Proceedings of Symposium on Parallel and Distributed Tools (1996)
May 22, 1996 to May 24, 1996
Samir R. Das , Division of Computer Science, The University of Texas at San Antonio
Over-optimistic execution has long been identified as a major performance bottleneck in Time Warp based parallel simulation systems. An appropriate throttle or control of optimism can improve performance by reducing the number of rollbacks. However, the design of an appropriate throttle is a difficult task, as correct computations on the critical path may be blocked, thus increasing the overall execution time. In this paper we build a cost model for throttled execution that involves both rollback probability and probability for an event computation being on the critical path. The model can estimate an appropriate size of time window for a throttled execution using statistics collected from the purely optimistic execution. The model is validated by an experimental study with a set of synthetic workloads.
discrete event simulation, parallel simulation, time warp, performance model
S. R. Das, "Estimating the Cost of Throttled Execution in Time Warp," Proceedings of Symposium on Parallel and Distributed Tools(PADS), Philadelphia, PA, 1996, pp. 0186.