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 2312.08617cs.PLcs.AR
收藏

RTLCoder:凭借我们的开源数据集和轻量级解决方案,在RTL设计生成方面超越GPT-3.5

RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution

Shang Liu, Wenji Fang, Yao Lu, Qijun Zhang, Hongce Zhang, Zhiyao Xie

AI总结:

本文提出参数仅7B的开源定制LLM方案RTLCoder,利用新数据集和算法,在RTL代码生成基准上超越GPT-3.5,并在VerilogEval Machine上超过GPT-4。

摘要:

近年来,利用自然语言指令和大型语言模型(LLMs)自动生成RTL代码(如Verilog)引起了广泛的研究兴趣。然而,大多数现有方法严重依赖商业LLM(如ChatGPT),而针对这一特定设计生成任务定制的开源LLM性能明显较差。缺乏高质量的开源解决方案限制了这一新兴技术的灵活性和数据隐私。在本研究中,我们提出了一种新的定制LLM解决方案,其参数数量仅为7B,在RTL代码生成的所有代表性基准测试中均取得了优于GPT-3.5的性能。特别是在VerilogEval Machine基准测试中,它超越了GPT-4。这种精度与效率的显著平衡得益于我们新的RTL代码数据集和定制的LLM算法,两者均已完全开源。

英文摘要:

The automatic generation of RTL code (e.g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently. However, most existing approaches heavily rely on commercial LLMs such as ChatGPT, while open-source LLMs tailored for this specific design generation task exhibit notably inferior performance. The absence of high-quality open-source solutions restricts the flexibility and data privacy of this emerging technique. In this study, we present a new customized LLM solution with a modest parameter count of only 7B, achieving better performance than GPT-3.5 on all representative benchmarks for RTL code generation. Especially, it outperforms GPT-4 in VerilogEval Machine benchmark. This remarkable balance between accuracy and efficiency is made possible by leveraging our new RTL code dataset and a customized LLM algorithm, both of which have been made fully open-source.

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。

↑