Floyd B. Hanson
Laboratory for Advanced Computing
Annotated Publications in Performance Evaluation
55. F. B. Hanson, J.-D. Mei, C. Tier and H. H. Xu,
PDAC: A Data Parallel Algorithm for the Performance Analysis of
Closed Queueing Networks , Parallel Computing, vol. 19,
pp. 1345-1358, December 1993.
This paper was presented at the 5th SIAM Conference on Parallel Processing
for Scientific Computing, Houston, TX, Mar. 1991. 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.
May 08, 1996