Saved in:
Bibliographic Details
Main Authors: Ma, Ruiyang, Yang, Yuxin, Liu, Ziqian, Zhang, Jiaxi, Li, Min, Huang, Junhua, Luo, Guojie
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.04373
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916546337570816
author Ma, Ruiyang
Yang, Yuxin
Liu, Ziqian
Zhang, Jiaxi
Li, Min
Huang, Junhua
Luo, Guojie
author_facet Ma, Ruiyang
Yang, Yuxin
Liu, Ziqian
Zhang, Jiaxi
Li, Min
Huang, Junhua
Luo, Guojie
contents Test generation has been a critical and labor-intensive process in hardware design verification. Recently, the emergence of Large Language Model (LLM) with their advanced understanding and inference capabilities, has introduced a novel approach. In this work, we investigate the integration of LLM into the Coverage Directed Test Generation (CDG) process, where the LLM functions as a Verilog Reader. It accurately grasps the code logic, thereby generating stimuli that can reach unexplored code branches. We compare our framework with random testing, using our self-designed Verilog benchmark suite. Experiments demonstrate that our framework outperforms random testing on designs within the LLM's comprehension scope. Our work also proposes prompt engineering optimizations to augment LLM's understanding scope and accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04373
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VerilogReader: LLM-Aided Hardware Test Generation
Ma, Ruiyang
Yang, Yuxin
Liu, Ziqian
Zhang, Jiaxi
Li, Min
Huang, Junhua
Luo, Guojie
Software Engineering
Artificial Intelligence
Test generation has been a critical and labor-intensive process in hardware design verification. Recently, the emergence of Large Language Model (LLM) with their advanced understanding and inference capabilities, has introduced a novel approach. In this work, we investigate the integration of LLM into the Coverage Directed Test Generation (CDG) process, where the LLM functions as a Verilog Reader. It accurately grasps the code logic, thereby generating stimuli that can reach unexplored code branches. We compare our framework with random testing, using our self-designed Verilog benchmark suite. Experiments demonstrate that our framework outperforms random testing on designs within the LLM's comprehension scope. Our work also proposes prompt engineering optimizations to augment LLM's understanding scope and accuracy.
title VerilogReader: LLM-Aided Hardware Test Generation
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2406.04373