LITHOGRAPHY HOTSPOT DETECTION USING VISION TRANSFORMER

Abstract

In the process of IC design, lithography can be defined as the process of reprinting the pattern of mask on Silicon wafer. Lithography is one of the most important steps in the process as it enables Moore’s law to be satisfied, for this feature size needs to be decreased every couple of years. This continuous decrease in feature size may lead to printability issues and hence hotspots. Presence of hotspots can lead to complete failure of the circuit, so it is very important to detect these hotspots with high accuracy. Previously various simulation, machine leaning and deep learning based techniques have been implemented to solve this problem. In this work, we propose a method to identify hotspots using Vision Transformers. Along with this, we also use other deep learning techniques such as CNNs and ANNs for comparison purposes. ViTs give an overall accuracy of 98.05% which is 1.39% higher than accuracy of CNNs and 2.04% better accuracy of ANNs. Although the ViTs prove the best in terms of overall accuracy, but at sub-dataset level its performance can be improved. Two out of five sub-datasets have accuracy slightly above 95% and for rest three it is above 99%. In future, we wish to improve accuracy for these two sub-datasets by improving our model and reducing imbalance in the sub-datasets.