On the Evolution of Time Horizons in Parallel and Grid Simulations

TL;DR

This paper introduces a novel approach to parallel discrete event simulations by associating local simulation times with nodes and reducing inter-processor communication, enhancing efficiency and scalability.

Contribution

It proposes a new method that associates local simulation times with nodes and minimizes boundary communication, improving processor utilization and memory exchange efficiency.

Findings

Maintains high processor utilization during simulation

Reduces memory exchange time compared to message passing

Scales effectively with increasing number of nodes

Abstract

We analyze the evolution of the local simulation times (LST) in Parallel Discrete Event Simulations. The new ingredients introduced are i) we associate the LST with the nodes and not with the processing elements, and 2) we propose to minimize the exchange of information between different processing elements by freezing the LST on the boundaries between processing elements for some time of processing and then releasing them by a wide-stream memory exchange between processing elements. Highlights of our approach are i) it keeps the highest level of processor time utilization during the algorithm evolution, ii) it takes a reasonable time for the memory exchange excluding the time-consuming and complicated process of message exchange between processors, and iii) the communication between processors is decoupled from the calculations performed on a processor. The effectiveness of our algorithm grows with the number of nodes (or threads). This algorithm should be applicable for any parallel simulation with short-range interactions, including parallel or grid simulations of partial differential equations.