Methodology for Biasing Random Simulation for Rapid Coverage of Corner Cases in AMS Designs

TL;DR

This paper introduces two innovative methods, frequency domain analysis and Bayesian optimization, to efficiently explore corner cases in AMS circuit design, significantly reducing simulation time and improving coverage.

Contribution

It presents novel biasing techniques for random simulation that guide the search towards critical corner cases in analog and mixed signal circuits.

Findings

Effective identification of corner cases in AMS circuits

Reduction in simulation time for coverage analysis

Successful application on industrial and benchmark circuits

Abstract

Exploring the limits of an Analog and Mixed Signal (AMS) circuit by driving appropriate inputs has been a serious challenge to the industry. Doing an exhaustive search of the entire input state space is a time-consuming exercise and the returns to efforts ratio is quite low. In order to meet time-to-market requirements, often suboptimal coverage results of an integrated circuit (IC) are leveraged. Additionally, no standards have been defined which can be used to identify a target in the continuous state space of analog domain such that the searching algorithm can be guided with some heuristics. In this report, we elaborate on two approaches for tackling this challenge - one is based on frequency domain analysis of the circuit, while the other applies the concept of Bayesian optimization. We have also presented our results by applying the two approaches on an industrial LDO and a few AMS benchmark circuits.