Abstract
This article advocates the use of a formal framework for analyzing simulation performance. Simulation performance is characterized based on the three simulation development process boundaries: physical system, simulation model, and simulator implementation. First, the authors formalize simulation event ordering using partially ordered set theory. A simulator implements a simulation event ordering and incurs implementation overheads when enforcing event ordering at runtime. Second, they apply their formalism to extract and formalize the simulation event orderings of both sequential and parallel simulations. Third, they propose the relation stricter and a measure called strictness for comparing and quantifying the degree of event dependency of simulation event orderings, respectively. In contrast to the event parallelism measure, strictness is independent of time.
Keywords
Get full access to this article
View all access options for this article.
