Taiwan Semiconductor Manufacturing Comp. Ltd.

Synopsys, Inc.

Geng-He Lin

Tseng Chin Lo

Bo-Sen Chang

Chih-Ting Sun

Molly Chang

Ya-Wen Tseng

Zi-Kuan Li

Charles C Chiang

Hui-Ru Jiang

Yen-Ting Yu

Provided is a method for inserting a pre-designed filler cell, as a replacement to a standard filler cell, including identifying at least one gap among a plurality of functional cells. In some embodiments, a pre-designed filler cell is inserted within the at least one gap. By way of example, the pre-designed filler cell includes a layout design having a pattern associated with a particular failure mode. In various embodiments, a layer is patterned on a semiconductor substrate such that the pattern of the layout design is transferred to the layer on the semiconductor substrate. Thereafter, the patterned layer is inspected using an electron beam (e-beam) inspection process.

Integrated circuit filler and method thereof

A hotspot detection system that classifies a set of hotspot training data into a plurality of hotspot clusters according to their topologies, where the hotspot clusters are associated with different hotspot topologies, and classifies a set of non-hotspot training data into a plurality of non-hotspot clusters according to their topologies, where the non-hotspot clusters are associated with different topologies. The system extracts topological and non-topological critical features from the hotspot clusters and centroids of the non-hotspot clusters. The system also creates a plurality of kernels configured to identify hotspots, where each kernel is constructed using the extracted critical features of the non-hotspot clusters and the extracted critical features from one of the hotspot clusters, and each kernel is configured to identify hotspot topologies different from hotspot topologies that the other kernels are configured to identify.

Lithographic hotspot detection using multiple machine learning kernels

Growing community of inventors

Hsinchu, Taiwan

Geng-He Lin