EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search

TL;DR

EasySize introduces a lightweight, universal analog circuit gate sizing framework using a finetuned LLM-guided heuristic search, achieving high performance across multiple technology nodes with reduced computational resources.

Contribution

It is the first lightweight, LLM-based gate sizing method that generalizes across process nodes and circuit topologies without extensive retraining.

Findings

Strong performance on 5 Op-Amp netlists across 180nm, 45nm, and 22nm nodes.

Outperforms AutoCkt on 86.67% of tasks with over 96.67% resource savings.

Achieves effective sizing without additional targeted training.

Abstract

Analog circuit design is a time-consuming, experience-driven task in chip development. Despite advances in AI, developing universal, fast, and stable gate sizing methods for analog circuits remains a significant challenge. Recent approaches combine Large Language Models (LLMs) with heuristic search techniques to enhance generalizability, but they often depend on large model sizes and lack portability across different technology nodes. To overcome these limitations, we propose EasySize, the first lightweight gate sizing framework based on a finetuned Qwen3-8B model, designed for universal applicability across process nodes, design specifications, and circuit topologies. EasySize exploits the varying Ease of Attainability (EOA) of performance metrics to dynamically construct task-specific loss functions, enabling efficient heuristic search through global Differential Evolution (DE) and local Particle Swarm Optimization (PSO) within a feedback-enhanced flow. Although finetuned solely on 350nm node data, EasySize achieves strong performance on 5 operational amplifier (Op-Amp) netlists across 180nm, 45nm, and 22nm technology nodes without additional targeted training, and outperforms AutoCkt, a widely-used Reinforcement Learning based sizing framework, on 86.67\% of tasks with more than 96.67\% of simulation resources reduction. We argue that EasySize can significantly reduce the reliance on human expertise and computational resources in gate sizing, thereby accelerating and simplifying the analog circuit design process. EasySize will be open-sourced at a later date.