Regularized Logistic Regression for Fast Importance Sampling Based SRAM Yield Analysis

Lama Shaer1, Rouwaida Kanj1, Rajiv Joshi2, Maria Malik3, Ali Chehab1
1American University of Beirut, 2IBM, 3George Mason University


In this paper, we propose a fast logistic regression based importance sampling methodology with ordered feature selection to avoid overfitting and enable regularization. We rely on the importance region search simulations to build a regularized logistic regression model that is capable of accurately predicting pass fail criteria for purposes of yield analysis. We also propose a cross-validation-based regularization framework for ordered feature selection. We prove the efficiency of the proposed methodology by analyzing state-of-the-art boosted FinFET SRAM designs. The proposed methodology is comprehensive and computationally efficient resulting in high-fidelity models. We report on average around 4.5% false prediction rate for the importance samples predictions. This translates into accurate yield prediction for the rare fail events. All this comes at significant savings in runtime.