Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shahidzadeh, Mohammad, Ghavami, Behnam, Wilton, Steve, Shannon, Lesley
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912131113287680
author Shahidzadeh, Mohammad
Ghavami, Behnam
Wilton, Steve
Shannon, Lesley
author_facet Shahidzadeh, Mohammad
Ghavami, Behnam
Wilton, Steve
Shannon, Lesley
contents Formal Property Verification (FPV), using SystemVerilog Assertions (SVA), is crucial for ensuring the completeness of design with respect to the specification. However, writing SVA is a laborious task and has a steep learning curve. In this work, we present a large language model (LLM) -based flow to automatically generate high-quality SVA from the design specification documents, named \ToolName. We introduce a novel sub-task-focused fine-tuning approach that effectively addresses functionally incorrect assertions produced by baseline LLMs, leading to a remarkable 7.3-fold increase in the number of functionally correct assertions. Recognizing the prevalence of syntax and semantic errors, we also developed an iterative refinement method that enhances the LLM's initial outputs by systematically re-prompting it to correct identified issues. This process is further strengthened by a custom compiler that generates meaningful error messages, guiding the LLM towards improved accuracy. The experiments demonstrate a 26\% increase in the number of assertions free from syntax errors using this approach, showcasing its potential to streamline the FPV process.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15442
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting
Shahidzadeh, Mohammad
Ghavami, Behnam
Wilton, Steve
Shannon, Lesley
Hardware Architecture
Artificial Intelligence
Formal Property Verification (FPV), using SystemVerilog Assertions (SVA), is crucial for ensuring the completeness of design with respect to the specification. However, writing SVA is a laborious task and has a steep learning curve. In this work, we present a large language model (LLM) -based flow to automatically generate high-quality SVA from the design specification documents, named \ToolName. We introduce a novel sub-task-focused fine-tuning approach that effectively addresses functionally incorrect assertions produced by baseline LLMs, leading to a remarkable 7.3-fold increase in the number of functionally correct assertions. Recognizing the prevalence of syntax and semantic errors, we also developed an iterative refinement method that enhances the LLM's initial outputs by systematically re-prompting it to correct identified issues. This process is further strengthened by a custom compiler that generates meaningful error messages, guiding the LLM towards improved accuracy. The experiments demonstrate a 26\% increase in the number of assertions free from syntax errors using this approach, showcasing its potential to streamline the FPV process.
title Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting
topic Hardware Architecture
Artificial Intelligence
url https://arxiv.org/abs/2411.15442