Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era
Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era
复制标题
空间支持向量回归检测百亿亿次时代的无声错误
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
F. Cappello
中科院分区：
文献类型：
--
作者：
Omer Subasi;S. Di;L. Bautista;Prasanna Balaprakash;O. Unsal;Jesús Labarta;A. Cristal;F. Cappello
随着百亿亿次时代的临近，具有目标功率和能源预算目标的高性能计算（HPC）系统的容量不断增加，对可靠性提出了重大挑战。静默数据损坏（sdc）或静默错误是破坏HPC应用程序执行结果而不被检测到的主要来源之一。在这项工作中，我们探索了一种低内存开销的SDC检测器，通过利用对epsilon不敏感的支持向量机回归，来检测HPC应用中发生的SDC，这些SDC可以以影响错误界限为特征。主要贡献有三个方面。(1)我们的设计将空间特征（即快照中每个数据点的相邻数据值）纳入训练数据，这样就引入了很少的内存开销（小于1%）。(2)对不同参数下的检测能力和性能进行了深入研究，并对检测距离进行了精心优化。(3) 8个实际HPC应用的实验表明，我们的检测器可以实现高达99%的检测灵敏度（即召回率），并且大多数情况下的假阳性率小于1%。对于本文研究的所有基准测试，我们的检测器产生的性能开销很低，平均为5%。与其他最先进的技术相比，考虑到检测能力和开销，我们的检测器表现出最佳的权衡。
As the exascale era approaches, the increasing capacity of high-performance computing (HPC) systems with targeted power and energy budget goals introduces significant challenges in reliability. Silent data corruptions (SDCs) or silent errors are one of the major sources that corrupt the executionresults of HPC applications without being detected. In this work, we explore a low-memory-overhead SDC detector, by leveraging epsilon-insensitive support vector machine regression, to detect SDCs that occur in HPC applications that can be characterized by an impact error bound. The key contributions are three fold. (1) Our design takes spatialfeatures (i.e., neighbouring data values for each data point in a snapshot) into training data, such that little memory overhead (less than 1%) is introduced. (2) We provide an in-depth study on the detection ability and performance with different parameters, and we optimize the detection range carefully. (3) Experiments with eight real-world HPC applications show thatour detector can achieve the detection sensitivity (i.e., recall) up to 99% yet suffer a less than 1% of false positive rate for most cases. Our detector incurs low performance overhead, 5% on average, for all benchmarks studied in the paper. Compared with other state-of-the-art techniques, our detector exhibits the best tradeoff considering the detection ability and overheads.