Abstract
Chemical mechanical polishing (CMP) has become one of the most important process stages in the fabrication of advanced integrated circuits (IC). The CMP pattern effect strongly influences the planarization of the chip surface morphology after CMP, degrading the performance and the yield of the circuits. In this paper, we introduce a method to predict the post-CMP surface morphology with a convolutional neural network (CNN)-based CMP model. Then, CNN-based, density step height (DSH)-based, and common neural-network-based CMP models are built to compare the accuracy of the predictions. The test chips are designed and taped out and the predictions of the three models are compared with experimental results measured by an atomic force profiler (AFP) and scanning electron microscope (SEM). The results show that CNN-based CMP models have better accuracy by taking advantage of the CNN networks to extract features from images instead of the traditional equivalent pattern parameters. The effective planarization length (EPL) is introduced and defined to make better predictions with real-time CMP models and in dummy filling tasks. Experiments are designed to show a method to solve the EPL.
Highlights
Chemical mechanical polishing (CMP) is a physical-chemical process usually used to make locally and globally flat wafer surfaces
The planarization of the post-CMP surface determines the depth of field (DOF), which will strongly affect the quality of the lithography during the fabrication of higher layers, while large CMP defects may cause chip failure [3,4]
The practicality was discussed and the results showed that our convolutional neural network (CNN)-based CMP model had good accuracy
Summary
Chemical mechanical polishing (CMP) is a physical-chemical process usually used to make locally and globally flat wafer surfaces. Massachusetts Institute of Technology (MIT) [6,7] and Microelectronics of the Chinese Academy of Sciences (IMECAS) [8,9] have built several pressure-distribution-based CMP models These models predict the defects of post-CMP surfaces by taking advantage of the physical mechanisms of the fabrication process. The CMP process involves too many interfering factors, including the interactions among wafers, polishing pads, abrasives, and the slurry, for which some of the mechanisms are not yet well studied As they are bound by the computation speed, the process windows cannot be too small (usually 10 um × 10 um). CNN-based, neural-network-based, and DSH-based CMP models are built to compare the predictions with the experimental results.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
