LLM-based Behaviour Driven Development for Hardware Design

TL;DR

This paper explores using Large Language Models to automate the creation of behavioral scenarios in hardware design, aiming to improve verification processes through Behavior Driven Development.

Contribution

It introduces a novel approach leveraging LLMs to automate behavioral scenario generation for hardware BDD, addressing manual effort challenges.

Findings

LLMs can effectively generate behavioral scenarios from textual specifications.

Automating scenario creation reduces manual effort in hardware verification.

The approach enhances the practicality of BDD in hardware design.

Abstract

Test and verification are essential activities in hardware and system design, but their complexity grows significantly with increasing system sizes. While Behavior Driven Development (BDD) has proven effective in software engineering, it is not yet well established in hardware design, and its practical use remains limited. One contributing factor is the manual effort required to derive precise behavioral scenarios from textual specifications. Recent advances in Large Language Models (LLMs) offer new opportunities to automate this step. In this paper, we investigate the use of LLM-based techniques to support BDD in the context of hardware design.