Hierarchical Tori Connected Mesh Network

  • M. M. Hafizur Rahman
  • Asadullah Shah
  • Masaru Fukushi
  • Yasushi Inoguchi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7975)

Abstract

Hierarchical interconnection networks provide high performance at low cost by exploring the locality that exists in the communication 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 hierarchically 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 under 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) bisection 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 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dally, W.J.: Performance Analysis of k-ary n-cube Interconnection Networks. IEEE Trans. on Computers 39(6), 775–785 (1990)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Abd-El-Barr, M., Al-Somani, T.F.: Topological Properties of Hierarchical Interconnection Networks: A Review and Comparison. Journal of Electrical and Computer Engineering 2011, 12 pages 2011)Google Scholar
  3. 3.
    Lai, P.L., Hsu, H.C., Tsai, C.H., Stewart, I.A.: A class of hierarchical graphs as topologies for interconnection networks. Theoretical Computer Science, Elsevier 411, 2912–2924 (2010)MathSciNetMATHCrossRefGoogle Scholar
  4. 4.
    Liu, Y., Li, C., Han, J.: RTTM: A New Hierarchical Interconnection Network for Massively Parallel Computing. In: Zhang, W., Chen, Z., Douglas, C.C., Tong, W. (eds.) HPCA 2009. LNCS, vol. 5938, pp. 264–271. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Horiguchi, S.: New Interconnection for massively Parallel and Distributed System. Research Report, 09044150, JAIST, pp. 47-57 (1999)Google Scholar
  6. 6.
    Rahman, M.M.H., Shah, A., Inoguchi, Y.: On Dynamic Communication Performance of a Hierarchical 3D-Mesh Network. In: Park, J.J., Zomaya, A., Yeo, S.-S., Sahni, S. (eds.) NPC 2012. LNCS, vol. 7513, pp. 180–187. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Ni, L.M., McKinley, P.K.: A Survey of Wormhole Routing Techniques in Direct Networks. IEEE Computer 26(2), 62–76 (1993)CrossRefGoogle Scholar
  8. 8.
    Dally, W.J., Seitz, C.L.: Deadlock free Message Routing in Multiprocessor Interconnection Networks. IEEE Trans. on Computers C36(5), 547–553 (1987)CrossRefGoogle Scholar
  9. 9.
    Dally, W.J.: Virtual-Channel Flow Control. IEEE Trans. on Parallel and Distributed Systems 3(2), 194–205 (1992)CrossRefGoogle Scholar
  10. 10.
    Kumar, J.M., Patnaik, L.M.: Extended Hypercube: A Hierarchical Interconnection Network of Hypercube. IEEE Trans. Parallel Distrib. Syst. 3(1), 45–57 (1992)CrossRefGoogle Scholar
  11. 11.
    Najaf-abadi, H.H., Sarbazi-Azad, H.: The Effects of Adaptivity on the Performance of the OTIS-Hypercube Under Different Traffic Patterns. In: Jin, H., Gao, G.R., Xu, Z., Chen, H. (eds.) NPC 2004. LNCS, vol. 3222, pp. 390–398. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  12. 12.
    Najaf-abadi, H.H., Sarbazi-Azad, H.: The Effects of Adaptivity on the Performance of the OTIS-Hypercube Under Different Traffic Patterns. In: Jin, H., Gao, G.R., Xu, Z., Chen, H. (eds.) NPC 2004. LNCS, vol. 3222, pp. 390–398. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  13. 13.
    Holsmark, R., Kumar, S., Palesi, M., Mekia, A.: HiRA: A Methodology for Deadlock Free Routing in Hierarchical Networks on Chip. In: Proc. of the 3rd ACM/IEEE NOCS, pp. 2–11 (2009)Google Scholar
  14. 14.
    Koibuchi, M., Anjo, K., Yamada, Y., Jouraku, A., Amano, H.: A Simple Data Transfer Technique using Local Address for Networks-on-Chips. IEEE Transactions on Parallel and Distributed Systems 17(12), 1425–1437 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • M. M. Hafizur Rahman
    • 1
  • Asadullah Shah
    • 1
  • Masaru Fukushi
    • 2
  • Yasushi Inoguchi
    • 3
  1. 1.Dept. of Computer Science, KICTInternational Islamic University Malaysia (IIUM)Kuala LumpurMalaysia
  2. 2.Graduate School of Science and EngineeringYamaguchi UniversityUbeJapan
  3. 3.Research Center for Advanced Computing InfrastructureJapan Advanced Institute of Science and Technology (JAIST)IshikawaJapan

Personalised recommendations