Detecting Silent Data Corruption for Extreme-Scale Applications through Data Mining

doi:https://doi.org/10.2172/1177404

Title: Detecting Silent Data Corruption for Extreme-Scale Applications through Data Mining

Full Record
Other Related Research

Abstract

Supercomputers allow scientists to study natural phenomena by means of computer simulations. Next-generation machines are expected to have more components and, at the same time, consume several times less energy per operation. These trends are pushing supercomputer construction to the limits of miniaturization and energy-saving strategies. Consequently, the number of soft errors is expected to increase dramatically in the coming years. While mechanisms are in place to correct or at least detect some soft errors, a significant percentage of those errors pass unnoticed by the hardware. Such silent errors are extremely damaging because they can make applications silently produce wrong results. In this work we propose a technique that leverages certain properties of high-performance computing applications in order to detect silent errors at the application level. Our technique detects corruption solely based on the behavior of the application datasets and is completely application-agnostic. We propose multiple corruption detectors, and we couple them to work together in a fashion transparent to the user. We demonstrate that this strategy can detect the majority of the corruptions, while incurring negligible overhead. We show that with the help of these detectors, applications can have up to 80% of coverage against data corruption.

Authors:

Bautista-Gomez, Leonardo ^[1]; Cappello, Franck ^[1]

Argonne National Lab. (ANL), Argonne, IL (United States)

Publication Date:: 2014-01-16

Research Org.:: Argonne National Lab. (ANL), Argonne, IL (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1177404

Report Number(s):: ANL/MCS-TM-346
109004

DOE Contract Number:: AC02-06CH11357

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Bautista-Gomez, Leonardo, and Cappello, Franck. Detecting Silent Data Corruption for Extreme-Scale Applications through Data Mining.  United States: N. p., 2014. 
        Web.  doi:10.2172/1177404.

Copy to clipboard


                    Bautista-Gomez, Leonardo, & Cappello, Franck. Detecting Silent Data Corruption for Extreme-Scale Applications through Data Mining.  United States.  https://doi.org/10.2172/1177404

Copy to clipboard


                    Bautista-Gomez, Leonardo, and Cappello, Franck. Thu .  
        "Detecting Silent Data Corruption for Extreme-Scale Applications through Data Mining".  United States.  https://doi.org/10.2172/1177404.  https://www.osti.gov/servlets/purl/1177404.

Copy to clipboard


                    
@article{osti_1177404,

  title        = {Detecting Silent Data Corruption for Extreme-Scale Applications through Data Mining},

  author       = {Bautista-Gomez, Leonardo and Cappello, Franck},

  abstractNote = {Supercomputers allow scientists to study natural phenomena by means of computer simulations. Next-generation machines are expected to have more components and, at the same time, consume several times less energy per operation. These trends are pushing supercomputer construction to the limits of miniaturization and energy-saving strategies. Consequently, the number of soft errors is expected to increase dramatically in the coming years. While mechanisms are in place to correct or at least detect some soft errors, a significant percentage of those errors pass unnoticed by the hardware. Such silent errors are extremely damaging because they can make applications silently produce wrong results. In this work we propose a technique that leverages certain properties of high-performance computing applications in order to detect silent errors at the application level. Our technique detects corruption solely based on the behavior of the application datasets and is completely application-agnostic. We propose multiple corruption detectors, and we couple them to work together in a fashion transparent to the user. We demonstrate that this strategy can detect the majority of the corruptions, while incurring negligible overhead. We show that with the help of these detectors, applications can have up to 80% of coverage against data corruption.},

  doi          = {10.2172/1177404},

  url          = {https://www.osti.gov/biblio/1177404},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2014},

  month        = {1}

}

Copy to clipboard

Technical Report:

View Technical Report

https://doi.org/10.2172/1177404

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

An Efficient Silent Data Corruption Detection Method with Error-Feedback Control and Even Sampling for HPC Applications

Conference Di, Sheng ; Berrocal, Eduardo ; Cappello, Franck

The silent data corruption (SDC) problem is attracting more and more attentions because it is expected to have a great impact on exascale HPC applications. SDC faults are hazardous in that they pass unnoticed by hardware and can lead to wrong computation results. In this work, we formulate SDC detection as a runtime one-step-ahead prediction method, leveraging multiple linear prediction methods in order to improve the detection results. The contributions are twofold: (1) we propose an error feedback control model that can reduce the prediction errors for different linear prediction methods, and (2) we propose a spatial-data-based even-sampling method tomore »« less
https://doi.org/10.1109/CCGrid.2015.17
Exploring the capabilities of support vector machines in detecting silent data corruptions

Journal Article Subasi, Omer ; Di, Sheng ; Bautista-Gomez, Leonardo ; ... - Sustainable Computing

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 execution results of HPC applications without being detected. Here in this paper, we explore a set of novel SDC detectors – by leveraging epsilon-insensitive support vector machine regression – to detect SDCs that occur in HPC applications. The key contributions are threefold. (1) Our exploration takes temporal, spatial, and spatiotemporal features into account and analyzes different detectors based onmore »« less
https://doi.org/10.1016/J.SUSCOM.2018.01.004

Full Text Available
Detection and Correction of Silent Data Corruption for Large-Scale High-Performance Computing

Conference Fiala, David J ; Mueller, Frank ; Engelmann, Christian ; ...

Faults have become the norm rather than the exception for high-end computing on clusters with 10s/100s of thousands of cores. Exacerbating this situation, some of these faults remain undetected, manifesting themselves as silent errors that corrupt memory while applications continue to operate and report incorrect results. This paper studies the potential for redundancy to both detect and correct soft errors in MPI message-passing applications. Our study investigates the challenges inherent to detecting soft errors within MPI application while providing transparent MPI redundancy. By assuming a model wherein corruption in application data manifests itself by producing differing MPI message data betweenmore »« less
Toward General Software Level Silent Data Corruption Detection for Parallel Applications

Journal Article Berrocal, Eduardo ; Bautista-Gomez, Leonardo ; Di, Sheng ; ... - IEEE Transactions on Parallel and Distributed Systems

Silent data corruption (SDC) poses a great challenge for high-performance computing (HPC) applications as we move to extreme-scale systems. Mechanisms have been proposed that are able to detect SDC in HPC applications by using the peculiarities of the data (more specifically, its “smoothness” in time and space) to make predictions. However, these data-analytic solutions are still far from fully protecting applications to a level comparable with more expensive solutions such as full replication. In this work, we propose partial replication to overcome this limitation. More specifically, we have observed that not all processes of an MPI application experience the samemore »« less
Cited by 3
https://doi.org/10.1109/TPDS.2017.2735971

Full Text Available
Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era

Conference Subasi, Omer ; Di, Sheng ; Bautista-Gomez, Leonardo ; ...

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 pointmore »« less
https://doi.org/10.1109/CCGrid.2016.33

Similar Records