Efficient Approximation of Performance Spaces for Analog Circuits via Multi-Objective Optimization

This paper presents an adaptation of the well-known normal boundary intersection (NBI) method for approximating complete feasible performance spaces of analog integrated circuits. Those spaces provide accurate information about all feasible combinations of competing performance parameters in a circuit. While the NBI-method is originally designed for computing the so-called Pareto front of a multi-objective optimization problem only, it can be adapted for approximating the complete performance space with some modifications. A scalarization into single-objective optimization problems is performed within our developed tool, which can be connected to any Spice-based simulator. Besides presenting the algorithm and its adaptations, the focus lies on investigating parallelization techniques and their effect on decreasing the computational time. Numerical experiments show the computed approximations of two- and three-dimensional performance spaces of several OTAs and compare the efficiencies of different parallelization schemes.