VerilogReader: LLM-Aided Hardware Test Generation
This addresses the labor-intensive process of hardware design verification, but it appears incremental as it builds on existing Coverage Directed Test Generation with LLM integration.
The paper tackles hardware test generation by integrating a Large Language Model as a Verilog reader to generate stimuli for reaching unexplored code branches, showing it outperforms random testing on designs within the LLM's comprehension scope.
Test generation has been a critical and labor-intensive process in hardware design verification. Recently, the emergence of Large Language Model (LLM) with their advanced understanding and inference capabilities, has introduced a novel approach. In this work, we investigate the integration of LLM into the Coverage Directed Test Generation (CDG) process, where the LLM functions as a Verilog Reader. It accurately grasps the code logic, thereby generating stimuli that can reach unexplored code branches. We compare our framework with random testing, using our self-designed Verilog benchmark suite. Experiments demonstrate that our framework outperforms random testing on designs within the LLM's comprehension scope. Our work also proposes prompt engineering optimizations to augment LLM's understanding scope and accuracy.