VeriRAG: A Retrieval-Augmented Framework for Automated RTL Testability Repair

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qi, Haomin, Du, Yuyang, Zhang, Lihao, Liew, Soung Chang, Chen, Kexin, Du, Yining
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914546809044992
author Qi, Haomin
Du, Yuyang
Zhang, Lihao
Liew, Soung Chang
Chen, Kexin
Du, Yining
author_facet Qi, Haomin
Du, Yuyang
Zhang, Lihao
Liew, Soung Chang
Chen, Kexin
Du, Yining
contents Large language models (LLMs) have demonstrated immense potential in computer-aided design (CAD), particularly for automated debugging and verification within electronic design automation (EDA) tools. However, Design for Testability (DFT) remains a relatively underexplored area. This paper presents VeriRAG, the first LLM-assisted DFT-EDA framework. VeriRAG leverages a Retrieval-Augmented Generation (RAG) approach to enable LLM to revise code to ensure DFT compliance. VeriRAG integrates (1) an autoencoder-based similarity measurement model for precise retrieval of reference RTL designs for the LLM, and (2) an iterative code revision pipeline that allows the LLM to ensure DFT compliance while maintaining synthesizability. To support VeriRAG, we introduce VeriDFT, a Verilog-based DFT dataset curated for DFT-aware RTL repairs. VeriRAG retrieves structurally similar RTL designs from VeriDFT, each paired with a rigorously validated correction, as references for code repair. With VeriRAG and VeriDFT, we achieve fully automated DFT correction -- resulting in a 7.72-fold improvement in successful repair rate compared to the zero-shot baseline (Fig. 5 in Section V). Ablation studies further confirm the contribution of each component of the VeriRAG framework. We open-source our data, models, and scripts at https://github.com/HarminChee/VeriRAG.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VeriRAG: A Retrieval-Augmented Framework for Automated RTL Testability Repair
Qi, Haomin
Du, Yuyang
Zhang, Lihao
Liew, Soung Chang
Chen, Kexin
Du, Yining
Hardware Architecture
Large language models (LLMs) have demonstrated immense potential in computer-aided design (CAD), particularly for automated debugging and verification within electronic design automation (EDA) tools. However, Design for Testability (DFT) remains a relatively underexplored area. This paper presents VeriRAG, the first LLM-assisted DFT-EDA framework. VeriRAG leverages a Retrieval-Augmented Generation (RAG) approach to enable LLM to revise code to ensure DFT compliance. VeriRAG integrates (1) an autoencoder-based similarity measurement model for precise retrieval of reference RTL designs for the LLM, and (2) an iterative code revision pipeline that allows the LLM to ensure DFT compliance while maintaining synthesizability. To support VeriRAG, we introduce VeriDFT, a Verilog-based DFT dataset curated for DFT-aware RTL repairs. VeriRAG retrieves structurally similar RTL designs from VeriDFT, each paired with a rigorously validated correction, as references for code repair. With VeriRAG and VeriDFT, we achieve fully automated DFT correction -- resulting in a 7.72-fold improvement in successful repair rate compared to the zero-shot baseline (Fig. 5 in Section V). Ablation studies further confirm the contribution of each component of the VeriRAG framework. We open-source our data, models, and scripts at https://github.com/HarminChee/VeriRAG.
title VeriRAG: A Retrieval-Augmented Framework for Automated RTL Testability Repair
topic Hardware Architecture
url https://arxiv.org/abs/2507.15664