arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00704cs.LG
收藏

LocalV: 利用信息局部性进行IP级Verilog生成

QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation

University of Science(科学大学);SKL of Processors, Institute of Computing Technology, CAS(处理器研究所,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学)

Hanqi Lyu, Di Huang, Yaoyu Zhu, Kangcheng Liu, Bohan Dou, Chongxiao Li, Pengwei Jin, Shuyao Cheng, Rui Zhang, Zidong Du, Qi Guo, Xing Hu, Yunji Chen

AI总结:

LocalV通过利用模块化硬件设计中的信息局部性,解决IP级Verilog生成中的长文档处理、长代码生成和调试挑战,实现更高的生成准确率。

摘要:

在数字硬件设计中,寄存器传输级(RTL)代码的生成是一个关键但劳动密集的步骤,传统上需要工程师手动将复杂规格转换为数千行可综合的硬件描述语言(HDL)代码。尽管大型语言模型(LLMs)在自动化此过程方面显示出潜力,但现有方法,包括微调的领域专用模型和先进的代理系统,在扩展到工业IP级设计任务时面临困难。我们识别出三个关键挑战:(1)处理长而详细的文档,其中关键接口约束被无关子模块描述所掩盖;(2)生成长RTL代码,其中语法和语义正确性随着输出长度的增加而急剧下降;(3)通过模拟和波形分析进行功能验证所需的复杂调试循环。为克服这些挑战,我们提出LocalV,一种利用模块化硬件设计中信息局部性的多代理框架。LocalV将长文档到长代码生成问题分解为一组短文档、短代码任务,从而实现可扩展的生成和调试。具体而言,LocalV集成了分层文档划分、任务规划、局部代码生成、接口一致的合并以及AST引导的局部性感知调试。在RealBench,一个IP级Verilog生成基准测试中,实验表明LocalV显著优于最先进的(SOTA)LLMs和代理,达到45.0%的通过率,相比21.6%。

英文摘要:

The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engineers to manually translate complex specifications into thousands of lines of synthesizable Hardware Description Language (HDL) code. While Large Language Models (LLMs) have shown promise in automating this process, existing approaches--including fine-tuned domain-specific models and advanced agent-based systems--struggle to scale to industrial IP-level design tasks. We identify three key challenges: (1) handling long, highly detailed documents, where critical interface constraints become buried in unrelated submodule descriptions; (2) generating long RTL code, where both syntactic and semantic correctness degrade sharply with increasing output length; and (3) navigating the complex debugging cycles required for functional verification through simulation and waveform analysis. To overcome these challenges, we propose ChipV-RTL, a multi-agent framework that leverages information locality in modular hardware design. ChipV-RTL decomposes the long-document to long-code generation problem into a set of short-document, short-code tasks, enabling scalable generation and debugging. Specifically, ChipV-RTL integrates hierarchical document partitioning, task planning, localized code generation, interface-consistent merging, and AST-guided locality-aware debugging. Experiments on RealBench, an IP-level Verilog generation benchmark, demonstrate that ChipV-RTL substantially outperforms state-of-the-art (SOTA) LLMs and agents, achieving a pass rate of 45.0% compared to 21.6%. Code, project page are available at https://iprc-dip.github.io/ChipV-RTL/.

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。

↑