COmPOSER: Circuit Optimization of mm-wave/RF circuits with Performance-Oriented Synthesis for Efficient Realizations

2026-03-20

AI Summary

This work proposes the first end-to-end open-source design framework for millimeter-wave and RF circuit synthesis, addressing the heavy reliance on expert intuition and the inefficiency of conventional manual workflows. By integrating physics-based equations with a machine learning–driven electromagnetic surrogate model, the framework automates the entire design flow—from performance specifications to post-layout simulation—including schematic synthesis, placement, and routing of both active and passive components. Validated in a 65 nm CMOS process, the methodology successfully generates multiple 60 GHz low-noise amplifiers and power amplifiers whose post-simulation performance matches that of hand-crafted designs. The approach achieves a 100–300× improvement in design efficiency while significantly enhancing reproducibility and scalability.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

This work presents COmPOSER, an open-source, end-to-end framework for RF/mm-wave design automation that translates target specifications into optimized circuits with layouts. It unifies schematic synthesis, layout generation for actives and passives, and placement/routing, incorporating physics-based equations and machine-learning-driven electromagnetic models. Based on post-layout validation on multiple LNAs and PAs operating at up to 60GHz in a commercial 65nm process-kit, COmPOSER meets performance targets, comparable to expert manual designs, while delivering a 100-300x productivity gain.

Problem

• RF/mm-wave design automation
• circuit optimization
• performance-oriented synthesis
• layout generation
• design productivity

Innovation

• RF/mm-wave design automation
• performance-oriented synthesis
• machine-learning-driven EM modeling
• layout-aware circuit optimization
• open-source EDA framework