On the Detection of Silent Data Corruptions in HPC Applications Using Redundant Multi-threading
On the Detection of Silent Data Corruptions in HPC Applications Using Redundant Multi-threading
复制标题
DOI：
10.1007/978-3-030-71593-9_23
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Diego Pérez;Thomas Ropars;Esteban Meneses
中科院分区：
文献类型：
--
作者：
Diego Pérez;Thomas Ropars;Esteban Meneses
本文研究了使用冗余多线程（RMT）来检测HPC应用程序中的静默数据损坏。为了了解它是否可以在HPC环境中成为一个可行的解决方案，我们研究了两种软件优化，通过减少复制线程之间交换的数据量来减少RMT性能开销。我们进行实验，代表HPC工作负载，以衡量通过这些优化获得的性能增益，以及它们实现的错误检测覆盖率。在最好的情况下，当运行在具有同步多线程的处理器上时，我们的结果表明，开销可以低至1.4，而不会显着降低检测数据损坏的能力。
This paper studies the use of Redundant Multi-Threading (RMT) to detect Silent Data Corruptions in HPC applications. To understand if it can be a viable solution in an HPC context, we study two software optimizations to reduce RMT performance overhead by reducing the amount of data exchanged between the replicated threads. We conduct experiments with representative HPC workloads to measure the performance gains obtained through these optimizations, and the error detection coverage they achieve. In the best case, when running on a processor that features Simultaneous Multi-Threading, our results show that the overhead can be as low as 1.4without significantly reducing the ability to detect data corruptions.