There is a consistent dependence between integrated circuits (ICs) performance parameters and manufacturing process variations and capturing it at an early development phase represents a major ongoing topic in the semiconductor industry. Typically, this is addressed by the means of Monte Carlo (MC) simulations, where the device model parameters are randomly instantiated according to the technology variations based on a predefined nominal process. Thus, the resulted simulation data can only capture the effect of these variations. This offers little or no insight on the performance’s sensitivities to specific process variations or on the effect of altered statistical technology properties, as it may be the case of process drift or fab-to-fab migration. This article proposes a methodology for modeling the dependency of the device performances (i.e., electrical parameters—EPs) with the influential technology parameters (i.e., process control monitor parameters—PCMs), at an early stage (preSilicon). Using a set of standard MC co-simulations of PCM structures and the circuit schematics (to maintain consistent process variation), it employs a feature selection step to choose the influential PCMs and it trains a machine learning regression algorithm. Both are wrapped up in a Bayesian optimization (BO) framework to find the optimal feature set and the regression hyperparameters. The obtained regression model can explain the functional dependency of the EP on the influential PCMs. Thus, it directly enables sensitivity analysis (SA) to process variation and parametric yield prediction of the IC, as it will be illustrated for the case of an experimental Infineon Technologies product.
The modern electronic systems have become very complex with a high number of potential factors that may affect the systems' behavior. Sensitivity analysis may be employed to simplify the analysis of such systems and identify the most important factors upfront. The paper introduces two new sensitivity analysis methods based on the measure of entropy, which overcome the limitation of several state-of-the-art methods imposing a specific design of experiments and a high computational cost, measured as the number of simulations (measurements) needed, for the sensitivity analysis. Their performance is compared to other methods based on variance decomposition and One-Factor-at-a-Time screening. The proposed methods named the Entropy Simple method and the Entropy Pair one are applied on a set of custom functions and an E-Bike application. They proved to have comparable accuracy to the state-of-the-art methods with the advantage of a lower computational cost and which does not increase with the number of factors.