In previous work we presented an algorithm for cloning parallel simulations that enables multiple simulated execution paths to be explored simultaneously. The method is targeted for parallel discrete event simulators that provide the simulation application developer a logical process (LP) execution model. The cloning algorithm gains efficiency by cloning logical processes only as necessary. In this work we examine the scalability of cloning in detail. Specifically, we examine how the number of clones impacts the performance of cloning as we vary the “size” of the simulation problem.
Maria Hybinette, Richard M. Fujimoto