AutoBench: Automatic Testbench Generation and Evaluation Using LLMs for HDL Design

In digital circuit design, testbenches (TBs) constitute the cornerstone of simulation-based hardware verification. Traditional methodologies for testbench generation during simulation-based hardware verification still remain partially manual, resulting in inefficiencies in te sting various sc enarios an d re quiring expensive time from designers. Large Language Models (LLMs) have demonstrated their potential in automating the circuit design flow. However, directly applying LLMs to generate testbenches suffers from a low pass rate. To address this challenge, we introduce Auto-Bench, the first LLM-based testbench generator for digital circuit design, which requires only the description of the design under test (DUT) to automatically generate comprehensive testbenches. In AutoBench, a hybrid testbench structure and a self-checking system are realized using LLMs. To validate the generated test-benches, we also introduce an automated testbench evaluation framework to evaluate the quality of generated testbenches from multiple perspectives. Experimental results demonstrate that Auto-Bench achieves a 57% improvement in the testbench pass@l ratio compared with the baseline that directly generates testbenches using LLMs. For 75 sequential circuits, AutoBench successfully has a 3.36 times testbench pass@l ratio compared with the baseline. The source codes and experimental results are open-sourced at this link: https://github.com/AutoBench/AutoBench. Artifact DOI: 10.5281/zenodo.13325723.