Advertisement

Scalable Optical Interconnection Networks for Large-Scale Parallel Computers

  • Ahmed Louri
  • Brent Weech
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 468)

Abstract

A new scalable interconnection topology called the Spanning Multichannel Linked Hypercube (SMLH) is proposed along with an optical implementation methodology that combines both the advantages of free space optics with those of wavelength division multiplexing techniques. The SMLH uses the hypercube topology as a basic building block and connects such building blocks using two-dimensional multichannel links (similar to spanning buses). In doing so, the SMLH combines positive features of both the hypercube (small diameter, high connectivity, symmetry, simple routing, and fault tolerance) and the spanning bus hypercube (SBH) (constant node degree, scalability, and ease of physical implementation), while at the same time circumventing their disadvantages. The SMLH topology supports many communication patterns found in different classes of computation, such as bus-based, mesh-based, and tree-based problems as well as hypercube-based problems. A very attractive feature of the SMLH network is its ability to support a large number of processors with the possibility of maintaining a constant degree and a constant diameter. Other positive features include symmetry, incremental scalability, and fault-tolerance. It is shown that the SMLH network provides better average message distance, average traffic density, and queueing delay than many similar networks, including the binary hypercube, the SBH, etc. Additionally, the SMLH has comparable performance to other high-performance hypercubic networks, including the Generalized Hypercube and the Hypermesh.

Keywords

Parallel Computing Interconnection Network Wavelength Assignment Free Space Optic Optical Interconnection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    D.P. Agrawl, C. Chen, and J. R. Burke. A comparison of hybrid graph based topologies. In E. F. Gehringer, editor, IEEE Computer Society Techinal Committee on Computer Architecture Newsletter, pages 5–8, Winter 1994–95.Google Scholar
  2. [2]
    L. N. Bhuyan and D. P. Agrawal. Generalized Hypercube and Hyper-bus Structures Constructing Massively Parallel Computers. IEEE Trans. Computers, C-33:323–333, 1984.Google Scholar
  3. [3]
    C. Chen, D. P. Agrawal, and J. R. Burke. dBCube: A New Class of Hierarchical Multiprocessor Interconnection Networks with Area Efficient Layout. IEEE Trans. Parallel and Distributed Systems, 4:1332–1344, Jan. 1993.CrossRefGoogle Scholar
  4. [4]
    D. M. Chiarulli, S. P. Levitan, R. G. Mehlen, M. Bidnurkar, R. Ditmore, G. Gravenstreter, Z. Guo, C. Qiao, M. F. Sakr, and J. P. Teza. Optoelectronic Buses for High-Performance Computing. Proc. of the IEEE, 82(11):1701–1710, Nov 1994.CrossRefGoogle Scholar
  5. [5]
    A. Cisneros and C. A. Brackett. A large ATM switch Based on Memory Switches and Optical Star Couplers. IEEE J. Selected Areas in Communications, 9:1348–1360, Oct. 1991.CrossRefGoogle Scholar
  6. [6]
    P. W. Dowd. Wavelength Division Multiple Access Channel Hypercube Processor Interconnection. IEEE Trans. on Computers, 41:1223–1241, Oct 1992.CrossRefGoogle Scholar
  7. [7]
    S.A. Felperin, L. Gravano, G.D. Pifarre, and J.L.C. Sanz. Fully-adaptive routing: Packet switching performance and wormhole algorithms. In Supercomputing’ 91 Proceedings, pages 654–663, 1991.Google Scholar
  8. [8]
    E. Ganesan and D. K. Pradhan. The Hyper-deBruijn Networks: Scalable Versatile Architecture. IEEE Trans. on Parallel and Distributed Systems, 4:962–978, Sep 1993.CrossRefGoogle Scholar
  9. [9]
    K. Ghose and K. R. Desai. Hierarchical Cubic Networks. IEEE Trans. on Computers, 6:427–435, Apr. 1995.Google Scholar
  10. [10]
    J. R. Goodman and C. H. Sequin. Hypertree: a Multiprocessor Interconnection Topology. IEEE Trans. on Computers, C-30:923–933, 1981.Google Scholar
  11. [11]
    K. Hwang. Advanced Computer Architecture: Parallelism, Scalability, Programmability. McGraw-Hill, New York, NY, 1993.Google Scholar
  12. [12]
    D. Israel, R. Baets, M. J. Goodwin, N. Shaw, M. D. Salik, and C. J. Groves-Kirkby. Comparison of Different Polymetric Multimode Star Couplers for Backplane Optical Interconnect. IEEE J. Lightwave Technology, 13:1057–64, June 1995.CrossRefGoogle Scholar
  13. [13]
    J. Kim and C. R. Das. Hypercube Communication Delay with Wormhole Routing. IEEE Trans. on Computers, 43:806–814, July 1994.MATHCrossRefGoogle Scholar
  14. [14]
    L. Klienrock. Queueing Systems: Vol. II, Computer Applications. Wiley, New York, NY, 1976.Google Scholar
  15. [15]
    V. Kumar, A. Grama, A. Gupta, and G. Karypis. Introduction to Parallel Computing: Design and Analysis of Algorithms. Benjamin/Cummings Publishing Co., New York, NY, 1994.MATHGoogle Scholar
  16. [16]
    G. Lerman and L. Rudolph. Parallel Evolution of Parallel Processors. Plenum Press, New York, 1993.Google Scholar
  17. [17]
    Y. Li, A. W. Lohmann, and S. B. Rao. Free-space Optical Mesh-connected Bus Networks Using Wavelength-division Mutiple Access. Applied Optics, 32:6425–6437, 1993.Google Scholar
  18. [18]
    A. Louri and S. Furlonge. Feasibility Study of a Scalable Optical Inter-connection Network for Massively Parallel Processing Systems. Applied Optics, 35:1296–1308, Mar. 1996.Google Scholar
  19. [19]
    A. Louri, S. Furlonge, and C. Neocleous. Experimental Demonstration of the Optical Multi-Mesh Hypercube: A Scalable Interconnection Network for Multiprocessors and Multicomputers. Applied Optics, 35:6909–6920, Dec 1996.Google Scholar
  20. [20]
    A. Louri and H. Sung. Efficient Implementation Methodology for Three-dimensional Space-invariant Hypercube-based Free-space Optical Inter-connection Networks. Applied Optics, 32:7200–7209, Dec. 1993.Google Scholar
  21. [21]
    A. Louri and H. Sung. 3D Optical Interconnects for High-Speed Interchip and Interboard Communications. Computer, 27:27–37, Oct. 1994.CrossRefGoogle Scholar
  22. [22]
    A. Louri and H. Sung. A Scalable Optical Hypercube-based Interconnection Network for Massively Parallel Computing. Applied Optics, 33:7588–7598, Nov. 1994.Google Scholar
  23. [23]
    A. Louri and H. Sung. An Optical Multi-Mesh Hypercube: A Scalable Optical Interconnection Network for Massively Parallel Computing. IEEE J. Lightwave Technology, 12:704–716, Apr. 1994.CrossRefGoogle Scholar
  24. [24]
    Q. M. Malluhi and M. A. Bayoumi. The Hierarchical Hypercube: A New Interconnection Topology for Massively Parallel Systems. IEEE Trans. Parallel and Distributed Systems, 5:17–30, Jan. 1994.CrossRefMathSciNetGoogle Scholar
  25. [25]
    A. D. McAulay. Optical Computer Architectures: the Application of Optical Concepts to Next Generation Computers. Wiley, New York, NY, 1991.Google Scholar
  26. [26]
    B. D. Metcalf and J. F. Providakes. High-capacity Wavelength Demultiplexer with a Large-diameter GRIN Rod Lens. Applied Optics, 21:794–796, 1982.CrossRefGoogle Scholar
  27. [27]
    R. A. Morgan. Advances in vertical cavity surface emitting lasers. Proc. of the SPIE, 2147:97–119, 1994.CrossRefGoogle Scholar
  28. [28]
    T. V. Moui. Receiver design for high-speed optical fiber systems. IEEE J. Lightwave Technology, pages 243–267, 1984.Google Scholar
  29. [29]
    P. F. Moulton. Tunable Solid State Lasers. Proc. of the IEEE, 80:348–364, Mar. 1992.CrossRefGoogle Scholar
  30. [30]
    L. M. Ni and P. K. McKinley. A Survey of Wormhole Routing Techniques in Direct Networks. Computer, 26:62–76, Feb. 1993.CrossRefGoogle Scholar
  31. [31]
    S. Ohring and S.K. Das. Folded Petersen Cube Networks: New Competitors for the Hypercubes. IEEE Trans. Parallel and Distributed Systems, 7:151–168, Feb. 1996.CrossRefGoogle Scholar
  32. [32]
    F. P Preparata and J. Vuillemin. The cube-connected cycles: a versatile network parallel computation. Communications of the ACM, 24:300–309, May 1981.CrossRefMathSciNetGoogle Scholar
  33. [33]
    D. A. Reed and R. M. Fujimoto. Multicomputer Networks: Message-Based Parallel Processing. MIT Press, Cambridge, MA, 1987.Google Scholar
  34. [34]
    Youcef Saad and Martin H. Schultz. Topological Properties of Hypercubes. IEEE Trans. on Computers, 37:867–872, July 1988.CrossRefGoogle Scholar
  35. [35]
    N. K. Shankaranarayanan, U. Koren, B. Glance, and G. Wright. Two-section DBR laser transmitters with accurate channel spacing and fast arbitrary-sequence tuning for FDMA networks. In Technical Digest of Fiber Optical Communication., pages 36–7. Washington, DC: Optical Society of America, 1994.Google Scholar
  36. [36]
    H. J. Siegel. Interconnection Networks for Large-scale Parallel Processing. McGraw-Hill, New York, NY, 1990.Google Scholar
  37. [37]
    H. S. Stone and J. Cocke. Computer Architecture in the 1990s. Computer, pages 30–38, Sep. 1991.Google Scholar
  38. [38]
    P. Sweazey. Limits of performance of backplane buses. In Digital Bus Handbook. New York: McGraw-Hill, 1990.Google Scholar
  39. [39]
    T. Szymanski. Hypermeshes: Optical Interconnection Networks for Parallel Computing. J. Parallel and Distribted Computing, 26:1–23, 1995.MATHCrossRefGoogle Scholar
  40. [40]
    A. Takai, T. Kato, S. Yamashita, S. Hanatani, Y. Motegi, K. Ito, H. Abe, and H. Kodera. 200 — Mb/s/ch 100m Optical Subsystem Interconnections Using 8-channel 1.3μ Laser Diode Arrays and Single-Mode Fiber Arrays. IEEE J. Lightwave Technology, 12:260–269, Feb 1994.CrossRefGoogle Scholar
  41. [41]
    F. N Tinofeev, P. Bayvel, J. E. Midwinter, and M. N. Sokolskii. High-Performance, free-space ruled concave grating demultiplexer. Electronics Letters, 31:2200–1, Dec 1995.CrossRefGoogle Scholar
  42. [42]
    F. N Tinofeev, P. Bayvel, J. E. Midwinter, M. N. Sokolskii, E. G Churin, and A. Stavdas. Free-Space aberration-corrected grating demultiplexer for application in densely-spaced, subnanometer wavelength-routed optical networks. Electronics Letters, 31:1368–70, Aug 1995.CrossRefGoogle Scholar
  43. [43]
    L. D. Wittie. Communication Structures for Large Networks of Microcomputers. IEEE Trans. on Computers, C-30:264–273, Apr. 1981.Google Scholar

Copyright information

© Kluwer Academic Publishers 1998

Authors and Affiliations

  • Ahmed Louri
    • 1
  • Brent Weech
    • 1
  1. 1.Department of Electrical and Computer EngineeringUniversity of ArizonaTucson

Personalised recommendations