MPISE: Symbolic Execution of MPI Programs
Abstract
Message Passing Interfaces (MPI) plays an important role in parallel computing. Many parallel applications are implemented as MPI programs. The existing methods of bug detection for MPI programs have the shortage of providing both input and non-determinism coverage, leading to missed bugs. In this paper, we employ symbolic execution to ensure the input coverage, and propose an on-the-fly schedule algorithm to reduce the interleaving explorations for non-determinism coverage, while ensuring the soundness and completeness. We have implemented our approach as a tool, called MPISE, which can automatically detect the deadlock and runtime bugs in MPI programs. The results of the experiments on benchmark programs and real world MPI programs indicate that MPISE finds bugs effectively and efficiently. In addition, our tool also provides diagnostic information and replay mechanism to help understanding bugs.
Cite
@article{arxiv.1403.4813,
title = {MPISE: Symbolic Execution of MPI Programs},
author = {Xianjin Fu and Zhenbang Chen and Yufeng Zhang and Chun Huang and Wei Dong and Ji Wang},
journal= {arXiv preprint arXiv:1403.4813},
year = {2014}
}
Comments
25pages, extended version (unpublished!) of paper submitted to ictac 2014. Version 0.2, we carry out experiments using release llvm istead of a debug version one, which makes mpise 10 times faster