LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhandari, Jitendra, Knechtel, Johann, Narayanaswamy, Ramesh, Garg, Siddharth, Karri, Ramesh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908415288147968
author Bhandari, Jitendra
Knechtel, Johann
Narayanaswamy, Ramesh
Garg, Siddharth
Karri, Ramesh
author_facet Bhandari, Jitendra
Knechtel, Johann
Narayanaswamy, Ramesh
Garg, Siddharth
Karri, Ramesh
contents This work investigates the potential of tailoring Large Language Models (LLMs), specifically GPT3.5 and GPT4, for the domain of chip testing. A key aspect of chip design is functional testing, which relies on testbenches to evaluate the functionality and coverage of Register-Transfer Level (RTL) designs. We aim to enhance testbench generation by incorporating feedback from commercial-grade Electronic Design Automation (EDA) tools into LLMs. Through iterative feedback from these tools, we refine the testbenches to achieve improved test coverage. Our case studies present promising results, demonstrating that this approach can effectively enhance test coverage. By integrating EDA tool feedback, the generated testbenches become more accurate in identifying potential issues in the RTL design. Furthermore, we extended our study to use this enhanced test coverage framework for detecting bugs in the RTL implementations
format Preprint
id arxiv_https___arxiv_org_abs_2406_17132
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines
Bhandari, Jitendra
Knechtel, Johann
Narayanaswamy, Ramesh
Garg, Siddharth
Karri, Ramesh
Hardware Architecture
This work investigates the potential of tailoring Large Language Models (LLMs), specifically GPT3.5 and GPT4, for the domain of chip testing. A key aspect of chip design is functional testing, which relies on testbenches to evaluate the functionality and coverage of Register-Transfer Level (RTL) designs. We aim to enhance testbench generation by incorporating feedback from commercial-grade Electronic Design Automation (EDA) tools into LLMs. Through iterative feedback from these tools, we refine the testbenches to achieve improved test coverage. Our case studies present promising results, demonstrating that this approach can effectively enhance test coverage. By integrating EDA tool feedback, the generated testbenches become more accurate in identifying potential issues in the RTL design. Furthermore, we extended our study to use this enhanced test coverage framework for detecting bugs in the RTL implementations
title LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines
topic Hardware Architecture
url https://arxiv.org/abs/2406.17132