Performance Evaluation of a Multistage Interconnection Network with Output-Buffered ${\alpha}{\times}{\alpha}$ Switches

출력 버퍼형${\alpha}{\times}{\alpha}$스위치로 구성된 다단 연결망의 성능 분석

  • 신태지 (울산대학교 전기전자정보시스템공학부) ;
  • 양명국 (울산대학교 전기전자정보시스템공학부)
  • Published : 2002.12.01

Abstract

In this paper, a performance evaluation model of the Multistage Interconnection Network(MIN) with the multiple-buffered crossbar switches is Proposed and examined. Buffered switch technique is well known to solve the data collision problem of the MIN. The proposed evaluation model is developed by investigating the transfer patterns of data packets in a switch with output-buffers. The performance of the multiple-buffered${\alpha}{\times}{\alpha}$ crossbar switch is analyzed. Steady state probability concept is used to simplify the analyzing processes, Two important parameters of the network performance, throughput and delay, are then evaluated, To validate the proposed analysis model, the simulation is carried out on a Baseline network that uses the multiple buffered crossbar switches. Less than 2% differences between analysis and simulation results are observed. It is also shown that the network performance is significantly improved when the small number of buffer spaces is given. However, the throughput elevation is getting reduced and network delay becomes increasing as more buffer spaces are added in a switch.

본 논문에서는, ${\alpha}{\times}{\alpha}$ 출력 버퍼 스위치로 구성된 다단 연결 망(Multistage Interconnection Network, MIN)의 성능 예측 모형을 제안하고, 스위치에 장착된 버퍼의 개수 증가에 따른 성능 향상 추이를 분석하였다. Buffered 스위치 기법은 다단 연결 망 내부의 데이타 충들 문제를 효과적으로 해결할 수 있는 방법으로 널리 알려져 있다. 제안한 성능 예측 모형은 먼저 네트웍 내부 임의 스위치 입력 단에 유입되는 데이타 패킷이 스위치 내부에서 전공되는 유형을 확률적으로 분석하여 수립되었다. 제안한 모형은 스위치에 장착된 버퍼의 개수와 무관하게 출력 버퍼를 장착한 ${\alpha}{\times}{\alpha}$스위치의 성능, 즉 네트웍 성능 평가의 두 가지 주요 요소인 네트웍 정상상태 처리율(Normalized Throughput, NT)과 네트웍 지연시간(Network Delay)의 예측이 가능하고, 나아가서 이들로 구성된 모든 종류의 다단 연결 망 성 분석에 적용이 용이하다. 제안한 수학적 성능 분석 연구의 실효성 검증을 위하여 병행된 시뮬레이션 결과는 상호 미세한 오차 범위 내에서 모형의 예측 데이타와 일치하는 곁과를 보며 분석 모형의 타당성을 입증하였다. 또한, 분석 결과 스위치 내부에 많은 버퍼를 장착할수록 정상상태 처리율의 증가율은 감소하고, 네트웍 지연시간은 증가하는 것으로 나타났다.

Keywords

References

  1. Allan Gottlieb, Ralph Grishman, et al, 'The NYU Ultracornputer - Designing an MIMD Shared Memory Parallel Computer,' IEEE Trans. on Computers, Vol. C-32, No.2, pp175-189, Feb. 1983 https://doi.org/10.1109/TC.1983.1676201
  2. G. F. Pfister, W. C. Brantley, et al., 'The IBM Research Parallel processor Prototype(RP3):Introduction and Architecture,' Proc. Intl. Conf. on Parallel Processing, pp764-771, Aug. 1985
  3. G. F. Pfister, W. C. Brantley, et al., 'Butterfly GP1000 - Overview,' BBN Advanced Computer Inc., Nov. 1988
  4. G. F. Pfister, W. C. Brantley, et al., 'TC2000 Technical Product Summary,' BBN Advanced Computer Inc., Jul. 1989
  5. T. Feng, 'Data Manipulating Functions in Parallel Processors and Their Implementations,' IEEE Trans. on Computers, Vol. C-23, pp309-318, Mar. 1974 https://doi.org/10.1109/T-C.1974.223927
  6. K. E. Batcher, 'The Flip Network in STARAN,' Proc. Intl. Conf. on Parallel Processing, pp65-71, Aug. 1976
  7. D. K. Lawrie, 'Access and Alignment of Data in an Array processor,' IEEE Trans. on Computers, Vol. C-24, pp1145-1155, Dec. 1975 https://doi.org/10.1109/T-C.1975.224157
  8. G. J. Lipovski and A. Tripathi, 'A Reconfigurable Varistructure Array Processor,' Proc. Intl. Conf. on Parallel Processing, pp165-174, Aug. 1977
  9. M. Lee, C. L. Wu, 'Performance Analysis of Circuit Switching Baseline Interconnection Networks,' Proc. 11th Computer Architecture Conf., pp82-90, 1984
  10. V. P. Kumar and S. M. Reddy, 'Augmented Shuffle-Exchange Multistage Interconnection Networks,' IEEE Computer, Jun. 1987 https://doi.org/10.1109/MC.1987.1663588
  11. Chuan-Lin Wu and Tse-Yun Feng, 'On a class of Multistage Interconnection Networks,' IEEE Trans. on Computers, Vol. C-29, No.8, pp108-116, Aug. 1980 https://doi.org/10.1109/TC.1980.1675651
  12. D. M. Dias and J. R. Jump, 'Analysis and Simulation of Buffered Delta Networks,' IEEE Trans. on Computers, Vol. C-30, No.4. pp273-282, Apr. 1981 https://doi.org/10.1109/TC.1981.1675775
  13. Y. C. Jeriq, 'Performance Analysis of a Packet Switch Based on Single Buffered Banyan Network,' IEEE J. Select. Areas Comm., Vol. SAC-3, No.6, pp1014-1021, Dec. 1983
  14. C. P. Krusal and M. Snir, 'The Performance of Multistage Interconnection Networks for Multiprocessors,' IEEE Trans. on Computers, Vol. C-32, No. 12. pp1091-1098, Dec. 1983 https://doi.org/10.1109/TC.1983.1676169
  15. H. Yoon, K. Y. Lee, and M. T. Liu, 'Performance Analysis of Multibuffered Packet-Switching Networks in Multiprocessor Systems,' IEEE Trans. on Computers, Vol. C-39, No.3. pp319-327, Mar. 1990 https://doi.org/10.1109/12.48863
  16. Y. Mun and H. Y. Youn, 'Performance Analysis of Finite Buffered Multistage Interconnection Networks,' IEEE Trans. on Computers, Vol. 43, No.2, pp. 153-162, Feb. 1994 https://doi.org/10.1109/12.262120
  17. Chita R. Das and Prasant Mohapatra, 'Performance Analysis of Finite-Buffered Asynchronous Multistage Interconnection Networks,' IEEE Trans. on Parallel and Distributed systems, Vol. 7, NO.1, pp. IS-25, June 1996 https://doi.org/10.1109/71.481594
  18. B. Zhou and M. Atiquzzaman, 'Efficient analysis of multistage interconnection networks using finite output-buffered switching elements,' Tech Rep. 15/94, La Trobe University, Melbourne, Department of Computer Science, July 1994
  19. S. H. Byun, D. K. Sung, 'The UniMlN Switch Architecture for Large-Scale ATM Switches,' IEEE Trans. on Networking, Vol. S, NO.1, pp109-120, Feb. 2000 https://doi.org/10.1109/90.836482
  20. J. Ding and L.N. Bhuyan, 'Finite Buffer Analysis of Multistage Interconnection Networks,' IEEE Trans. on Computers, vol. 43, no. 2, pp.243-247, Feb. 1994 https://doi.org/10.1109/12.262132
  21. H. Y. Youn and H. S. Choo, 'Performance Enhancement of Multistage Interconnection Networks with Unit Step Buffering,' IEEE Trans. on Communications, Vol. 47, No.4. pp.618-630, APR. 1999 https://doi.org/10.1109/26.764935