DOI QR코드

DOI QR Code

Biased Multistage Inter connection Network in Multiprocessor System

다중프로세서 시스템에서 편향된 다단계 상호연결망

  • Choi, Chang-Hoon (School of Computer Information, Kyungpook National University)
  • 최창훈 (경북대학교 컴퓨터정보학부)
  • Received : 2011.02.15
  • Accepted : 2011.04.07
  • Published : 2011.04.30

Abstract

There has been a lot of researches to develop techniques that provide redundant paths, there by making Multistage Interconnection Networks(MINs) fault tolerant. So far, the redundant paths in MINs have been realized by adding additional hardware such as extra stages or duplicated data links. This paper presents a new MIN topology called Hierarchical MIN. The proposed MIN is constructed with 2.5N-4 switching elements, which are much fewer than that of the classical MINs. Even though there are fewer hardware than the classical MINs, the HMIN possesses the property of full access and also provides alternative paths for the fault tolerant. Furthermore, since there is the short cut in HMIN for the localized communication, it takes advantage of exploiting the locality of reference in multiprocessor systems. Its performance under varying degrees of localized communication is analysed and simulated.

다단계 상호 연결망(MIN)에 중복 경로를 제공하여 오류를 허용하는 기술을 개발하기 위하여 많은 연구가 진행되어 왔다. 지금까지 MIN에서 중복 경로는 추가된 stage와 중복된 데이터 경로 같은 추가 적인 하드웨어를 첨가함으로써 실현되었다. 본 논문은 계층적 MIN이라는 새로운 위상의 MIN을 제안한다. 제안된 MIN은 기존의 MIN보다 적은 2.5N-4개의 스위칭소자를 사용하여 구성되었다. 비록 기존의 MIN 보다 적은 하드웨어를 사용할지라도 완전 접근 성질을 가지고 있으며, 또한 오류 허용을 위한 선택적 중복 경로를 제공한다. 더욱이 HMIN에서는 지역화된 통신을 위한 지름길이 제공되어 다중 프로세서 시스템에서 지역 참조성을 활용하는 장점을 갖게 된다. 지역참조성의 정도를 변화시키며 제안된 시스템의 성능을 분석하였으며 모의실험을 수행하였다.

Keywords

References

  1. G. B. Adams, D. P. Agrawal, and H.J. Siegel, "A Survey and Comparison of Fault-Tolerant Multistage Interconnection Networks", IEEE Computer, vol. 20, pp. 14-27, June, 1987.
  2. B. D. Alleyne and I. D. Scherson, "Expanded Delta Networks for Large Parallel Computers'', in Proc. Int'l Conf. on Parallel Processing, vol. I., pp. 127-131, 1992.
  3. K.V. Arya and R. K. Ghosh, "Designing a New Class of Fault Tolerant Multistage Interconnection Networks", Journal of Interconnection Networks, Vol. 6, No. 4, pp.361-382, 2005. https://doi.org/10.1142/S0219265905001472
  4. R.J. Baron and L. Higbie, Computer Architecture Case Studies, Addison-Wesley Pub., 1992.
  5. C.M. Chiang, S. Bhattacharya, and L.M. Li, "Multicast in Extra-Stage Multistage Interconnection Networks'', in Proc. the 6th IEEE Symp. on Parallel and Distributed Processing, pp.452-459, Oct., 1994.
  6. T. Y. Chung and D. P. Agrawal, "Cost - Performance Trade - off in Manhattan Street Network versus 2-D Torus", in Proc. IEEE Int'l Conf. on Parallel Processing'', pp. 169-172, Aug., 1990.
  7. A.L. Decegama, The Technology of Parallel Processing : Parallel Processing Architectures and VLSI hardware volume I, Prentice-Hall International Editions, 1989.
  8. C.C. Fan and J. Bruck, "Tolerating Fault Interconnection Networks with Minimal Extra states", IEEE Transactions on Computers, 49(9), pp. 998-1004, 2000. https://doi.org/10.1109/12.869334
  9. C.S. Ferner and K.Y. Lee, "Hyperbanyan Networks: A New Class of Networks for Distributed-Memory Multiprocessor", in Proc. the Fourth Symp. on the Frontiers of Massively Parallel Computation, pp.254-261, Oct., 1992.
  10. J.R. Goodman and C.H. Sequin, "Hypertree: A Multiprocessor Interconnection Topology", IEEE Trans. on Compt., vol. C-30, pp.923-93., Dec., 1981. https://doi.org/10.1109/TC.1981.1675731
  11. A. Gottlieb, R. Grishman, et al., "The NYU Ultacomputer Designing a MIMD Shared Memory Parallel Computer", IEEE Trans. on Computers, Vol. C-32, No.2, pp.175-189, Feb. 1983. https://doi.org/10.1109/TC.1983.1676201
  12. T. Hanawa, H. Amano, and Y. Fusikawa, "Multistage Interconnection Networks with Multiple Outlets", in Proc. Int'l Conf. on Parallel Processing, vol. I, pp. 1-8, 1994.
  13. K. Hwang, Advanced Computer Architecture : Parallelism Scalability Programmability, McGraw-Hill International Editions, 1993.
  14. Nitin, S. Garhwal and N. Srivastava, "Designing a Fault-tolerant Fully-Chained Combining Switches Multi-stage Interconnection Network with Disjoint Paths", The Journal of Supercomputing, Vol. 55, No. 3, pp. 400-431, 2011. https://doi.org/10.1007/s11227-009-0336-z
  15. K. Padmanabhan and D.H. Lawrie, "A Class of Redundant Path Multistage Interconnection Networks'', IEEE Trans. Compt., vol. C-32, pp. 1099-1108, Dec., 1983. https://doi.org/10.1109/TC.1983.1676170
  16. J.H. Patel, "Performance of Processor-Memory Interconnections for Multiprocessors" IEEE Trans. on Compt., vol. C-30, pp.771-780, Oct., 1981. https://doi.org/10.1109/TC.1981.1675695
  17. M. C. Pease, "The Indirect binary n-cube microprocessor array", IEEE Trans. Comt., vol. 26, pp. 458-473, May, 1977. https://doi.org/10.1109/TC.1977.1674863
  18. G. F. Pfister and W. C. Brantley, et al., "The IBM Research Parallel Processor Prototype(RP3): Introduction and Architecture", Proc. Int'l. Conf. on Parallel Processing, pp.767-771, Aug., 1985.
  19. G. F. Pfister and W. C. "Butterfly GP1000 Overview", BBN Advanced Computer Inc., Nov., 1988.
  20. G. F. Pfister and W. C. "TC2000 Technical Product Summary", BBN Advanced Computer Inc., Jul., 1989.
  21. C. Schack, W. Heenes and R. Hoffmann, "A Multiprocessor Architecture with an Omega Network for the Massively Parallel Model GCA", Lecture Notes in Computer Science, Vol. 5657, pp. 98-107, 2009. https://doi.org/10.1007/978-3-642-03138-0_11
  22. S.R. Shankar and L. Jenkins, "The extra stage fault tolerant technique for self-routing permutation networks", Proc. FTS 1st Int'l. Conf. on Fault Tolerant Systems, 1995.
  23. H.J. Siegel, Interconnection Networks for Large-scale Parallel Processing, Lexington books, 1985.
  24. T.H. Szymanski, "On the universality of Multipath Multistage Interconnection Networks'', J. Parallel and Distributed Computing, vol.7, pp.541-569, 1989. https://doi.org/10.1016/0743-7315(89)90035-X