic patterns, Bit-Flip traffic patterns, Dynamic communication performance. 1 Introduction High-performance computing is necessary in solving the grand challenge prob- lems in many areas such as development of new materials and sources of energy, development of new medicines and improved health care, strategies for disaster prevention and mitigation, weather forecasting, and for scientific research includ- ing the origins of matter and the universe. This makes the current supercomputer B. Murgante et al. (Eds.): ICCSA 2013, Part V, LNCS 7975, pp. 197–210, 2013. c  Springer-Verlag Berlin Heidelberg 2013