arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.04535cs.LGcs.AR
收藏

LLM4DV:使用大型语言模型生成硬件测试激励

LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation

University of Cambridge(剑桥大学);Imperial College London(伦敦帝国理工学院);lowRISC;University of Edinburgh(爱丁堡大学)

Zixi Zhang, Balint Szekely, Pedro Gimenes, Greg Chadwick, Hugo McNally, Jianyi Cheng, Robert Mullins, Yiren Zhao

AI总结:

本文提出LLM4DV开源框架,利用大型语言模型自动生成硬件测试激励,评估六种模型和六种提示改进,覆盖八个设计,为高效自动化硬件验证提供见解。

摘要:

硬件设计验证(DV)是一个检查硬件设计与其规格功能等价性的过程,旨在提高硬件的可靠性和鲁棒性。DV过程中的一个关键任务是测试激励生成,即为测试创建一组条件或输入。这些测试条件通常复杂且特定于给定的硬件设计,需要大量的人工工程努力来优化。我们寻求一种利用大型语言模型(LLMs)对任意硬件设计进行自动化和高效测试的解决方案。LLMs已经在改进硬件设计自动化方面显示出有前景的结果,但在硬件DV方面的探索仍然不足。在本文中,我们提出了一个名为LLM4DV的开源基准测试框架,该框架高效地编排LLMs以自动生成硬件测试激励。我们的分析评估了六种不同的LLMs,涉及六种提示改进,跨越八个硬件设计,并为未来LLMs开发高效自动化DV的工作提供了见解。

英文摘要:

Hardware design verification (DV) is a process that checks the functional equivalence of a hardware design against its specifications, improving hardware reliability and robustness. A key task in the DV process is the test stimuli generation, which creates a set of conditions or inputs for testing. These test conditions are often complex and specific to the given hardware design, requiring substantial human engineering effort to optimize. We seek a solution of automated and efficient testing for arbitrary hardware designs that takes advantage of large language models (LLMs). LLMs have already shown promising results for improving hardware design automation, but remain under-explored for hardware DV. In this paper, we propose an open-source benchmarking framework named LLM4DV that efficiently orchestrates LLMs for automated hardware test stimuli generation. Our analysis evaluates six different LLMs involving six prompting improvements over eight hardware designs and provides insight for future work on LLMs development for efficient automated DV.

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。

↑