EM-Aware Physical Synthesis: Neural Inductor Modeling and Intelligent Placement & Routing for RF Circuits
This work addresses the challenge of automated physical design for RF circuits, enabling faster and more accurate layout generation for engineers, though it is incremental by building on existing ML approaches with specific enhancements.
The paper tackles the problem of generating manufacturable RF circuit layouts by introducing an ML-driven framework that includes a neural inductor model with less than 2% error and a 93.77% success rate in high-Q layout optimization, along with intelligent placement and routing to produce DRC-compliant GDSII layouts.
This paper presents an ML-driven framework for automated RF physical synthesis that transforms circuit netlists into manufacturable GDSII layouts. While recent ML approaches demonstrate success in topology selection and parameter optimization, they fail to produce manufacturable layouts due to oversimplified component models and lack of routing capabilities. Our framework addresses these limitations through three key innovations: (1) a neural network framework trained on 18,210 inductor geometries with frequency sweeps from 1-100 GHz, generating 7.5 million training samples, that predicts inductor Q-factor with less than 2% error and enables fast gradient-based layout optimization with a 93.77% success rate in producing high-Q layouts; (2) an intelligent P-Cell optimizer that reduces layout area while maintaining design-rule-check (DRC) compliance; and (3) a complete placement and routing engine with frequency-dependent EM spacing rules and DRC-aware synthesis. The neural inductor model demonstrates superior accuracy across 1-100 GHz, enabling EM-accurate component synthesis with real-time inference. The framework successfully generates DRC-aware GDSII layouts for RF circuits, representing a significant step toward automated RF physical design.