arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.15664cs.AR
收藏

VeriRAG:一种用于自动RTL可测试性修复的检索增强框架

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

The Chinese University of Hong Kong(香港中文大学);University of California San Diego(加州大学圣地亚哥分校);Hong Kong University(香港大学)

Haomin Qi, Yuyang Du, Lihao Zhang, Soung Chang Liew, Kexin Chen, Yining Du

AI总结:

本文提出VeriRAG框架,利用检索增强生成方法实现自动化RTL可测试性修复,通过VeriDFT数据集提升修复成功率,相比零样本基线提升7.72倍。

摘要:

大型语言模型(LLMs)在计算机辅助设计(CAD)中展现出巨大潜力,特别是在电子设计自动化(EDA)工具中的自动调试和验证。然而,可测试性设计(DFT)仍是一个相对未被探索的领域。本文提出了VeriRAG,首个LLM辅助的DFT-EDA框架。VeriRAG利用检索增强生成(RAG)方法,使LLM能够修改代码以确保DFT合规性。VeriRAG整合(1)基于自动编码器的相似性测量模型,用于精确检索参考RTL设计供LLM使用,以及(2)迭代代码修订流程,使LLM在保持可综合性的同时确保DFT合规性。为支持VeriRAG,我们引入VeriDFT,一个基于Verilog的DFT数据集,用于DFT-aware的RTL修复。VeriRAG从VeriDFT检索结构相似的RTL设计,每个设计均配以严格验证的修正作为代码修复的参考。借助VeriRAG和VeriDFT,我们实现了完全自动化的DFT修正,相较于零样本基线(第V节图5)修复成功率提升7.72倍。消融研究进一步证实了VeriRAG框架各组件的贡献。我们开源了数据、模型和脚本,网址为https://github.com/HarminChee/VeriRAG。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑