Data-Efficient Prediction of Minimum Operating Voltage via Inter- and Intra-Wafer Variation Alignment

TL;DR

This paper introduces a data-efficient method called restricted bias alignment (RBA) for predicting minimum operating voltage of chips, effectively accounting for wafer-to-wafer and wafer zone-to-zone variations to improve accuracy and reliability.

Contribution

The paper presents a novel variation alignment technique that models inter- and intra-wafer variations simultaneously, using class probe data for the first time in $V_{min}$ prediction.

Findings

RBA improves prediction accuracy on industrial datasets.

The method enhances data efficiency in $V_{min}$ estimation.

Empirical results demonstrate robustness against process variations.

Abstract

Predicting the minimum operating voltage ($V_{min}$) of chips stands as a crucial technique in enhancing the speed and reliability of manufacturing testing flow. However, existing $V_{min}$ prediction methods often overlook various sources of variations in both training and deployment phases. Notably, the neglect of wafer zone-to-zone (intra-wafer) variations and wafer-to-wafer (inter-wafer) variations, compounded by process variations, diminishes the accuracy, data efficiency, and reliability of $V_{min}$ predictors. To address this gap, we introduce a novel data-efficient $V_{min}$ prediction flow, termed restricted bias alignment (RBA), which incorporates a novel variation alignment technique. Our approach concurrently estimates inter- and intra-wafer variations. Furthermore, we propose utilizing class probe data to model inter-wafer variations for the first time. We empirically demonstrate RBA's effectiveness and data efficiency on an industrial 16nm automotive chip dataset.