| S. Swope and R. Fujimoto, "Optimal Performance of Distributed Simulation Programs" Proceedings of the 1987 Winter Simulation Conference, pages 612-617, December 1987. |
....tagged with its path ID. Parsec supports several conservative simulation protocols, including the following: 1. A null message based scheme (Null) 4] 2. Conditional Event (Cond) 5] 3. Accelerated Null Message (ANM) 9] a combination of the previous two. 4. Ideal Simulation Protocol (ISP) [10,15]. ISP is a performance evaluation tool that measures the parallelism in a model. The experiments compare the performance of these protocols with the modified null message protocol that takes advantage of path lookahead. All of these experiments were run on both an eight processor SPARCserver 1000 ....
S. Swope and R. Fujimoto, "Optimal Performance of Distributed Simulation Programs" Proceedings of the 1987 Winter Simulation Conference, pages 612-617, December 1987.
....and yields a statement on the speed up with limited resources for a given mapping strategy. Oracle log. To get a more realistic estimate on the obtainable speed up, the communication overhead and message latencies should be taken into consideration. This problem is focused by Swope and Fujimoto [31]. They propose a method called oracle log . The oracle log is produced (for a given mapping) by a conventional sequential or parallel simulator. Whenever a signal that crosses partitions changes its value, it will be registered and a log is written to the logfile. Each log consists of the ....
Swope, S. and Fujimoto, R. (1987) Optimal Performance of Distributed Simulation Programs. Proc. of the Winter Simulation Conference, pp. 612 -- 617
....Kernighan Lin [KEL70a] and SOCCER [RUN88a] A simulated annealing based algorithm will be integrated soon. In addition to the results gained from the usual experiments, the parallelism available from our benchmarks [BBK89a] is also examined using the critical path approach [BEJ85a] and oracle lag [SWF87a] to reflect both the ideal speed up and the effects of real communication. Furthermore, we are implementing several variants of Time Warp to be able to faithfully compare conservative and optimistic approaches. To ease the design of new synchronization strategies, all protocol dependent actions ....
Swope, S. and Fujimoto, R. (1987) Optimal Performance of Distributed Simulation Programs, Proc. Winter Simulation Conference, pp. 612--617
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC