EM-Aware Physical Synthesis: Neural Inductor Modeling and Intelligent Placement & Routing for RF Circuits

TL;DR

This paper introduces an ML-driven framework for RF physical synthesis that uses neural networks to accurately model inductors, enabling automated placement and routing of manufacturable GDSII layouts with high efficiency and EM accuracy.

Contribution

The paper presents a novel neural inductor model trained on extensive data, integrated with an intelligent optimizer and placement-routing engine for EM-aware RF layout synthesis.

Findings

Neural inductor model predicts Q-factor with less than 2% error.

Achieves 93.77% success rate in high-Q layout generation.

Successfully generates DRC-compliant GDSII layouts for RF circuits.

Abstract

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.