Algorithmic scalability in globally constrained conservative parallel discrete event simulations of asynchronous systems

TL;DR

This paper introduces a moving window global constraint in parallel discrete event simulations of asynchronous systems, which improves scalability by bounding the virtual time horizon and optimizing processor utilization.

Contribution

It proposes a novel moving window constraint that ensures both scalability of the measurement phase and control over virtual time fluctuations in parallel simulations.

Findings

The constraint eliminates extreme virtual time fluctuations.

It bounds the width of the virtual time horizon.

It allows tuning for optimal processor utilization.

Abstract

We consider parallel simulations for asynchronous systems employing L processing elements that are arranged on a ring. Processors communicate only among the nearest neighbors and advance their local simulated time only if it is guaranteed that this does not violate causality. In simulations with no constraints, in the infinite L-limit the utilization scales (Korniss et al, PRL 84, 2000); but, the width of the virtual time horizon diverges (i.e., the measurement phase of the algorithm does not scale). In this work, we introduce a moving window global constraint, which modifies the algorithm so that the measurement phase scales as well. We present results of systematic studies in which the system size (i.e., L and the volume load per processor) as well as the constraint are varied. The constraint eliminates the extreme fluctuations in the virtual time horizon, provides a bound on its width, and controls the average progress rate. The width of the window constraint can serve as a tuning parameter that, for a given volume load per processor, could be adjusted to optimize the utilization so as to maximize the efficiency. This result may find numerous applications in modeling the evolution of general spatially extended short-range interacting systems with asynchronous dynamics, including dynamic Monte Carlo studies.