Concurrent gate-level circuit simulation

Abstract

In the last several years, parallel computing on multicore processors has transformed from a niche discipline relegated primarily to scientific computing into a standard component of highperformance personal computers. At the same time, simulating processors prior to manufacture has become increasingly time-consuming due to the increasing number of gates on a single chip. However, writing parallel programs in a way that significantly improves performance can be a difficult task. In this thesis, I outline principles that must be considered when running good gate-level circuit simulations in parallel. I also analyze a test circuit's performance in order to quantitatively demonstrate the benefit of considering these principles in advance of running simulations.