ACM Transactions on Programming Languages and Systems (TOPLAS)
Rollback sometimes works...if filtered
WSC '89 Proceedings of the 21st conference on Winter simulation
PADS '93 Proceedings of the seventh workshop on Parallel and distributed simulation
The MIMDIX environment for parallel simulation
Journal of Parallel and Distributed Computing - Special issue on parallel and discrete event simulation
Effects of the checkpoint interval on time and space in time warp
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Scheduling time warp processes using adaptive control techniques
WSC '94 Proceedings of the 26th conference on Winter simulation
Service oriented scheduling in Time Warp
WSC '94 Proceedings of the 26th conference on Winter simulation
Probabilistic adaptive direct optimism control in Time Warp
PADS '95 Proceedings of the ninth workshop on Parallel and distributed simulation
A probabilistic event scheduling policy for optimistic parallel discrete event simulation
PADS '98 Proceedings of the twelfth workshop on Parallel and distributed simulation
ACM Transactions on Modeling and Computer Simulation (TOMACS) - Special issue on modeling and analysis of stochastic systems
Summary cache: a scalable wide-area Web cache sharing protocol
Proceedings of the ACM SIGCOMM '98 conference on Applications, technologies, architectures, and protocols for computer communication
A spectrum of options for parallel simulation
WSC '88 Proceedings of the 20th conference on Winter simulation
Grain sensitive event scheduling in time warp parallel discrete event simulation
PADS '00 Proceedings of the fourteenth workshop on Parallel and distributed simulation
Estimating rollback overhead for optimism control in Time Warp
SS '95 Proceedings of the 28th Annual Simulation Symposium
A State-Based Scheduling Algorithm for Time Warp Synchronization
SS '00 Proceedings of the 33rd Annual Simulation Symposium
Hi-index | 0.00 |
The Time Warp synchronization protocol for parallel discrete event simulation is characterized by aggressiveness and risk. The former property refers to greediness in the execution of unsafe events. The latter one refers to greediness in the notication of new events produced by aggressive event execution. Both these properties are potential sources for rollback occurrence/spreading. In this paper we present a scheduling algorithm for the selection of the next LP to be run on a processor which tends to keep low the joint impact of these two properties on the experienced amount of rollback. Reduction of negative effects of aggressiveness and risk is achieved by giving higher priority to the LPs whose next event has low probability to be undone due to rollback and has low fan-out that is, notifies few new events. Our algorithm differs from most previous solutions in that they miss a direct control on the effects due to risk. These solutions could originate poor performance for applications with high variance of the number of new events notified which is an indicator of the risk associated with event execution.