AutoAssert 1: A LoRA Fine-Tuned LLM Model for Efficient Automated Assertion Generation

TL;DR

AutoAssert 1 introduces a LoRA fine-tuned LLM approach combined with the Unsloth platform to efficiently generate hardware assertions, reducing training costs while maintaining accuracy for automated hardware testing.

Contribution

It presents a novel assertion generation method using a lightweight, parameter-adjustable LLM integrated with Unsloth, enhancing efficiency and accuracy in hardware testing.

Findings

Efficient assertion generation conforming to hardware logic

Reduced training costs with maintained accuracy

Flexible framework for hardware testing and maintenance

Abstract

As the complexity of software systems continues to increase, the demand for automated testing and maintenance tools is growing exponentially. To meet this urgent need, we propose a new assertion generation method based on Hardware Description Language (HDL). This method combines a lightweight, parameter-adjustable large language model (LLM) with the Unsloth platform to automatically generate test cases, thereby significantly reducing training costs without sacrificing accuracy or generalization performance. Empirical evaluation shows that our method can efficiently generate assertions that strictly conform to the hardware logic. This framework provides a robust and flexible solution to modern software testing and maintenance challenges. https://github.com/liusu-orange/AutoAssert-1 and https://gitee.com/OpenBPU/auto-assert1 are the locations of the source code.