Test stimuli generation has been a crucial but labor-intensive task in
hardware design verification. In this paper, we revolutionize this process by
harnessing the power of large language models (LLMs) and present a novel
benchmarking framework, LLM4DV. This framework introduces a prompt template for
interactively eliciting test stimuli from the LLM, along with four innovative
prompting improvements to support the pipeline execution and further enhance
its performance. We compare LLM4DV to traditional constrained-random testing
(CRT), using three self-designed design-under-test (DUT) modules. Experiments
demonstrate that LLM4DV excels in efficiently handling straightforward DUT
scenarios, leveraging its ability to employ basic mathematical reasoning and
pre-trained knowledge. While it exhibits reduced efficiency in complex task
settings, it still outperforms CRT in relative terms. The proposed framework
and the DUT modules used in our experiments will be open-sourced upon
publication.

通过利用大型语言模型（LLM）的能力，本文提出了一种基于框架 LLM4DV 的创新性基准测试方法，该方法引入了与 LLM 互动产生测试刺激的提示模板，并提供了四种创新的提示改进来支持流水线执行，并进一步提高其性能。通过与传统的约束随机测试（CRT）进行比较，基于自行设计的三个被测试模块（DUT），实验证明 LLM4DV 能够有效处理直接的 DUT 情景，并利用其基本的数学推理和预训练的知识。尽管在复杂任务设置中其效率有所降低，但相对而言，它仍然优于 CRT。本文中提出的框架和实验中使用的 DUT 模块将在发表后进行开源。