Processor Allocation In Parallel Battlefield Simulation

Load balancing is a critical issue for exploiting the parallelism in any application and, particularly, in battlefield simulation where the computational load dynamically changes with both time and space. Domain decomposition is an effective means to balance the load distribution in battlefield simulation. However, finer domain decompositions that lead to better load balance incur heavier communication overhead. Earlier attempts in parallelizing battlefield sinlulation have traded load balance in favor of low con~-munication overhead. In this paper, we present three parallel battlefield simulators, implemented on Intel\u27s iPSC/2 and BBN Butterfly GP-1OOO multicomputers, with finer domain decomposition and address the communication overhead problem by processor allocation strategies that suit the underlying architecture of the machine, On the shared-memory BBN Butterfly, the strategy leads to a new parallel battlefield simulation with dynamic load balancing. Execution times of these simulators are provided, which show that the communication overhead is tolerable