The Time Warp distributed simulation algorithm uses checkpointing to save process states after certain event executions for later recovery at the time of a rollback. Two main techniques have been used for checkpointing: periodic state saving and incremental state saving. The former technique introduces large overheads in reconstructing a desired state by coasting forward from an earlier checkpointed state if the computational granularity is large. The latter technique also has large overheads in applications with large rollback distances. A hybrid checkpointing technique is proposed which uses both periodic and incremental state saving simultaneously in such a way that it reduces checkpointing time overheads. A detailed analytical model is developed for the hybrid technique, and comparisons are made using similar analytical models with periodic and incremental state saving techniques. Results show that when the system parameters are chosen to represent large and complex simulated systems, the hybrid approach has less checkpointing time overhead than the other two techniques.

The aggressive adaptive-risk (AAR) approach is an efficient clustered and adaptive approach for parallel simulation which provides optimistic logical processes the ability to adjust their degree of risk at run time, based on observed behavior. The AAR approach is implemented on a network of workstations. Performance results using large synthetic loads are reported and compared to those obtained for the time warp optimistic technique.

An efficient adaptive approach for parallel and distributed simulation (PADS) is formalized and implemented. The aggressive adaptive-risk (AAR) approach aims at reducing cascading rollbacks in large and complex simulations by clustering optimistic logical processes on each processor, and providing these processes the ability to adjust their degree of risk, at run time, to a good operating point based on observed behavior. The AAR approach is used to develop the Clustered Adaptive Distributed Simulator (CADS), which is implemented on a network of workstations. Details of the CADS implementation are described. Performance results for large synthetic loads are reported and compared to those obtained for the Time Warp optimistic technique.

A review of the state of the art in parallel and distributed simulation (PADS) is given. Sample performance results of currently used PADS techniques are presented using a network of workstations. The results demonstrate the capabilities and limitations of these techniques, and verify the logic of the current directions in PADS research.