Approximated Rollbacks
Authors/Creators
- 1. Tor Vergata University of Rome
- 2. Sapienza University of Rome
Description
A rollback operation in a speculative parallel discrete event simulator has historically targeted the perfect reconstruction of the state to be restored after a timestamp order violation. This imposes that the rollback support entails specific capabilities and consequently pays given costs. In this article we propose {\em approximate rollbacks}, which allow a simulation object to perfectly realign its virtual time to the timestamp of the state to be restored, but lead the state value to be an approximation of what it should really be. The advantage is an important reduction of the cost for managing the state restore task in a rollback phase, as well as for managing the activities (i.e. state saving) that actually enable rollbacks to be executed. Our proposal is suited for stochastic simulations, and explores a tradeoff between the statistical representativeness of the outcime of the simulation run and the execution performance. We provide mechanisms that enable the application programmer to control this tradeoff, as well as simulation-platform level mechanisms that constitute the basis for managing approximate rollbacks in general simulation scenarions. A study on the aforementioned tradeoff is also presented.
Files
Files
(81.8 MB)
| Name | Size | |
|---|---|---|
|
md5:f8ae285b8c5d1a681e73c19502fbf42f
|
81.8 MB | Download |