This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Virtual Bus Architecture for Dynamic Parallel Processing
February 1993 (vol. 4 no. 2)
pp. 121-130

To support parallel processing of data-intensive applications, the interconnection networkof a parallel/distributed machine must provide high end-to-end communication bandwidth and handle the bursty and concentrated communication patterns generated by dynamic load balancing and data collection operations. A large-scale interconnection network architecture called a virtual bus is proposed. The virtual bus can scale toterabits-per-second end-to-end communication bandwidth with low queuing delay fornonuniform traffic. A terabit virtual bus architecture can be efficiently implemented forless than 5% of the total cost of an eight-thousand-node system. In addition, the virtualbus has an open system parallel interface that is flexible enough to support up togigabytes per second data transfer rates, different grades of services, and broadcastoperation. Such flexibility makes the virtual bus a plausible open system communicationbackbone for a broad range of applications.

[1] J. Aceves and Pogg, "Computer-based multimedia communication,"IEEE Comput. Mag., pp. 10-11, 1985.
[2] E.A. Arnould et al., "The Design of Nectar: A Network Backplane for Heterogeneous Multicomputers,"Proc. Third Int'l Conf. Architectural Support for Programming Languages and Operating Systems, ACM, New York, 1989, pp. 205-216.
[3] W. C. Athas and C. L. Seitz, " Multicomputers: Message-passing concurrent computers,"IEEE Comput. Mag., pp. 9-24, Aug. 1988.
[4] C. K. Baru and O. Frieder, "Database operations in a cube-connected multicomputer system,"IEEE Trans. Comput., vol. 38, no. 6, June 1989.
[5] P.B. Berra and N.B. Troullinos, "Optical Techniques and Data/ Knowledge Base Machines,"Computer, Vol. 20, No. 10, Oct. 1987, pp. 59-70.
[6] D.R. Cheriton, H.A. Goosen, and P.D. Boyle, "Multi-Level Shared Caching Techniques for Scalability in VMP-MC,"Proc. 16th Int'l Symp. Computer Architecture, CS Press, Los Alamitos, Calif., May 1989, pp. 16-24.
[7] E. Chow, H. S. Madan, J. C. Peterson, D. Grunwald, and D. Reed, "Hyperswitch network for the hypercube computer," inProc. 15th Ann. Int. Symp. Comput. Architecture, 1988, pp. 90-99.
[8] G. Copeland, W. Alexander, E. Boughter, and T. Keller, "Data placement in bubba," inProc. ACM SIGMOD, Chicago, IL, June 1-3, 1988, pp. 99-109.
[9] G. E. Daddis and H. C. Torng, "A taxonomy of broadband integrated switching architecture,"IEEE Commun. Mag., pp. 32-42, May 1989.
[10] C. Days, J. Giacopelli, and J. Hickey. "Applications of self-routing switches to LATA fiber optic networks," inProc. Int. Switching Symp., Phoenix, AZ, Mar. 1987.
[11] S. P. Dandamudi and D. L. Eager "Hierarchical interconnection networks for multicomputer systems,"IEEE Trans. Comput., vol. 39, no. 6, pp. 786-797, June 1990.
[12] D. DeWitt, S. Ghandearizadeh, D. Schneider. R. Jauhari, M. Muralikrishna, and A. Sharma, " A single user evaluation of the GAMMA database machine," inDatabase Machines and Knowledge Base Machines, M. Kitsuregawa and H. Tanaka, Eds. Boston, MA: Kluwer Academic, 1988, pp. 370-386.
[13] K. Y. Eng, "A photonic knockout switch for high speed packet networks,"IEEE J. Select. Areas Commun., vol. 6, no. 7, Aug. 1988.
[14] Technology Trends-Packaging Standard inThe Electronic System Design, May 1089, 26 pp.
[15] E.F. Gehringer, D.P. Siewiorek, and Z. Segall,Parallel Processing: The Cm*Experience, Digital Press, Billerica, Mass., 1987.
[16] J.R. Goodman and P.J. Woest, "The Wisconsin Multicube: A New Large-Scale Cache-Coherent Multiprocessor,"Proc. 15th Int'l Symp. Computer Architecture, CS Press, Los Alamitos, Calif., June 1988, pp. 422-431.
[17] B. T. Hillyer, D. E. Shaw, and A. Nigram, "NON-VON's performance on certain database benchmarks,"IEEE Trans. Software Eng., Apr. 1986.
[18] C. Hoover, W. Harrod, and M. Cohen, "The technology of interconnection,"AT&T Tech. J., vol. 66, no. 4, July/Aug. 1987.
[19] A. Huang and S. Knauer. "Starlite: A wideband digital switch," inProc. Globecom, 1984, pp. 121-125.
[20] R. Johnson. "Multichip modules,"IEEE Spectrum, Mar. 1990.
[21] M. Karol, M.G. Hluchyj, and S.P. Morgan, "Input versus output queueing on a space-division packet switch,"IEEE Trans. Commun., vol. COM-35, Dec. 1987.
[22] L. Kleinrock,Queueing Systems, Vol II. New York: Wiley Interscience, 1976, ch. 5.
[23] B. Charron-Bost, "Combinatorics and Geometry of Consistent Cuts: Application to Concurrency Theory," inDistributed Algorithms, J.-C. Bermond and M. Raynal. eds.,Lecture Notes in Computer Science, Vol. 392, Springer-Verlag, Berlin, 1989.
[24] I. Lee and D. Smitley, "A synthesis algorithm for reconfigurable interconnection networks,"IEEE Trans. Comput., vol. 37, no. 9, June 1988.
[25] K. C. Lee "VLSI accelerator architectures for database systems," Ph.D. dissertation, Elec. Eng., Rutgers Univ., 1990.
[26] B. Lent, "A variable arbiter for resource allocation in asynchronous multiprocessor systems,"Microprocessing and Microprogramming, Euromicro J., vol. 9, 1982.
[27] K. Li, "IVY: A shared virtual memory system for parallel computing," inProc. Int. Conf. Parallel Processing, 1988.
[28] J. K. Muppala and L. N. Bhuyan, "Arbiter designs for multiprocessor interconnection networks."Microprocessing and Microprogramming, Eurimicro J., vol. 26, 1989.
[29] G. F. Pfister, W. C. Brantley, D. A. George, S. L. Harvey, W. J. Kleinfelder, K. P. McAuliffe, E. A. Melton, V. A. Norton, and J. Weiss, "The IBM Research Parallel Processor Prototype (RP3): Introduction and architecture," inProc. Int. Conf. Parallel Processing, 1985, pp. 764-771.
[30] G. Perucca, P. Belforte, E. Garetti, and F. Perardi, "Research on advanced switching techniques for the evolution to ISDN and broadband ISDN,"IEEE J. Select. Areas Commun., vol. SAC-5, no. 8, Oct. 1987.
[31] D. A. Reed and R. M. Fujimoto,Multicomputer Networks, Message-Based Parallel Processing. Cambridge, MA: MIT Press, 1987.
[32] J. Robinson, "Design of concurrency controls for transaction processing systems," Ph.D. dissertation, Dep. of Comput. Sci., Carnegie-Mellon Univ., 1982.
[33] D. M. Taub, "Arbitration and control acquisition scheme for the IEEE 896 Futurebus,"IEEE Micro, vol. 4, no. 4, pp. 28-41, Aug. 1984.
[34] X. Wang and W. S. Luk, "Parallel join algorithms on a network of workstations," inProc. IEEE and ACM Int. Symp. Databases in Parallel and Distributed Systems, Dec. 1988.
[35] M. P. Veechi, H. Kobrinski, E. Goldstein, and R. Bulley, "Wavelength selection with nanosecond switching times using distributed-feedback optical amplifiers," inProc. 14th Euro. Conf. Opt. Commun., Brington, England, Sept. 1988.
[36] M. K. Vernon and U. Manbar, "Distributed round-robin and first-come first-serve protocols and their application to multiprocessor bus arbitration," inProc. 15th Annu. Int. Symp. Comput. Architecture, Honolulu, HI, May 1988, pp. 269-277.
[37] C.L. Wu and T.Y. Feng,Interconnection Networks for Parallel and Distributed Processing, Computer Society Press, Los Alamitos, Calif., Order No. 574, 1984.
[38] Y.S. Yeh, M.G. Hluchyj, and A.S. Acampora, "The Knockout Switch: A Simple, Modular Architecture for High-Performance Packet Switching,"IEEE J. Select. Areas Comm., SAC-5, Vol. 8, Oct. 1987, p. 1274.
[39] A. Urquhart, "Hard examples for resolution,"J. Ass. Comput. Mach., vol. 31, no. 1, pp. 209-219, 1987.
[40] H. Yoon, M. Liu, and K. Lee, "The Knockout Switch under Nonuniform Traffic,"Proc. GlobeCom 88, IEEE Press, Piscataway, N.J., 1988, pp. 1,628-1,634.

Index Terms:
Index Termsvirtual bus architecture; dynamic parallel processing; interconnection network;parallel/distributed machine; end-to-end communication bandwidth; communicationpatterns; dynamic load balancing; data collection operations; queuing delay; nonuniformtraffic; open system parallel interface; open system communication backbone; delays;multiprocessor interconnection networks; network interfaces; open systems; scheduling
Citation:
K.C. Lee, "A Virtual Bus Architecture for Dynamic Parallel Processing," IEEE Transactions on Parallel and Distributed Systems, vol. 4, no. 2, pp. 121-130, Feb. 1993, doi:10.1109/71.207588
Usage of this product signifies your acceptance of the Terms of Use.