Workshops Archive

Data Race Detection through Vibe Translation

Workshop: 9th International Workshop on Software Correctness for HPC Applications (Correctness '25)

Authors: Jan Hueckelheim (Argonne National Laboratory (ANL)) and Vimarsh Sathia and Siyuan Brant Qian (University of Illinois at Urbana-Champaign)

Abstract: We propose a data race detection approach for code written in a source programming language, by means of AI-agent translation to a target language, followed by conventional tool-based detection in the target language. We evaluate this translate-then-check approach by translating the C/Fortran+OpenMP programs in DataRaceBench to the Go programming language, and using the Go data race detector to check for races. The translation is controlled through natural language prompts, similar to approaches popularized as vibe coding. Translate-then-check achieves 92.8% accuracy and 9 false negatives for the C programs in DataRaceBench, compared to 89.9% accuracy and 17 false negatives for Clang+ThreadSanitizer applied directly to the original C programs. We discuss the approach and overall accuracy, as well as individual programs for which translate-then-check leads to false negatives or positives, in part due to limitations of the Go data race checker, and limitations of the translation.

Back to 9th International Workshop on Software Correctness for HPC Applications (Correctness '25) Archive Listing Back to Full Workshop Archive Listing