Dependency preserving probabilistic modeling of switching activity using Bayesian networks

We propose a new switching probability model for combinational circuits using a logic-induced-directed-acyclic-graph (LIDBG) and prove that such a graph corresponds to a Bayesian network guaranteed to map all the dependencies inherent in the circuit. This switching activity can be estimated by capturing complex dependencies (spatiotemporal and conditional) among signals efficiently by local message-passing based on the Bayesian networks. Switching activity estimation of ISCAS and MCNC circuits with random input streams yield high accuracy (average mean error=0.002) and low computational time (average time=3.93 seconds).