Path Delay Variation Prediction Model with Machine Learning

TL;DR: Two machine learning-based models are proposed by limited SPICE simulations for artificial paths including back propagation (BP) and random forest (RF) regression that can be employed to solve the issue of path delay variation prediction under the unknown corners.

Abstract: Path delay variation becomes a serious concern in advanced technology, especially at low supply voltage. Plenty of timing analysis methods have been proposed based on the characterized timing library, which neglects the correlation among multiple corners, resulting in high characterization effort for all required corners. In this paper, two machine learning-based models are proposed by limited SPICE simulations for artificial paths including back propagation (BP) and random forest (RF) regression. They can be employed to solve the issue of path delay variation prediction under the unknown corners which have not been characterized during the establishment the proposed models. Experimental results show that both models outperform the traditional AOCV method with higher accuracy for the prediction of path delay variation under multiple corners.