公开(公告)号：US20230195986A1

公开(公告)日：2023-06-22

申请号：US18010131

申请日：2022-03-09

Applicant: SOUTHEAST UNIVERSITY

Inventor： Peng CAO ,  Kai WANG ,  Tai YANG ,  Wei BAO

IPC: G06F30/367 ,  G06N3/0442 ,  G06N3/045 ,  G06N3/0464

CPC classification number: G06F30/367 ,  G06N3/0442 ,  G06N3/045 ,  G06N3/0464 ,  G06F2119/12

Abstract: Disclosed in the present invention is a method for predicting a delay at multiple corners for a digital integrated circuit, which is applicable to the problem of timing signoff at multiple corners. In the aspect of feature engineering, a path delay relationship at adjacent corners is extracted by using a dilated convolutional neural network (Dilated CNN), and learning is performed by using a bi-directional long short-term memory model (Bi-directional Long Short-Term Memory, BLSTM) to obtain topology information of a path. Finally, prediction results of a path delay at a plurality of corners are obtained by using an output of a multi-gate mixture-of-experts network model (Multi-gate Mixture-of-Experts, MMoE). Compared with a conventional machine learning method, the present invention can achieve prediction with higher precision through more effective feature engineering processing in a case of low simulation overheads, and is of great significance for timing signoff at multiple corners of a digital integrated circuit.