Refine
Document Type
- Conference proceeding (2) (remove)
Language
- English (2)
Has full text
- no (2) (remove)
Is part of the Bibliography
- yes (2)
Institute
- Technik (2)
Publisher
Lithographical hotspot (LH) detection using deep learning (DL) has received much attention in the recent years. It happens mainly due to the facts the DL approach leads to a better accuracy over the traditional, state-of-the-art programming approaches. The purpose of ths study is to compare existing data augmentation (DA) techniques for the integrated circuit (IC) mask data using DL methods. DA is a method which refers to the process of creating new samples similar to the training set, thereby helping to reduce the gap between classes as well as improving the performance of the DL system. Experimental results suggest that the DA methods increase overall DL models performance for the hotspot detection tasks.
The limited interfaces of today's IC design environments for editing PCell parameters hinder a solid advancement towards more complex analog PCell modules. This paper presents Hierarchical Instance Parameter Editing (HIPE), a highly flexible concept for the customization of PCell sub-instances. Introducing a new type of parameter, HIPE facilitates the dynamic creation of multi-level editing forms reflecting the actual contents of a PCell instance. This approach greatly improves a PCell's ease-of-use, substantially simplifies PCell development, and allows for a hierarchical execution of parameter validation callbacks. Our HIPE implementation has been integrated into a professional PCell development tool and represents a key enabling technology for upcoming generations of high-level hierarchical PCells.