arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.02518cs.DCcs.SE
收藏

基于LLVM IR上GNN嵌入与向量嵌入的MPI错误检测

MPI Errors Detection using GNN Embedding and Vector Embedding over LLVM IR

Jad El Karchi, Hanze Chen, Ali TehraniJamsaz, Ali Jannesari, Mihail Popov, Emmanuelle Saillard

AI总结:

针对并行MPI程序错误检测难题,首次提出基于LLVM IR结合GNN嵌入与向量嵌入的两类检测模型,在同基准测试集上准确率达92%,跨基准超80%,并验证了错误模式关联性与模型泛化性。

摘要:

识别并行MPI程序中的错误是一项具有挑战性的任务。尽管验证工具的数量不断增加,并行程序调试仍然是一个重大难题。本文首次利用嵌入技术与深度学习图神经网络(GNNs)来解决MPI程序中的错误识别问题。具体而言,我们设计并开发了两个模型,它们能够根据代码的LLVM中间表示(IR)判断代码是正确的,还是包含已知的MPI错误。我们使用两个专门用于验证的MPI基准测试集对模型进行了测试:MBI和MPI-CorrBench。通过在同一基准测试集上训练并验证模型,我们在错误类型检测中取得了92%的预测准确率。此外,我们在不同的基准测试集上(例如从MBI切换到MPI-CorrBench)训练并评估模型,取得了超过80%的可观准确率。最后,我们研究了不同MPI错误之间的相互作用,并量化了模型在未见过的新错误上的泛化能力。这一过程包括在训练时移除部分错误类型,评估模型是否仍能预测这些错误。被移除错误的检测准确率在20%到80%之间差异显著,表明错误模式之间存在关联。

英文摘要:

Identifying errors in parallel MPI programs is a challenging task. Despite the growing number of verification tools, debugging parallel programs remains a significant challenge. This paper is the first to utilize embedding and deep learning graph neural networks (GNNs) to tackle the issue of identifying bugs in MPI programs. Specifically, we have designed and developed two models that can determine, from a code's LLVM Intermediate Representation (IR), whether the code is correct or contains a known MPI error. We tested our models using two dedicated MPI benchmark suites for verification: MBI and MPI-CorrBench. By training and validating our models on the same benchmark suite, we achieved a prediction accuracy of 92% in detecting error types. Additionally, we trained and evaluated our models on distinct benchmark suites (e.g., transitioning from MBI to MPI-CorrBench) and achieved a promising accuracy of over 80%. Finally, we investigated the interaction between different MPI errors and quantified our models' generalization capabilities over new unseen errors. This involved removing error types during training and assessing whether our models could still predict them. The detection accuracy of removed errors varies significantly between 20% to 80%, indicating connected error patterns.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑