Performance analysis of optimistic parallel simulations with limited rolled back events

Abstract

Using the parallel simulation approach is not always the best choice. There are situations in which the sequential approach works better, in terms of simulation effectiveness. Indeed, the optimistic parallel simulation time consists of two basic components: the forward execution time, and the rollback mechanism time-overhead. It is convenient to parallelize a simulation until the latter component is not predominant with respect to the former one. The breakeven point depends on the nature of the model to simulate, on the characteristics of the simulation platform, and on the choice of tuning parameters such as the number of processors and the checkpoint interval. This paper deals with an evaluation of the performances of the sequential and parallel approach, in case the optimistic parallel method is used. An analytical model is introduced to study the sensitivity of the parallel simulation effectiveness to the forward event time, in case each event is rolled back no more than once. The model is first experimentally validated and then used to determine the breakeven point between the parallel and sequential approach.