Autonomy Loops for Monitoring, Operational Data Analytics, Feedback, and Response in HPC Operations

Author:

Boito Francieli1,Brandt Jim2,Cardellini Valeria3,Carns Philip4,Ciorba Florina M.5,Egan Hilary6,Eleliemy Ahmed5,Gentile Ann2,Gruber Thomas7,Hanson Jeff8,Haus Utz-Uwe9,Huck Kevin10,Ilsche Thomas11,Jakobsche Thomas5,Jones Terry12,Karlsson Sven13,Mueen Abdullah14,Ott Michael15,Patki Tapasya16,Peng Ivy17,Raghavan Krishnan4,Simms Stephen18,Shoga Kathleen16,Showerman Michael19,Tiwari Devesh20,Wilde Torsten8,Yamamoto Keiji21

Affiliation:

1. University of Bordeaux, CNRS, Bordeaux INP, INRIA, LaBRI,FR

2. Sandia National Laboratories,CA and NM,US

3. University of Rome Tor Vergata,IT

4. Argonne National Laboratory,IL,US

5. University of Basel,Basel,CH

6. National Renewable Energy Laboratory,CO,US

7. Erlangen National High Performance Computing Center (NHR@FAU),DE

8. Hewlett Packard Enterprise,DE and US

9. Hewlett Packard Labs, EMEA Research Lab,CH

10. University of Oregon, Eugene,OR,US

11. Technische Universität Dresden,DE

12. Oak Ridge National Laboratory,TN,US

13. Technical University of Denmark,DK

14. University of New Mexico,NM,US

15. Leibniz Supercomputing Centre,DE

16. Lawrence Livermore National Laboratory,CA,US

17. KTH Royal Institute of Technology,SE

18. Lawrence Berkeley National Laboratory,CA,US

19. University of Illinois,IL,US

20. Northeastern University,MA,US

21. RIKEN R-CCS,JP

Publisher

IEEE

Reference33 articles.

1. Enabling advanced operational analysis through multi-subsystem data integration on Trinity;brandt;Proc Cray Users Group,2015

2. Integrating Low-latency Analysis into HPC System Monitoring

3. HPC I/O Throughput Bottleneck Analysis with Explainable Local Models

4. Cluster-Cockpit — a web application for job-specific performance monitoring;eitzinger;2019 IEEE International Conference on Cluster Computing ser CLUSTER ’19,2019

5. Explanations for human-on-the-loop

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3