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 2407.18271cs.ARcs.AI
收藏

用于Verilog生成的大语言模型:基于代码结构引导的强化学习

Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning

City University of Hong Kong(香港城市大学);Southeast University(东南大学)

Ning Wang, Bingkun Yao, Jie Zhou, Xi Wang, Zhe Jiang, Nan Guan

AI总结:

本文提出VeriSeek,一种利用代码结构引导的强化学习增强的大语言模型,以少量高质量数据高效生成Verilog代码,在多个基准上超越现有方法。

摘要:

近年来,大语言模型(LLMs)的进步激发了人们对自动生成寄存器传输级(RTL)设计的浓厚兴趣,尤其是使用Verilog语言。当前关于该主题的研究主要集中于预训练和指令微调,但这些方法的有效性受到训练数据有限性的制约,因为公开的Verilog代码远不如软件代码丰富。特别是,这些方法难以有效捕捉Verilog的并行代码结构,这种结构从根本上不同于大多数软件编程语言中典型的命令式顺序控制流。本文介绍了VeriSeek,一种通过强化学习增强的大语言模型,利用少量高质量训练数据实现高性能的Verilog代码生成。我们的强化学习方法采用代码结构信息作为反馈信号来优化预训练模型,使其能够有效学习具有并行结构的Verilog代码中的重要模式。实验表明,VeriSeek在多个基准测试中均优于现有最先进的方法。

英文摘要:

Recent advancements in large language models (LLMs) have sparked significant interest in the automatic generation of Register Transfer Level (RTL) designs, particularly using Verilog. Current research on this topic primarily focuses on pre-training and instruction tuning, but the effectiveness of these methods is constrained by the limited availability of training data, as public Verilog code is far less abundant than software code. In particular, these methods struggle to effectively capture Verilog parallel code structures, which fundamentally differ from the imperative, sequential control flow typical in most software programming languages. This paper introduces VeriSeek, an LLM enhanced by reinforcement learning using a limited amount of high-quality training data to achieve high Verilog code generation performance. Our reinforcement learning approach employs code structure information as feedback signals to refine the pre-trained model, enabling it to effectively learn important patterns from Verilog code with parallel structures. Experiments show that VeriSeek outperforms state-of-the-art methods across multiple benchmarks.

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。

↑