A parallel approach of interest management in exascale simulation systems

Abstract

Interest management in parallel/distributed simulation is a filtering technique which is designed to reduce bandwidth consumption of data communication and therefore enhances the scalability of the system. This technique usually involves a process called "interest matching", which determines what data should be sent to the participants as well as what data should be filtered. However, existing interest matching algorithms are mainly designed for serial processing which is supposed to be ruu oil a single processor. As the problem size grows, these algorithms may not, be scalable since the single processor may eventually become a bottleneck. In this research, a parallel approach of interest matching is developed, which is suitable to apply 011 exascale parallel/distributed simulation systems.