Improving Lookahead in Parallel Multiprocessor Simulation Using Dynamic Execution Path Prediction

Simulation performance is dominated by lookahead in null message-based conservative time management of parallel discrete event simulation (PDES). This paper proposes a scheme for software execution path prediction to extend lookahead in parallel multiprocessor simulation. Templates for predicting program execution path are generated by software analysis, then, a processor model gets lookaheads by evaluating the templates at simulation time. We reduced the amount of null messages by a factor of 10 to 50 in parallel simulation with eight clustered workstations and, as a result, achieved a speedup factor of 4 to 7 compared to a conventional method having constant lookahead.