Recent advances in large language models have demonstrated their potential
for automated generation of hardware description language (HDL) code from
high-level prompts. Researchers have utilized fine-tuning to enhance the
ability of these large language models (LLMs) in the field of Chip Design.
However, the lack of Verilog data hinders further improvement in the quality of
Verilog generation by LLMs. Additionally, the absence of a Verilog and
Electronic Design Automation (EDA) script data augmentation framework
significantly increases the time required to prepare the training dataset for
LLM trainers. This paper proposes an automated design-data augmentation
framework, which generates high-volume and high-quality natural language
aligned with Verilog and EDA scripts. For Verilog generation, it translates
Verilog files to an abstract syntax tree and then maps nodes to natural
language with a predefined template. For Verilog repair, it uses predefined
rules to generate the wrong verilog file and then pairs EDA Tool feedback with
the right and wrong verilog file. For EDA Script generation, it uses existing
LLM(GPT-3.5) to obtain the description of the Script. To evaluate the
effectiveness of our data augmentation method, we finetune Llama2-13B and
Llama2-7B models using the dataset generated by our augmentation framework. The
results demonstrate a significant improvement in the Verilog generation tasks
with LLMs. Moreover, the accuracy of Verilog generation surpasses that of the
current state-of-the-art open-source Verilog generation model, increasing from
58.8% to 70.6% with the same benchmark. Our 13B model (ChipGPT-FT) has a pass
rate improvement compared with GPT-3.5 in Verilog generation and outperforms in
EDA script (i.e., SiliconCompiler) generation with only 200 EDA script data.

通过自动生成与 Verilog 和 EDA 脚本对齐的高容量高质量自然语言，本研究提出了一种自动化设计数据增强框架，以改善 LLM 在 Verilog 代码生成和 EDA 脚本生成任务中的表现。结果表明，使用我们的增强方法对 Llama2-13B 和 Llama2-7B 模型进行微调在 Verilog 生成任务中有显著改善，并且与当前最先进的开源 Verilog 生成模型相比，Verilog 生成的准确性从 58.8％提高到 70.6％。与 GPT-3.5 相比，我们的 13B 模型（ChipGPT-FT）在 Verilog 生成和 EDA 脚本生成方面具有更好的性能。