Scalable Parallelization of Harmonic Balance Simulation

A new approach to parallelizing harmonic balance simulation is presented. The technique leverages circuit substructure to expose potential parallelism in the form of a directed, acyclic graph (dag) of computations. This dag is then allocated and scheduled using various linear clustering techniques. The result is a highly scalable and efcient approach to harmonic balance simulation. Two large examples, one from the integrated circuit regime and another from the communication regime, executed on three di erent parallel computers are used to demonstrate the e cacy of the approach.