This Article 
 Bibliographic References 
 Add to: 
Performance Analysis of Cluster-Based Multiprocessors
January 1994 (vol. 43 no. 1)
pp. 109-114

A queueing model for performance evaluation of cluster-based multiprocessors is proposed. Most system components are modeled as M/D/1/L queues to capture deterministic service time and finite buffer behavior. Various subsystems are analyzed independently and then integrated for the system level analysis. Average delay, throughput, and processor utilization are the performance parameters studied in this analysis. The analytical results are first validated via simulation. Next, several design alternatives are discussed using the model. These include the effect of buffer length and identification of bottleneck centers for various design configurations.

[1] J. Koniceket al., "The organization of the cedar system," inProc. Int. Conf. Parallel Processing, Aug. 1991, pp. 49-56.
[2] E. F. Gehringer, A. K. Jones, and Z. Z. Segall, "The CM*testbed,"IEEE Comput. Mag., pp. 40-53, Oct. 1982.
[3] D. Lenoskiet al., "The Stanford DASH multiprocessor,"IEEE Comput. Mag., pp. 63-79, Mar. 1992.
[4] W.T. Hsu and P.-C. Yew, "The performance of hierarchical systems with wiring constraints," inProc. Inf. Conf. Parallel Processing, Aug. 1991, pp. I-9-I-16.
[5] S.P. Dandamudi and D.L. Eager, "Hierarchical interconnection networks for multicomputer systems,"IEEE Trans. Comput., pp. 786-797, June 1990.
[6] L. N. Bhuyan, Q. Yang, and D. P. Agrawal, "Performance of multiprocessor interconnection networks,"IEEE Comput. Mag., pp. 25-37, Feb. 1989.
[7] C.P. Kruskal and M. Snir, "The performance of multistage interconnection networks for multiprocessors,"IEEE Trans. Comput., pp. 1091-1098, Dec. 1983.
[8] H. Jiang and L. N. Bhuyan, "MVAMIN: Mean value analysis algorithms for Multistage Interconnection Networks,"J. Parallel Distributed Comput., vol. 12, pp. 189-201, 1991.
[9] T. Lin and L. Kleinrock, "Performance analysis of finite-buffered multistage interconnection networks with a general traffic pattern," inProc. ACM SIGMETRICS Conf. Meas. Model. Comput. Syst., May 1991, pp. 68-78.
[10] D. M. Dias and J. R. Jump, "Analysis and simulation of buffered delta network,"IEEE Trans. Comput., pp. 273-282, Aug. 1981.
[11] T. N. Mudge and B.A. Makrucki, "An approximate queueing model for packet switched multistage interconnection networks," inProc. Int. Conf. Dstrib. Comput. Syst., Oct. 1982, pp. 556-562.
[12] R.O. Onvural, "Survey of closed queueing networks with blocking,"ACM Comput. Surveys, pp. 83-121, June 1990.
[13] P. Mohapatra and C. R. Das, "Performance analysis of finite-buffered multistage interconnection networks,"Comput. Eng. Tech. Rep., TR-92- 99, Pennsylvania State Univ., 1992.
[14] T. N. Mudge and B. A. Makrucki, "A queueing model for delta networks," SEL Rep. 159, Dept. Elect.&Comput. Eng., Univ. of Michigan, Jan. 1982.

Index Terms:
multiprocessing systems; performance evaluation; queueing theory; buffer storage; simulation; multiprocessor interconnection networks; cluster-based multiprocessors; performance analysis; queueing model; M/D/1/L queues; deterministic service time; finite buffer behavior; subsystems; system level analysis; average delay; throughput; processor utilization; simulation; results validation; design alternatives; buffer length; bottleneck centre identification; design configurations; decomposition technique; interconnection network.
P. Mohapatra, C.R. Das, Tse-yun Feng, "Performance Analysis of Cluster-Based Multiprocessors," IEEE Transactions on Computers, vol. 43, no. 1, pp. 109-114, Jan. 1994, doi:10.1109/12.250615
Usage of this product signifies your acceptance of the Terms of Use.