Interactive and Automatic Generation of Primitive Custom Circuit Layout Using LLMs

TL;DR

This paper explores using Large Language Models to interactively and automatically generate custom circuit layouts from natural language descriptions, improving efficiency and customization in circuit design.

Contribution

It introduces a novel natural language-based layout generation framework leveraging LLMs for interactive and automated circuit design, including high-speed and mixed-signal circuits.

Findings

LLMs can generate diverse circuit layouts with customization.

Layouts pass DRC, LVS, and performance tests.

The approach enhances intuitiveness and efficiency in circuit design.

Abstract

In this study, we investigate the use of Large Language Models (LLMs) for the interactive and automated production of customs circuit layouts described in natural language. Our proposed layout automation process leverages a template-and-grid-based layout generation framework to create process-portable layout generators tailored for various custom circuits, including standard cells and high-speed mixed-signal circuits. However, rather than directly describing the layout generators in traditional programming language, we utilize natural language using LLMs to make the layout generation process more intuitive and efficient. This approach also supports interactive modifications of the layout generator code, enhancing customization capabilities. We demonstrate the effectiveness of our LLM-based layout generation method across several custom circuit examples, such as logic standard cells, a serializer and a strong arm latch, including their completeness in terms of Design Rule Check (DRC), Layout Versus Schematic (LVS) test, and post-layout performance for high-speed circuits. Our experimental results indicate that LLMs can generate a diverse range of circuit layouts with substantial customization options.