arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15388cs.AR
收藏

基于语法-语义表示的迭代LLM断言生成用于功能覆盖率引导的验证

Iterative LLM-Based Assertion Generation Using Syntax-Semantic Representations for Functional Coverage-Guided Verification

State Key Lab of Processors, Institute of Computing Technology, CAS(中国科学院计算技术研究所处理器重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Beijing Normal University(北京师范大学);Tencent Ltd.(腾讯有限公司)

Yonghao Wang, Jiaxin Zhou, Yang Yin, Hongqin Lyu, Zhiteng Chao, Wenchao Ding, Jing Ye, Tiancheng Wang, Huawei Li

AI总结:

本文提出CoverAssert,一种基于语法-语义表示的迭代LLM断言生成框架,通过反馈机制提升功能覆盖率,实验显示在分支、语句和切换覆盖率上分别提升9.57%、9.64%和15.69%。

摘要:

尽管利用LLM自动从自然语言规范生成SystemVerilog断言(SVAs)具有巨大潜力,但现有技术面临关键挑战:LLM往往缺乏对集成电路设计的充分理解,导致单次生成的断言质量较差。因此,验证生成的断言是否有效覆盖功能规范,并基于此覆盖率设计反馈机制仍然是重大障碍。为解决这些限制,本文引入了CoverAssert,一种新的迭代框架,用于优化LLM生成SVA。核心贡献是轻量级机制,用于匹配生成的断言与规范中的特定功能描述。CoverAssert通过聚类LLM生成断言的语义特征与从抽象语法树(AST)中提取的结构特征(关于与断言相关的信号)的联合表示,然后将其映射回规范,以分析功能覆盖率质量。利用这一能力,CoverAssert基于功能覆盖率构建反馈回路,指导LLM优先处理未覆盖的功能点,从而迭代提高断言质量。在四个开源设计上的实验评估表明,将CoverAssert与最先进的生成器AssertLLM和Spec2Assertion结合,实现了平均分支覆盖率提高9.57%、语句覆盖率提高9.64%、切换覆盖率提高15.69%。

英文摘要:

While leveraging LLMs to automatically generate SystemVerilog assertions (SVAs) from natural language specifications holds great potential, existing techniques face a key challenge: LLMs often lack sufficient understanding of IC design, leading to poor assertion quality in a single pass. Therefore, verifying whether the generated assertions effectively cover the functional specifications and designing feedback mechanisms based on this coverage remain significant hurdles. To address these limitations, this paper introduces CoverAssert, a novel iterative framework for optimizing SVA generation with LLMs. The core contribution is a lightweight mechanism for matching generated assertions with specific functional descriptions in the specifications. CoverAssert achieves this by clustering the joint representations of semantic features of LLM-generated assertions and structural features extracted from abstract syntax trees (ASTs) about signals related to assertions, and then mapping them back to the specifications to analyze functional coverage quality. Leveraging this capability, CoverAssert constructs a feedback loop based on functional coverage to guide LLMs in prioritizing uncovered functional points, thereby iteratively improving assertion quality. Experimental evaluations on four open-source designs demonstrate that integrating CoverAssert with state-of-the-art generators, AssertLLM and Spec2Assertion, achieves average improvements of 9.57 % in branch coverage, 9.64 % in statement coverage, and 15.69 % in toggle coverage.

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。

↑