Dynamic load balancing in parallel discrete event simulation for spatially explicit problems
PADS '98 Proceedings of the twelfth workshop on Parallel and distributed simulation
ROSS: a high-performance, low memory, modular time warp system
PADS '00 Proceedings of the fourteenth workshop on Parallel and distributed simulation
The dependence list in time warp
Proceedings of the fifteenth workshop on Parallel and distributed simulation
Causality representation and cancellation mechanism in time warp simulations
Proceedings of the fifteenth workshop on Parallel and distributed simulation
Systems support for scalable data mining
ACM SIGKDD Explorations Newsletter - Special issue on “Scalable data mining algorithms”
Proceedings of the 32nd conference on Winter simulation
Accelerating Spatially Explicit Simulations of Spread of Lyme Disease
ANSS '05 Proceedings of the 38th annual Symposium on Simulation
| Hi-index | 0.00 |
The efficiency of parallel discrete event simulations that use the optimistic protocol is strongly dependent on the overhead incurred by rollbacks. The paper introduces a novel approach to rollback processing which limits the number of events rolled back as a result of a straggler or antimessage. The method, called breadth-first rollback (BFR), is suitable for spatially explicit problems where the space is discretized and distributed among processes and simulation objects move freely in the space. BFR uses incremental state saving, allowing the recovery of causal relationships between events during rollback. These relationships are then used to determine which events need to be rolled back. The results demonstrate an almost linear speedup-a dramatic improvement over the traditional approach to rollback processing.