Stephen G. Eick
Albert G. Greenberg
Abstract
Synchronous relaxation, a new, general-purpose, efficient method for parallel simulation, is proposed. The method is applied to obtain a new parallel algorithm for simulating large circuit-switched communication networks. To show that synchronous-relaxation method is efficient, we present the results of circuit-switched network simulation experiments, and analytic approximations derived from a mathematical model of the simulation method.
- ASH, G R., CARDWELL, R., AND MURRAY, R.P. 1984. Design and optimization of networks with dynamic routing. Bell Syst. Tech. J. 63 (Sept.), 1261-1281Google Scholar
- ASH. G. R., KAFKER, A H., AND KRISHNAN, K. R. 1981. Servicing and real-time control of networks with dynamic routing. Bell Syst. Tech. J. 60 (Oct.), 1787 1820Google Scholar
- BECKMAN, B., D~ LORENTO, M., STURDEVANT, K., HONTALES, P., VAN WARREN L., BLUME, L., JEFFERSON, D., AND BELLENOT, S. 1988. Distributed simulation and time warp. Part I: Design of colliding pucks. In Proceedings of the 1988 SCS Multtconference. Stmul. Ser. SCS 19, 3, 56-60.Google Scholar
- CHANDY, K. M., AND SHERMAN, B. 1989. Space-time and simulation. In Proceedings of the 1989 SCS Multtconference. Stmul. Ser. SCS 21, 2, 53-57.Google Scholar
- CHUNG, M. J., AND CHUNG, Y. 1990. An experimental analysis of simulation clock advancement in parallel logic simulation on a SIMD machine. In Proceedings of the 1990 SCS Multtconference. Simul. Set. SCS 23, 1, 133 140.Google Scholar
- EICK, S. G., GREENBERG, A. G., LUBACHEVSKY, B. D., AND WEISS, A. 1991. Synchronous relaxation for parallel simulations with applications to circmt-switched networks. In Proceedtngs of the 1991 SCS Multlconference. Szmul. Ser. SCS 23, 1, 151-162.Google Scholar
- FUJtMOTO, R.M. 1990. Parallel discrete event driven simulation. Commun ACM 33, 10 (Oct.), 31 53. Google Scholar
- FUJIMOTO, R. M. 1988. Performance measurements of distributed simulation strategies. In Proceedtngs of the 1988 SCS Multzconference. Simul. Ser. SCS 19, 3, 14 20.Google Scholar
- GIBBENS, R.J. 1988. Dynamic routing in circuit-switched networks: The dynamic alternative routing strategy. Ph.D. thesis. Univ. of Cambridge, Cambridge, Mass.Google Scholar
- GmBENS, R. J., AND KELLY, F.P. 1990. Dynamic routing in fully connected networks. IMA. J. Math. Contr. Inf. 7, 77 111.Google Scholar
- GREENBERG, A., LUBACHEVStC/, B., AND MITRANI, I. 1990. Unboundedly parallel simulations via recurrence relations. In Proceedtngs of 1990 SIGMETRICS. ACM, New York, 1-12. To appear in ACM Trans. Comput. Syst. Google Scholar
- JEFFERSON, D.R. 1985. Virtual time. ACM Trans. Program. Lang. Syst 7, 3 (July), 404 425 Google Scholar
- KEY, P. B., AND COPE, A. 1990. Distributed dynamic routing schemes. IEEE Commun. Mag. 28, 10 (Oct.), 54 64.Google Scholar
- KOLCHIN, V. F., SEVAST'YANOV, B. A., AND CHmTYAKOV, V.P. 1978. Random Allocations. V. H. Winston & Sons, Washington, D.C.Google Scholar
- LUBACHEVSKY, B. D. 1990. Simulating colliding rigid disks in parallel using bounded lag without time warp. In Proceedings of the 1990 SCS Multwonference. Simul. Ser. SCS 22, 1/2, 194 202.Google Scholar
- LUBACHEVSKY, B. D. 1989. Efficient distributed event-driven simulation of multiple-loop networks. Commun. ACM 32, i (Jan.), 111 131. Google Scholar
- LUBACHEVSKY, B.D. 1988. Almost linear speed-up of d~stributed event simulations. In Proceedtngs of the 2nd Sympostum on the Frontters of Massively Parallel Computatwn. IEEE Computer Society, Washington, D.C.Google Scholar
- MITRA, D, AND GIBBENS, R.J. 1990. State-dependent routing on symmetric loss networks w~th trunk reservations' Analysm, asymptotms, optimal design. AT & T Bell Laboratories, Tech. Memo.Google Scholar
- NICOL, D.M. 1988. Parallel discrete-event simulation of FCFS stochasm queuing networks In Proceedings of the ACM SIGPLAN Symposium on Parallel Programming Experzence m Applications, Languages, and Systems ACM, New York, 124-137. Google Scholar
- THINKING MACHINES CORP 1989. Connection Machine, Model CM-2, Technical SuTr~rnary, Versmn 5.1. Thinking Machines Corporation, Cambridge, MassGoogle Scholar
- WAGNER, D. B., AND LAZOWSKA, E.D. 1989. Parallel simulation of queuemg networks: Limitations and potenhals. In Proceeding.~ of 1989 SIGMETRICS. ACM, New York, 146-155 Google Scholar
Index Terms
- Synchronous relaxation for parallel simulations with applications to circuit-switched networks
Recommendations
Superfast parallel discrete event simulations
Nonconventional parallel simulations methods are presented, wherein speed-ups are not limited by the number of simulated components. The methods capitalize on Chandy and Sherman's space-time relaxation paradigm, and incorporate fast algorithms for ...
Synchronous relaxation for parallel Ising spin simulations
PADS '01: Proceedings of the fifteenth workshop on Parallel and distributed simulationA new parallel algorithm for simulating Ising spin systems is presented. The sequential prototype is the n-fold way algorithm [2], which is efficient but is hard to parallelize using conservative methods. Our parallel algorithm is optimistic. Unlike ...
Good news for parallel wireless network simulations
MSWiM '09: Proceedings of the 12th ACM international conference on Modeling, analysis and simulation of wireless and mobile systemsWe present a parallel discrete-event simulation method for wireless networks such as mobile ad-hoc networks, mesh networks, or sensor networks. Our method combines new ideas with established approaches and gains considerable speedups over sequential ...
Reviews
Mihail Sadeanu
The authors propose synchronous relaxation (SR) as an efficient general-purpose tool to obtain a new parallel algorithm for large circuit-switched communication network simulation (LCSCNS). They compare the efficiency of the simulation results of LCSCNS experiments with that of an analytic approximate analysis from a large mathematical model. Applied to LCSCNS, the SR method processes large numbers of calls in parallel on a single-instruction multiple-data (SIMD) or multiple-instruction multiple-data (MIMD) computer on which all the processing elements execute the same instruction. The simulation method proceeds in a time-stepped fashion, with a relaxation iterative method applied to process the events at each time step. The system is partitioned into subsystems, and each processing element hosts the simulation of a subsystem. The algorithm belongs to a large class of SR optimistic approaches. The network considered for simulation has N nodes representing the large circuit-switched communication network switches and L= N N-1 2 links between nodes, with every link consisting of a fixed number of trunks. The proportionate routing policy is simulated. Gaining insight into dataflows in SR, the authors consider an oblivious version of proportionate routing for a detailed simple event-coupling model. The model is both randomized and worst-case, with stochastic assumptions about the placement of events and about the behavior of the relaxation algorithm on these events. The focus is on the speed of the algorithm. Insight is given into a mini-rollback or mini-backtrack SR algorithm in which a processing element processes a bounded number of events at each iteration. It seems that the SR method could be implemented efficiently on SIMD computers for large circuit-switched communication network s under a policy of queueing network simulations, with infinite buffer queues.
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments