Testing the Speed-up of Parallel Discrete Event Simulation in Heterogeneous Execution Environments

This paper deals with the experimental testing and verification of the earlier proposed load balancing and coupling factor criteria for the conservative parallel discrete event simulation in heterogeneous execution environments whether they can ensure a good speed-up. The definition of the relative speed-up is extended to the heterogeneous systems in a natural way. This definition is used to measure the efficiency of the parallel simulation executed by heterogeneous systems. A closed queueing network is used as the simulation model, and it is executed on different heterogeneous test systems. Among several scenarios, it is demonstrated on the example of a heterogeneous system containing 87 CPU cores of 5 different types that a good speed-up can be achieved using the load balancing and coupling factor criteria. It is shown that the extension of the definition of the relative speed-up to the heterogeneous systems made it easy to judge the speed-up of parallel discrete event simulation in heterogeneous execution environments.