Performance comparable design of efficient synchronization protocols for distributed simulation

A large number of variations of distributed simulation protocols have been proposed in the literature. Their performances, however, could not be compared directly, due to different implementation strategies, different optimizations and different software environments as well as parallel hardware platforms. To rank the protocols accurate enough with respect to their execution performance the only practical evaluation, consists in implementing different alternatives and measure their relative performance on significant test cases. In this paper we demonstrate the possibility of simultaneous implementation of the three substantially different protocols starting from a single program skeleton. A clear separation of the simulation part and the synchronisation part of the protocols and reuse of code for more than one variant are the key concepts.<
>