Automatic Layout Generation with Applications in Machine Learning Engine Evaluation

TL;DR

This paper evaluates the generalization of machine learning-based hotspot detectors on complex, synthetically generated layout patterns, highlighting the need for improved robustness in DFM applications.

Contribution

It introduces an automatic layout generation tool for synthesizing diverse layout patterns and uses it to assess the robustness of existing hotspot detection models.

Findings

ML-based hotspot detectors perform well on known benchmarks

Detection accuracy drops on complex, synthetic layouts

Robustness and generality of models need improvement

Abstract

Machine learning-based lithography hotspot detection has been deeply studied recently, from varies feature extraction techniques to efficient learning models. It has been observed that such machine learning-based frameworks are providing satisfactory metal layer hotspot prediction results on known public metal layer benchmarks. In this work, we seek to evaluate how these machine learning-based hotspot detectors generalize to complicated patterns. We first introduce a automatic layout generation tool that can synthesize varies layout patterns given a set of design rules. The tool currently supports both metal layer and via layer generation. As a case study, we conduct hotspot detection on the generated via layer layouts with representative machine learning-based hotspot detectors, which shows that continuous study on model robustness and generality is necessary to prototype and integrate the learning engines in DFM flows. The source code of the layout generation tool will be available at https://github. com/phdyang007/layout-generation.