SpotSDC: Revealing the Silent Data Corruption Propagation in High-Performance Computing Systems
SpotSDC: Revealing the Silent Data Corruption Propagation in High-Performance Computing Systems
复制标题
DOI：
10.1109/tvcg.2020.2994954
复制
发表时间：
2020-05
影响因子：
5.2
通讯作者：
Zhimin Li;Harshitha Menon;D. Maljovec;Y. Livnat;Shusen Liu;K. Mohror;P. Bremer;Valerio Pascucci
中科院分区：
文献类型：
--
作者：
Zhimin Li;Harshitha Menon;D. Maljovec;Y. Livnat;Shusen Liu;K. Mohror;P. Bremer;Valerio Pascucci
快速技术扩展的趋势预计将使高性能计算(HPC)系统的硬件更容易受到随机位翻转造成的计算错误的影响。一些位翻转可能导致程序崩溃或对输出的影响最小，但其他位翻转可能导致静默数据损坏(SDC)，即未检测到但重大的输出错误。经典的故障注入分析方法在程序执行期间使用随机位翻转的均匀采样来导出统计弹性分布。然而，很难充分详细地总结这样的错误注入结果，并且理解被错误破坏的程序的行为仍然是一个挑战。在本文中，我们介绍了SpotSDC，这是一个可视化系统，有助于分析程序对SDC的弹性。SpotSDC提供了与源代码中发生翻转的位的位置、翻转的位以及在执行期间发生翻转的时间相关的对输出的影响的不同详细程度的多个透视图。SpotSDC还使用户能够研究代码保护，并提供新的见解来了解错误注入程序的行为。在总结经验的基础上，我们演示了我们所发现的如何改进故障注入活动方法。
The trend of rapid technology scaling is expected to make the hardware of high-performance computing (HPC) systems more susceptible to computational errors due to random bit flips. Some bit flips may cause a program to crash or have a minimal effect on the output, but others may lead to silent data corruption (SDC), i.e., undetected yet significant output errors. Classical fault injection analysis methods employ uniform sampling of random bit flips during program execution to derive a statistical resiliency profile. However, summarizing such fault injection result with sufficient detail is difficult, and understanding the behavior of the fault-corrupted program is still a challenge. In this article, we introduce SpotSDC, a visualization system to facilitate the analysis of a program’s resilience to SDC. SpotSDC provides multiple perspectives at various levels of detail of the impact on the output relative to where in the source code the flipped bit occurs, which bit is flipped, and when during the execution it happens. SpotSDC also enables users to study the code protection and provide new insights to understand the behavior of a fault-injected program. Based on lessons learned, we demonstrate how what we found can improve the fault injection campaign method.