Efcient Performance Analysis of Asynchronous Systems Based on Periodicity

This paper presents an efcient method for the performance anal-ysis and optimization of asynchronous systems. An asynchronous system is modeled as a marked graph with probabilistic delay dis-tributions. We show that these systems exhibit inherent periodic behaviors. Based on this property, we derive an algorithm to con-struct the state space of the system through composition and cap-ture the time evolution of the states into a periodic Markov chain. The system is solved for important performance metrics such as the distribution of input arrival time at a component, which is use-ful for subsequent system optimization, as well as relative compo-nent utilization, system latency and throughput. We also present a tool to demonstrate the feasibility of this method. Initial experi-mental results are promising, showing over three orders of magni-tude improvement in runtime and nearly two orders of magnitude decrease in the size of the state space over previously published results. While the focus of this paper is on asynchronous digital systems, our technique can be applied to other concurrent systems that exhibit global asynchronous behavior, such as GALS and em-bedded systems