Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities

Bin Nie; Ji Xue; Saurabh Gupta; Christian Engelmann; Evgenia Smirni; Devesh Tiwari

doi:10.1109/MASCOTS.2017.12

Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities

Bin Nie, Ji Xue, Saurabh Gupta, Christian Engelmann, Evgenia Smirni, Devesh Tiwari

Intelligent Systems and Facilities

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

51 Scopus citations

Abstract

GPUs have become part of the mainstream high performance computing facilities that increasingly require more computational power to simulate physical phenomena quickly and accurately. However, GPU nodes also consume significantly more power than traditional CPU nodes, and high power consumption introduces new system operation challenges, including increased temperature, power/cooling cost, and lower system reliability. This paper explores how power consumption and temperature characteristics affect reliability, provides insights into what are the implications of such understanding, and how to exploit these insights toward predicting GPU errors using neural networks.

Original language	English
Title of host publication	Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	22-31
Number of pages	10
ISBN (Electronic)	9781538627631
DOIs	https://doi.org/10.1109/MASCOTS.2017.12
State	Published - Nov 13 2017
Event	25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017 - Banff, Canada Duration: Sep 20 2017 → Sep 22 2017

Publication series

Name	Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

Conference

Conference	25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017
Country/Territory	Canada
City	Banff
Period	09/20/17 → 09/22/17

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Access to Document

10.1109/MASCOTS.2017.12

Cite this

Nie, B., Xue, J., Gupta, S., Engelmann, C., Smirni, E., & Tiwari, D. (2017). Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities. In Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017 (pp. 22-31). Article 8107428 (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MASCOTS.2017.12

Nie, Bin ; Xue, Ji ; Gupta, Saurabh et al. / Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems : Insights, Challenges, and Opportunities. Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 22-31 (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017).

@inproceedings{114134c10dea4ccd9d0f0dc9e0f72d4d,

title = "Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities",

abstract = "GPUs have become part of the mainstream high performance computing facilities that increasingly require more computational power to simulate physical phenomena quickly and accurately. However, GPU nodes also consume significantly more power than traditional CPU nodes, and high power consumption introduces new system operation challenges, including increased temperature, power/cooling cost, and lower system reliability. This paper explores how power consumption and temperature characteristics affect reliability, provides insights into what are the implications of such understanding, and how to exploit these insights toward predicting GPU errors using neural networks.",

author = "Bin Nie and Ji Xue and Saurabh Gupta and Christian Engelmann and Evgenia Smirni and Devesh Tiwari",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017 ; Conference date: 20-09-2017 Through 22-09-2017",

year = "2017",

month = nov,

day = "13",

doi = "10.1109/MASCOTS.2017.12",

language = "English",

series = "Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017",

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

pages = "22--31",

booktitle = "Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017",

}

Nie, B, Xue, J, Gupta, S, Engelmann, C, Smirni, E & Tiwari, D 2017, Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities. in Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017., 8107428, Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017, Institute of Electrical and Electronics Engineers Inc., pp. 22-31, 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017, Banff, Canada, 09/20/17. https://doi.org/10.1109/MASCOTS.2017.12

Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities. / Nie, Bin; Xue, Ji; Gupta, Saurabh et al.
Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 22-31 8107428 (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017).

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

TY - GEN

T1 - Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems

T2 - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

AU - Nie, Bin

AU - Xue, Ji

AU - Gupta, Saurabh

AU - Engelmann, Christian

AU - Smirni, Evgenia

AU - Tiwari, Devesh

PY - 2017/11/13

Y1 - 2017/11/13

N2 - GPUs have become part of the mainstream high performance computing facilities that increasingly require more computational power to simulate physical phenomena quickly and accurately. However, GPU nodes also consume significantly more power than traditional CPU nodes, and high power consumption introduces new system operation challenges, including increased temperature, power/cooling cost, and lower system reliability. This paper explores how power consumption and temperature characteristics affect reliability, provides insights into what are the implications of such understanding, and how to exploit these insights toward predicting GPU errors using neural networks.

AB - GPUs have become part of the mainstream high performance computing facilities that increasingly require more computational power to simulate physical phenomena quickly and accurately. However, GPU nodes also consume significantly more power than traditional CPU nodes, and high power consumption introduces new system operation challenges, including increased temperature, power/cooling cost, and lower system reliability. This paper explores how power consumption and temperature characteristics affect reliability, provides insights into what are the implications of such understanding, and how to exploit these insights toward predicting GPU errors using neural networks.

UR - http://www.scopus.com/inward/record.url?scp=85040513529&partnerID=8YFLogxK

U2 - 10.1109/MASCOTS.2017.12

DO - 10.1109/MASCOTS.2017.12

M3 - Conference contribution

AN - SCOPUS:85040513529

T3 - Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

SP - 22

EP - 31

BT - Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 20 September 2017 through 22 September 2017

ER -

Nie B, Xue J, Gupta S, Engelmann C, Smirni E, Tiwari D. Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities. In Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 22-31. 8107428. (Proceedings - 25th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, MASCOTS 2017). doi: 10.1109/MASCOTS.2017.12

Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this