Harnessing MPI mutations for AI error detection

in Talks

Asia Auville is going to rehearse her ICS'26 presentation

Speaker

Asia Auville

When

Friday, June 12, 15:00

Where

room Alan Turing

Title

Harnessing MPI mutations for AI error detection

Abstract

MPI errors are challenging to identify despite the significant number of expert verification tools. Dynamic tools (i.e., requiring profiling) are computationally expensive and accurate in error detection, whereas static analysis (i.e., operating at source code or compilation) is computationally cheap but less accurate. Interestingly, the recent success of AI and LLMs offers an alternative to increase static analysis accuracy while preserving its low overhead. Yet current methods remain difficult to benchmark, too general, and poorly adapted to the specific challenges of high-performance computing. In this paper, we investigate how AI-powered tools can efficiently and accurately detect errors in real-world MPI applications. We propose a novel MPI Mutated Dataset (MMD), constructed from MPI programs extracted from thousands of open-source GitHub projects. After sorting and filtering these files, we inject errors that realistically emulate developers’ mistakes using synthetic code mu- tations. We leverage the dataset to train different AI models and assess their generalization capabilities against standard verification tools. We train compact multilayer perceptrons (MLP) with AST- T5 embeddings (i.e., transformer only encoder network) to detect diverse MPI errors (from the MPI-BugBench (MBB) classification) including CallOrdering or InvalidParameter, achieving detection accuracies up to 92.0%. In some cases, our method outperforms the expert prompted Qwen-3 Coder LLM and provides compet- itive results compared to established dynamic verification tools. We further evaluate Claude Sonnet 4.5 across different prompting strategies, showing that engineered prompts improve InvalidParam detection accuracy from 84.8% to 93.6%, surpassing the dynamic tool ITAC (87.0%). The full agentic pipeline achieves 73.9% overall multi-class accuracy and 87.6% bug detection recall on MBB. This paves the way for large-scale verification efforts that can use our dataset as a foundation to thoroughly investigate each MPI error in real world applications.