A comparative simulation study of the performance of single-bus and two-bus multiprocessors

Abstract

This paper presents a comparative simulation modeling of the performance of the uniprocessor, single-bus multiprocessor, and two-bus multipro cessor computer systems. The performance indexes of the single-bus and two-bus multiprocessor systems compared to the uniprocessor system, that are used in the modeling, are processor speedup factors S_P1 and S_P2 respectively. A third perfor mance index, Bus-speedup factor, S_B, is derived to compare the performance of the two-bus and single- bus systems. The first two indexes provide measures of the processing speedup improvement of both multiprocessors with respect to the uniprocessor system, while the third index provides a measure of the performance improvement resulting from adding an extra bus to the single- bus multiprocessor system. Three data transfer protocols are considered in this work: First Come First Served (FCFS), Token Ring (TR), and the Priority (PR) Policy. Simulation experiments show that increasing the number of processors in the considered multiprocessor architectures does not necessarily improve the overall performance. Moreover, adding an extra bus to the single- bus architecture provides some speedup improvement that depends on the nature of the task program and the data transfer protocol. Simulation results show that FCFS and TR scheduling policies provide better performance than the PR policy. However, FCFS requires relatively less hardware and software complexity than the TR.

Keywords

performance evaluation multi processor systems simulation modeling benchmarking.

Get full access to this article

View all access options for this article.

References

Bodnar, B. and Liu, A. 1987, "Modeling and Performance Analysis of Single-bus Tightly- Coupled Multiprocessor," IEEE Transactions on computers, Vol. C-38, No. 3, 464-470.

Civera, P. , Conte, G. , Gregoretti, F. , and Corso, D. 1985, Multiprocessor Systems for Real- Time Applications, D. Reidel Publishing Company, Amsterdam.

Caci 1988, Network II.5 User's Manual, Version 3.1, CACI Products Company, Los Angeles.

Heidelberger, P. , and Lavenberg, S. 1984, "Computer Performance Evaluation Methodology," IEEE Transactions on Computers, Vol. C-33, No. 12,108-130.

Hwang, K. , and Briggs, F. 1984, Computer Architecture and Parallel Processing, McGraw- Hill, New York.

Irani, K. and Onyuksel, I. 1984, "A Closed-Form Solution for the Performance Analysis of Multiple-Bus Multiprocessor Systems," IEEE Transactions on Computers, Vol. C-33, No.11,1004-1012.

Marsan, M.A. , Balbo, G. , and Conte, G. 1984, "Comparative Performance Analysis of Single Bus Multiprocessor Architectures," IEEE Transaction on Computers, Vol. C-31, No. 12, 1179-1191.

Marsan, M.A. , and Gerla, M. 1982, "Markov Models for Multiple Bus Multiprocessor Systems ," IEEE Transaction on Computers, Vol. C-31, No. 3, 239-248.

Obaidat, M.S. 1990, "Simulation of Queuing Models in Computer Systems", Queueing Systems and Computer Applications, S. Qzekici , Ed. Hemisphere publishing New York, pp. 111-151.

10.

Obaidat, M.S. , et al., 1987 "A Modular Multiprocessor System for Image Processing," Proc. of the IEEE Phoenix Conference on Computers and Communications, 518-523.

11.

Obaidat, M.S. 1989, "Performance Evaluation of the IMPS Multiprocessor System ," Journal of Computers & Electrical Engineering, Vol. 15, No. 3/4, Dec. 1989, pp. 121-130.

12.

Obaidat, M.S. , and Radaideh, M. 1990. "Performance Models for the Bus-Oriented Multiprocessor Computer System," Proceedings of the SCS Summer Computer Simulation Conference, 153-158.

13.

Woodbury, M.H. 1986, "Performance Modeling and Measurement of Real-Time Multiprocessors with Time-Shared Buses," Proc. of the IEEE Real-time Systems Symposium, 109-118.