A flexible language model-assisted electronic design automation framework

TL;DR

This paper introduces a flexible LLM-assisted EDA framework that interfaces with commercial tools, guiding design optimizations across analog, digital, and RF domains using feedback and constraints.

Contribution

It presents a novel versatile framework that leverages LLMs to generate compatible files and optimize designs within commercial EDA environments, supporting diverse design flows.

Findings

Effective in designing transconductance amplifiers

Successfully optimized microstrip patch antennas

Improved FPGA circuit design process

Abstract

Large language models (LLMs) are transforming electronic design automation (EDA) by enhancing design stages such as schematic design, simulation, netlist synthesis, and place-and-route. Existing methods primarily focus these optimisations within isolated open-source EDA tools and often lack the flexibility to handle multiple domains, such as analogue, digital, and radio-frequency design. In contrast, modern systems require to interface with commercial EDA environments, adhere to tool-specific operation rules, and incorporate feedback from design outcomes while supporting diverse design flows. We propose a versatile framework that uses LLMs to generate files compatible with commercial EDA tools and optimise designs using power-performance-area reports. This is accomplished by guiding the LLMs with tool constraints and feedback from design outputs to meet tool requirements and user specifications. Case studies on operational transconductance amplifiers, microstrip patch antennas, and FPGA circuits show that the framework is effective as an EDA-aware assistant, handling diverse design challenges reliably.