Data Centers

Know Thy Simulation Model: Analyzing Event Interactions for Probabilistic Synchronization in Parallel Simulations

Date Added: Mar 2012
Format: PDF

Efficiently scheduling and synchronizing parallel event execution constitutes the fundamental challenge in parallel discrete event simulation. Existing synchronization algorithms typically do not analyze event interactions within the simulation model - mainly to minimize runtime overhead and complexity. However, the authors argue that disregarding event interactions results in a lack of insight into the behavior of the simulation model, thereby severely limiting synchronization efficiency and thus parallel performance. In this paper, they present a probabilistic synchronization scheme that obtains extensive knowledge of the simulation behavior at runtime to guide event execution.