🤖 AI Summary
This work addresses the significant challenge posed by bias temperature instability (BTI) and random process–voltage (PV) variations to digital circuit reliability in deep-nanometer CMOS technologies, where conventional analysis methods suffer from high computational cost and poor scalability. To overcome these limitations, the paper proposes a novel gate-level delay distribution prediction framework that uniquely integrates random forest regression with Bayesian optimization. By leveraging offline training on Monte Carlo simulation data—bypassing time-consuming atomic parameter extraction—and employing Bayesian optimization for automated hyperparameter tuning, the approach achieves substantially improved accuracy and efficiency. Experimental validation on ISCAS85 benchmark circuits demonstrates a 94.54% reduction in analysis time compared to the state-of-the-art method, with an average prediction error of only 1.63%.
📝 Abstract
As CMOS technology scales into the deep nanometer regime, digital circuit reliability is increasingly threatened by the combined stochastic effects of Bias Temperature Instability (BTI) and Process Variation (PV). Traditional reliability analysis methods, which rely on computationally intensive simulations or extensive lookup tables, fail to scale efficiently for large designs, creating a critical bottleneck in design space exploration. To address this, we propose SMART, a novel framework that integrates Machine Learning (ML) with Monte Carlo simulation to enable rapid, high-fidelity reliability analysis. SMART employs Random Forest regression to predict gate delay distributions directly, bypassing time-consuming atomic model parameter extractions. Crucially, the model utilizes Bayesian Optimization for automated hyperparameter tuning, ensuring maximum predictive robustness across diverse libraries. Experimental validation on ISCAS85 benchmark circuits demonstrates that SMART achieves a 94.54% reduction in analysis time compared to state-of-the-art methods, while maintaining a remarkable average accuracy error of just 1.63%. By shifting computational complexity to an offline training phase, the proposed framework offers a scalable, accurate solution for designing resilient, reliability-aware digital systems.