Design Automation of CMOS Op-Amps Using Statistical Geometric Programming

Abstract

This work proposes a novel design automation (DA) technique that uses a multifaceted approach combining Multivariate Regression with Geometric Programming (GP) to design analog circuits. Previous DA methods employing GP have typically used analytical derivations of the various design equations representing an analog circuit. The proposed DA method eliminates the need for analytical derivations by using simulation data and multivariate regression to generate statistical models combined with GP to solve these statistical expressions with respect to optimum circuit design parameters. This presented statistical GP method has been applied to successfully design a five-transistor two-stage operational amplifier and a folded cascode amplifier in a TSMC 65nm CMOS technology. The presented statistical GP DA results are comparable to the design results obtained from both analytical GP and manual design by an experienced analog design engineer.