Synopsys, Inc.

Hsiang-Wen Chang

Yao-Wen Chang

Yang-Ming Chen

Ping-Wei Huang

A method, a system, and non-transitory computer readable medium for power and ground (P/G) routing for an integrated circuit (IC) design are provided. The method includes generating input features for a machine-learning (ML) model based on IR drop and routing congestion analysis for a P/G network for the IC design, and modifying a set of P/G vias or a set of P/G wires in the P/G network according to modifications identified by the ML model. The ML model comprises a feature extractor pre-trained using a plurality of images of P/G vias and P/G wires.

Machine-learning-based power/ground (P/G) via removal

A method and system for guided power grid augmentation determines a minimum resistance path for cells within an integrated circuit (IC) design. The minimum resistance path traces a conducting wire connecting a pin of a cell to an IC tap within the IC design. A voltage drop value for each of the cells is determined so as to identify target cells having a voltage drop value that satisfies a voltage drop criteria. Polygons have defined size characteristics are defined around the minimum resistance paths of the target cells, and conductors, such as additional conductors, are generated within the defined polygons.

Growing community of inventors

Taipei, Taiwan

Hsiang-Wen Chang