Close

Presentation

NeurFill: Migrating Full-Chip CMP Simulators to Neural Networks for Model-Based Dummy Filling Synthesis
Time
Location
Event Type
Research Manuscript
Virtual Programs
Hosted in Virtual Platform
Keywords
Physical Design and Verification, Lithography and DFM
Topics
EDA
DescriptionDummy filling is widely applied to significantly improve the planarity of topographic patterns for the chemical mechanical polishing (CMP) process in VLSI manufacturing. This paper proposes a novel model-based dummy filling synthesis framework NeurFill, integrated with multiple starting points-sequential quadratic programming (MSP-SQP) optimization solver. Inside this framework, a full-chip CMP simulator is first migrated to the neural network, achieving 8134x speedup on gradient calculation by backward propagation. Multi-modal starting points search is further applied in the framework to obtain satisfying filling quality optimums. The experimental results show that the proposed NeurFill outperforms existing rule- and model-based methods.