PDAC: A Data Parallel Algorithm for the Performance Analysis of Closed Queueing Networks

Abstract A parallel distribution analysis by chain algorithm (PDAC) is presented for the performance analysis of closed, multiple class queueing networks. The PDAC algorithm uses data parallel computation of the summation indices needed to compute the joint queue length probabilities. The computational cost of the PDAC algorithm is shown to be of polynomial order with a lower degree than the cost of the serial implementation of the DAC algorithm. Examples are presented comparing the PDAC algorithm with the DAC algorithm to illustrate its advantages and limitations.

[1]  S. Lennart Johnsson,et al.  A dataparallel implementation of an explicit method for the three-dimensional compressible Navier-Stokes equations , 1990, Parallel Comput..

[2]  Jagdish J. Modi,et al.  Parallel algorithms and matrix computation , 1988 .

[3]  Stephen S. Lavenberg,et al.  Computer Performance Modeling Handbook , 1983, Int. CMG Conference.

[4]  K. Mani Chandy,et al.  Computational algorithms for product form queueing networks , 1980 .

[5]  Nicolas D. Georganas,et al.  RECAL - A New Efficient Algorithm for the Exact Analysis of Multiple-Chain Closed Queueing Networks , 1985, SIGMETRICS.

[6]  Albert G. Greenberg,et al.  Solution of closed, product form, queueing networks via the RECAL and tree-RECAL methods on a shared memory multiprocessor , 1989, SIGMETRICS '89.

[7]  Stephen S. Lavenberg,et al.  Calculating joint queue-length distributions in product-form queuing networks , 1988, JACM.

[8]  Oliver A. McBryan,et al.  The Connection Machine: PDE solution on 65536 processors , 1988, Parallel Comput..

[9]  Jeffrey P. Buzen,et al.  Computational algorithms for closed queueing networks with exponential servers , 1973, Commun. ACM.

[10]  S. Lennart Johnsson,et al.  The Finite Element Method on a Data Parallel Computing System , 1989, Int. J. High Speed Comput..

[11]  Guy E. Blelloch,et al.  Vector Models for Data-Parallel Computing , 1990 .

[12]  Nicolas D. Georganas,et al.  RECAL—a new efficient algorithm for the exact analysis of multiple-chain closed queuing networks , 1986, JACM.

[13]  K. Mani Chandy,et al.  Open, Closed, and Mixed Networks of Queues with Different Classes of Customers , 1975, JACM.

[14]  Stephen S. Lavenberg,et al.  Mean-Value Analysis of Closed Multichain Queuing Networks , 1980, JACM.

[15]  Albert G. Greenberg,et al.  Massively Parallel Algorithms for Network Partition Functions , 1991, ICPP.

[16]  L. W. Tucker,et al.  Architecture and applications of the Connection Machine , 1988, Computer.

[17]  Stephen S. Lavenberg,et al.  Mean Value Analysis by Chain of Product Form Queueing Networks , 1989, IEEE Trans. Computers.