Machine Learning based Optical Proximity Correction Techniques

The shrinking of the size of the advanced technological nodes brings up new challenges to the semiconductor manufacturing community.The optical proximity correction(OPC)is invented to reduce the errors of the lithographic process.The conventional OPC techniques rely on the empirical models and optimization methods of iterative type.Both the accuracy and computing speed of the existing OPC techniques need to be improved to fulfill the stringent requirement of the research and design for latest technological nodes.The emergence of machine learning technologies inspires novel OPC algorithms.More accurate forward simulation of the lithographic process and single turn optimization methods are enabled by the machine learning based OPC techniques.We discuss the latest progress made by the OPC community in the process simulation and optimization based on machine learning techniques.

Efficient measurement and optical proximity correction modeling to catch lithography pattern shift issues of arbitrarily distributed hole layer

With the continued shrinking of the critical dimensions(CDs)of wafer patterning,the requirements for modeling precision in optical proximity correction(OPC)increase accordingly.This requirement extends beyond CD controlling accuracy to include pattern alignment accuracy because misalignment can lead to considerable overlay and metal-via coverage issues at advanced nodes,affecting process window and yield.This paper proposes an efficient OPC modeling approach that prioritizes pattern-shift-related elements to tackle the issue accurately.Our method integrates careful measurement selection,the implementation of pattern-shift-aware structures in design,and the manipulation of the cost function during model tuning to establish a robust model.Confirmatory experiments are performed on a via layer fabricated using a negative tone development.Results demonstrate that pattern shifts can be constrained within a range of+1 nm,remarkably better than the original range of±3 nm.Furthermore,simulations reveal notable differences between post OPC and original masks when considering pattern shifts at locations sensitive to this phenomenon.Experimental validation confirms the accuracy of the proposed modeling approach,and a firm consistency is observed between the simulation results and experimental data obtained from actual design structures.