FaultSight: A fault analysis tool for HPC researchers

Einar Horn; Dakota Fulp; Jon Calhoun; Luke Olson

doi:10.1109/FTXS49593.2019.00008

FaultSight: A fault analysis tool for HPC researchers

Einar Horn, Dakota Fulp, Jon Calhoun, Luke Olson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

System reliability is expected to be a significant challenge for future extreme-scale systems. Poor reliability results in a higher frequency of interruptions in high-performance computer (HPC) applications due to system/application crashes or data corruption due to soft errors. In response, application level error detection and recovery schemes are devised to mitigate the impact of these interruptions. Evaluating these schemes and the reliability of an application re-quires the analysis of thousands of fault injection trials, resulting in tedious and time-consuming process. Furthermore, there is no one data analysis tool that can work with all of the fault injection frameworks currently in use. In this paper, we present FaultSight, a fault injection analysis tool capable of efficiently assisting in the analysis of HPC application reliability as well as the effectiveness of resiliency schemes. FaultSight is designed to be flexible and work with data coming from a variety of fault injection frameworks. The effectiveness of FaultSight is demonstrated by exploring the reliability of different versions of the Matrix-Matrix Multiplication kernel using two different fault injection tools. In addition, the detection and recovery schemes are highlighted for the HPCCG mini-app.

Original language	English (US)
Title of host publication	Proceedings of FTXS 2019
Subtitle of host publication	Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	21-30
Number of pages	10
ISBN (Electronic)	9781728160139
DOIs	https://doi.org/10.1109/FTXS49593.2019.00008
State	Published - Nov 2019
Event	9th IEEE/ACM Workshop on Fault Tolerance for HPC at eXtreme Scale, FTXS 2019 - Denver, United States Duration: Nov 22 2019 → …

Publication series

Name	Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis

Conference

Conference	9th IEEE/ACM Workshop on Fault Tolerance for HPC at eXtreme Scale, FTXS 2019
Country/Territory	United States
City	Denver
Period	11/22/19 → …

Keywords

Fault-analysis
Fault-analysis-tool
Fault-injection
Fault-tolerance
Resiliency
Soft-error-analysis

ASJC Scopus subject areas

Hardware and Architecture
Safety, Risk, Reliability and Quality

Online availability

10.1109/FTXS49593.2019.00008

Library availability

Discover UIUC Full Text

Cite this

Horn, E., Fulp, D., Calhoun, J., & Olson, L. (2019). FaultSight: A fault analysis tool for HPC researchers. In Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 21-30). Article 8945875 (Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FTXS49593.2019.00008

FaultSight: A fault analysis tool for HPC researchers. / Horn, Einar; Fulp, Dakota; Calhoun, Jon et al.
Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2019. p. 21-30 8945875 (Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Horn, E, Fulp, D, Calhoun, J & Olson, L 2019, FaultSight: A fault analysis tool for HPC researchers. in Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis., 8945875, Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis, Institute of Electrical and Electronics Engineers Inc., pp. 21-30, 9th IEEE/ACM Workshop on Fault Tolerance for HPC at eXtreme Scale, FTXS 2019, Denver, United States, 11/22/19. https://doi.org/10.1109/FTXS49593.2019.00008

Horn E, Fulp D, Calhoun J, Olson L. FaultSight: A fault analysis tool for HPC researchers. In Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc. 2019. p. 21-30. 8945875. (Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis). doi: 10.1109/FTXS49593.2019.00008

Horn, Einar ; Fulp, Dakota ; Calhoun, Jon et al. / FaultSight : A fault analysis tool for HPC researchers. Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 21-30 (Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis).

@inproceedings{0dfde8a337ff4741b8cd8501f04273ce,

title = "FaultSight: A fault analysis tool for HPC researchers",

abstract = "System reliability is expected to be a significant challenge for future extreme-scale systems. Poor reliability results in a higher frequency of interruptions in high-performance computer (HPC) applications due to system/application crashes or data corruption due to soft errors. In response, application level error detection and recovery schemes are devised to mitigate the impact of these interruptions. Evaluating these schemes and the reliability of an application re-quires the analysis of thousands of fault injection trials, resulting in tedious and time-consuming process. Furthermore, there is no one data analysis tool that can work with all of the fault injection frameworks currently in use. In this paper, we present FaultSight, a fault injection analysis tool capable of efficiently assisting in the analysis of HPC application reliability as well as the effectiveness of resiliency schemes. FaultSight is designed to be flexible and work with data coming from a variety of fault injection frameworks. The effectiveness of FaultSight is demonstrated by exploring the reliability of different versions of the Matrix-Matrix Multiplication kernel using two different fault injection tools. In addition, the detection and recovery schemes are highlighted for the HPCCG mini-app.",

keywords = "Fault-analysis, Fault-analysis-tool, Fault-injection, Fault-tolerance, Resiliency, Soft-error-analysis",

author = "Einar Horn and Dakota Fulp and Jon Calhoun and Luke Olson",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 9th IEEE/ACM Workshop on Fault Tolerance for HPC at eXtreme Scale, FTXS 2019 ; Conference date: 22-11-2019",

year = "2019",

month = nov,

doi = "10.1109/FTXS49593.2019.00008",

language = "English (US)",

series = "Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "21--30",

booktitle = "Proceedings of FTXS 2019",

address = "United States",

}

TY - GEN

T1 - FaultSight

T2 - 9th IEEE/ACM Workshop on Fault Tolerance for HPC at eXtreme Scale, FTXS 2019

AU - Horn, Einar

AU - Fulp, Dakota

AU - Calhoun, Jon

AU - Olson, Luke

PY - 2019/11

Y1 - 2019/11

N2 - System reliability is expected to be a significant challenge for future extreme-scale systems. Poor reliability results in a higher frequency of interruptions in high-performance computer (HPC) applications due to system/application crashes or data corruption due to soft errors. In response, application level error detection and recovery schemes are devised to mitigate the impact of these interruptions. Evaluating these schemes and the reliability of an application re-quires the analysis of thousands of fault injection trials, resulting in tedious and time-consuming process. Furthermore, there is no one data analysis tool that can work with all of the fault injection frameworks currently in use. In this paper, we present FaultSight, a fault injection analysis tool capable of efficiently assisting in the analysis of HPC application reliability as well as the effectiveness of resiliency schemes. FaultSight is designed to be flexible and work with data coming from a variety of fault injection frameworks. The effectiveness of FaultSight is demonstrated by exploring the reliability of different versions of the Matrix-Matrix Multiplication kernel using two different fault injection tools. In addition, the detection and recovery schemes are highlighted for the HPCCG mini-app.

AB - System reliability is expected to be a significant challenge for future extreme-scale systems. Poor reliability results in a higher frequency of interruptions in high-performance computer (HPC) applications due to system/application crashes or data corruption due to soft errors. In response, application level error detection and recovery schemes are devised to mitigate the impact of these interruptions. Evaluating these schemes and the reliability of an application re-quires the analysis of thousands of fault injection trials, resulting in tedious and time-consuming process. Furthermore, there is no one data analysis tool that can work with all of the fault injection frameworks currently in use. In this paper, we present FaultSight, a fault injection analysis tool capable of efficiently assisting in the analysis of HPC application reliability as well as the effectiveness of resiliency schemes. FaultSight is designed to be flexible and work with data coming from a variety of fault injection frameworks. The effectiveness of FaultSight is demonstrated by exploring the reliability of different versions of the Matrix-Matrix Multiplication kernel using two different fault injection tools. In addition, the detection and recovery schemes are highlighted for the HPCCG mini-app.

KW - Fault-analysis

KW - Fault-analysis-tool

KW - Fault-injection

KW - Fault-tolerance

KW - Resiliency

KW - Soft-error-analysis

UR - http://www.scopus.com/inward/record.url?scp=85078901682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078901682&partnerID=8YFLogxK

U2 - 10.1109/FTXS49593.2019.00008

DO - 10.1109/FTXS49593.2019.00008

M3 - Conference contribution

AN - SCOPUS:85078901682

T3 - Proceedings of FTXS 2019: Fault Tolerance for HPC at eXtreme Scale Workshop - Held in conjunction with SC 2019: The International Conference for High Performance Computing, Networking, Storage and Analysis

SP - 21

EP - 30

BT - Proceedings of FTXS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 22 November 2019

ER -

FaultSight: A fault analysis tool for HPC researchers

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this