TY - GEN
T1 - Parallel discrete-event simulation of FCFS stochastic queueing networks
AU - Nicol, David M.
N1 - Funding Information:
*This research was supported in part by the National Aeronautics and Space Administration under NASA contract NASl-18107 while the author consulted at ICASE, Mail Stop 132C, NASA Langley Research Center, Hampton, VA 23665.
Publisher Copyright:
© 1988 ACM.
PY - 1988/1/1
Y1 - 1988/1/1
N2 - Physical systems are inherently parallel; intuition suggests that simulations of these systems may be amenable to parallel execution. The parallel execution of a discrete-event simulation requires careful synchronization of processes in order to ensure the execution's correctness; this synchronization can degrade performance. Largely negative results were recently reported in a study which used a well-known synchronization method on queueing network simulations. In this paper we discuss a synchronization method, appointments, which has proven itself to be effective on simulations of FCFS queueing networks. The key concept behind appointments is the provision of lookahead. Lookahead is a prediction on a processor's future behavior, based on an analysis of the processor's simulation state. We show how lookahead can be computed for FCFS queueing network simulations, give performance data that demonstrates the method's effectiveness under moderate to heavy loads, and discuss performance trade-offs between the quality of lookahead, and the cost of computing lookahead.
AB - Physical systems are inherently parallel; intuition suggests that simulations of these systems may be amenable to parallel execution. The parallel execution of a discrete-event simulation requires careful synchronization of processes in order to ensure the execution's correctness; this synchronization can degrade performance. Largely negative results were recently reported in a study which used a well-known synchronization method on queueing network simulations. In this paper we discuss a synchronization method, appointments, which has proven itself to be effective on simulations of FCFS queueing networks. The key concept behind appointments is the provision of lookahead. Lookahead is a prediction on a processor's future behavior, based on an analysis of the processor's simulation state. We show how lookahead can be computed for FCFS queueing network simulations, give performance data that demonstrates the method's effectiveness under moderate to heavy loads, and discuss performance trade-offs between the quality of lookahead, and the cost of computing lookahead.
UR - http://www.scopus.com/inward/record.url?scp=84894195391&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84894195391&partnerID=8YFLogxK
U2 - 10.1145/62115.62128
DO - 10.1145/62115.62128
M3 - Conference contribution
AN - SCOPUS:84894195391
T3 - Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP
SP - 124
EP - 137
BT - Proceedings of the ACM/SIGPLAN Conference on Parallel Programming
A2 - Wexelblat, Richard L.
PB - Association for Computing Machinery
T2 - 1988 ACM/SIGPLAN Conference on Parallel Programming: Experience with Applications, Languages and Systems, PPEALS 1988
Y2 - 19 July 1988 through 21 July 1988
ER -