arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.07235cs.ARcs.AIcs.PLcs.SE
收藏

LLM辅助的EDA综合错误解释

LLM-aided explanations of EDA synthesis errors

University of New South Wales(新南威尔士大学);University of Calgary(卡尔加里大学)

Siyu Qiu, Benjamin Tan, Hammond Pearce

AI总结:

本文研究利用大型语言模型为Quartus Prime和Vivado的综合错误消息生成新手友好解释,实验显示约71%的解释正确且完整。

摘要:

培养数字设计领域的新工程师是一项挑战,尤其是在教授该领域所使用的复杂电子设计自动化(EDA)工具时。学习者通常会将Verilog和VHDL硬件描述语言中的设计部署到Altera(Intel)和Xilinx(AMD)的现场可编程门阵列(FPGA)上,并通过专有的闭源工具链(分别为Quartus Prime和Vivado)完成。这些工具复杂且难以使用——然而,由于它们是工业界使用的工具,因此是进入该领域必不可少的第一步。在这项工作中,我们研究了如何利用人工智能的最新进展来应对这一挑战的某些方面。具体而言,我们调查了已经展示出文本理解和问答能力的大型语言模型(LLMs)是否可用于为Quartus Prime和Vivado的编译时综合错误消息生成适合初学者的解释。为了进行这项研究,我们使用三个OpenAI LLMs对21个不同的有缺陷代码样本生成了936条错误消息解释。随后对这些解释进行了相关性和正确性评分,我们发现大约71%的情况下,LLMs给出了适合初学者的正确且完整的解释。

英文摘要:

Training new engineers in digital design is a challenge, particularly when it comes to teaching the complex electronic design automation (EDA) tooling used in this domain. Learners will typically deploy designs in the Verilog and VHDL hardware description languages to Field Programmable Gate Arrays (FPGAs) from Altera (Intel) and Xilinx (AMD) via proprietary closed-source toolchains (Quartus Prime and Vivado, respectively). These tools are complex and difficult to use -- yet, as they are the tools used in industry, they are an essential first step in this space. In this work, we examine how recent advances in artificial intelligence may be leveraged to address aspects of this challenge. Specifically, we investigate if Large Language Models (LLMs), which have demonstrated text comprehension and question-answering capabilities, can be used to generate novice-friendly explanations of compile-time synthesis error messages from Quartus Prime and Vivado. To perform this study we generate 936 error message explanations using three OpenAI LLMs over 21 different buggy code samples. These are then graded for relevance and correctness, and we find that in approximately 71% of cases the LLMs give correct & complete explanations suitable for novice learners.

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。

↑