Efficient hierarchical performance modeling for analog and mixed-signal circuits via Bayesian co-learning

With the continuous drive toward integrated circuits scaling, efficient performance modeling is becoming more crucial yet more challenging. In this paper, we propose a novel method of hierarchical performance modeling based on Bayesian co-learning. We exploit the hierarchical structure of a circuit to establish a Bayesian framework where unlabeled data samples are generated to improve modeling accuracy without running additional simulation. Consequently, our proposed method only requires a small number of labeled samples, along with a large number of unlabeled samples obtained at almost no-cost, to accurately learn a performance model. Our numerical experiments demonstrate that the proposed approach achieves up to 3.6 × runtime speed-up over the state-of-the-art modeling technique without surrendering any accuracy.

Duke Scholars

Author Xin Li Electrical and Computer Engineering