SearchGEM5: Towards Reliable Gem5 with Search Based Software Testing and Large Language Models

Abstract

We introduce a novel automated testing technique that combines LLM and search-based fuzzing. We use ChatGPT to parameterise C programs. We compile the resultant code snippets, and feed compilable ones to SearchGEM5, our extension to AFL++ fuzzer with customised new mutation operators. We run thus created 4005 binaries through our system under test, gem5, increasing its existing test coverage by more than 1000 lines. We discover 244 instances where gem5 simulation of the binary differs from the binary's expected behaviour.