Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Christian Engelmann
@inproceedings{DBLP:conf/europlop/EngelmannS23,
author = {Christian Engelmann and
Suhas Somnath},
title = {Science Use Case Design Patterns for Autonomous Experiments},
booktitle = {Proceedings of the 28th European Conference on Pattern Languages of
Programs, EuroPLoP 2023, Irsee, Germany, July 5-9, 2023},
pages = {26:1--26:14},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3628034.3628060},
doi = {10.1145/3628034.3628060},
timestamp = {Sat, 10 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/europlop/EngelmannS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/AgulloAABBBBCCD22,
author = {Emmanuel Agullo and
Mirco Altenbernd and
Hartwig Anzt and
Leonardo Bautista{-}Gomez and
Tommaso Benacchio and
Luca Bonaventura and
Hans{-}Joachim Bungartz and
Sanjay Chatterjee and
Florina M. Ciorba and
Nathan DeBardeleben and
Daniel Drzisga and
Sebastian Eibl and
Christian Engelmann and
Wilfried N. Gansterer and
Luc Giraud and
Dominik G{\"{o}}ddeke and
Marco Heisig and
Fabienne J{\'{e}}z{\'{e}}quel and
Nils Kohl and
Xiaoye Sherry Li and
Romain Lion and
Miriam Mehl and
Paul Mycek and
Michael Obersteiner and
Enrique S. Quintana{-}Ort{\'{\i}} and
Francesco Rizzi and
Ulrich R{\"{u}}de and
Martin Schulz and
Fred Fung and
Robert Speck and
Linda Stals and
Keita Teranishi and
Samuel Thibault and
Dominik Th{\"{o}}nnes and
Andreas Wagner and
Barbara I. Wohlmuth},
title = {Resiliency in numerical algorithm design for extreme scale simulations},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {36},
number = {2},
pages = {251--285},
year = {2022},
url = {https://doi.org/10.1177/10943420211055188},
doi = {10.1177/10943420211055188},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpca/AgulloAABBBBCCD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc2/EngelmannKBBNSA22,
author = {Christian Engelmann and
Olga A. Kuchar and
Swen Boehm and
Michael J. Brim and
Thomas J. Naughton and
Suhas Somnath and
Scott Atchley and
Jack Lange and
Ben Mintz and
Elke Arenholz},
editor = {Douglas B. Kothe and
Al Geist and
Swaroop Pophale and
Hong Liu and
Suzanne Parete{-}Koon},
title = {The {INTERSECT} Open Federated Architecture for the Laboratory of
the Future},
booktitle = {Accelerating Science and Engineering Discoveries Through Integrated
Research Infrastructure for Experiment, Big Data, Modeling and Simulation
- 22nd Smoky Mountains Computational Sciences and Engineering Conference,
{SMC} 2022, Virtual Event, August 23-25, 2022, Revised Selected Papers},
series = {Communications in Computer and Information Science},
volume = {1690},
pages = {173--190},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-23606-8\_11},
doi = {10.1007/978-3-031-23606-8\_11},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/smc2/EngelmannKBBNSA22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jpdc/KumarGPWSFET21,
author = {Mohit Kumar and
Saurabh Gupta and
Tirthak Patel and
Michael Wilder and
Weisong Shi and
Song Fu and
Christian Engelmann and
Devesh Tiwari},
title = {Study of interconnect errors, network congestion, and applications
characteristics for throttle prediction on a large scale {HPC} system},
journal = {J. Parallel Distributed Comput.},
volume = {153},
pages = {29--43},
year = {2021},
url = {https://doi.org/10.1016/j.jpdc.2021.03.001},
doi = {10.1016/J.JPDC.2021.03.001},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jpdc/KumarGPWSFET21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/KumarE21,
author = {Mohit Kumar and
Christian Engelmann},
editor = {Ricardo Chaves and
Dora B. Heras and
Aleksandar Ilic and
Didem Unat and
Rosa M. Badia and
Andrea Bracciali and
Patrick Diehl and
Anshu Dubey and
Oh Sangyoon and
Stephen L. Scott and
Laura Ricci},
title = {{RDPM:} An Extensible Tool for Resilience Design Patterns Modelling},
booktitle = {Euro-Par 2021: Parallel Processing Workshops - Euro-Par 2021 International
Workshops, Lisbon, Portugal, August 30-31, 2021, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {13098},
pages = {283--297},
publisher = {Springer},
year = {2021},
url = {https://doi.org/10.1007/978-3-031-06156-1\_23},
doi = {10.1007/978-3-031-06156-1\_23},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/europar/KumarE21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/JeongYGELCRG20,
author = {Haewon Jeong and
Yaoqing Yang and
Vipul Gupta and
Christian Engelmann and
Tze Meng Low and
Viveck R. Cadambe and
Kannan Ramchandran and
Pulkit Grover},
editor = {Maciej Malawski and
Krzysztof Rzadca},
title = {3D Coded {SUMMA:} Communication-Efficient and Robust Parallel Matrix
Multiplication},
booktitle = {Euro-Par 2020: Parallel Processing - 26th International Conference
on Parallel and Distributed Computing, Warsaw, Poland, August 24-28,
2020, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {12247},
pages = {392--407},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-57675-2\_25},
doi = {10.1007/978-3-030-57675-2\_25},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/europar/JeongYGELCRG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/prdc/HukerikarE20,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {{PLEXUS:} {A} Pattern-Oriented Runtime System Architecture for Resilient
Extreme-Scale High-Performance Computing Systems},
booktitle = {25th {IEEE} Pacific Rim International Symposium on Dependable Computing,
{PRDC} 2020, Perth, Australia, December 1-4, 2020},
pages = {31--39},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/PRDC50213.2020.00014},
doi = {10.1109/PRDC50213.2020.00014},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/prdc/HukerikarE20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/KumarE20,
author = {Mohit Kumar and
Christian Engelmann},
title = {Models for Resilience Design Patterns},
booktitle = {10th {IEEE/ACM} Workshop on Fault Tolerance for {HPC} at eXtreme Scale,
FTXS@SC 2020, Atlanta, GA, USA, November 11, 2020},
pages = {21--30},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/FTXS51974.2020.00008},
doi = {10.1109/FTXS51974.2020.00008},
timestamp = {Fri, 30 Apr 2021 12:35:39 +0200},
biburl = {https://dblp.org/rec/conf/sc/KumarE20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/OstrouchovMAESR20,
author = {George Ostrouchov and
Don Maxwell and
Rizwan A. Ashraf and
Christian Engelmann and
Mallikarjun Shankar and
James H. Rogers},
editor = {Christine Cuicchi and
Irene Qualters and
William T. Kramer},
title = {{GPU} lifetimes on titan supercomputer: survival analysis and reliability},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2020, Virtual Event / Atlanta,
Georgia, USA, November 9-19, 2020},
pages = {41},
publisher = {{IEEE/ACM}},
year = {2020},
url = {https://doi.org/10.1109/SC41405.2020.00045},
doi = {10.1109/SC41405.2020.00045},
timestamp = {Wed, 04 May 2022 13:02:27 +0200},
biburl = {https://dblp.org/rec/conf/sc/OstrouchovMAESR20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-13342,
author = {Emmanuel Agullo and
Mirco Altenbernd and
Hartwig Anzt and
Leonardo Bautista{-}Gomez and
Tommaso Benacchio and
Luca Bonaventura and
Hans{-}Joachim Bungartz and
Sanjay Chatterjee and
Florina M. Ciorba and
Nathan DeBardeleben and
Daniel Drzisga and
Sebastian Eibl and
Christian Engelmann and
Wilfried N. Gansterer and
Luc Giraud and
Dominik G{\"{o}}ddeke and
Marco Heisig and
Fabienne J{\'{e}}z{\'{e}}quel and
Nils Kohl and
Xiaoye Sherry Li and
Romain Lion and
Miriam Mehl and
Paul Mycek and
Michael Obersteiner and
Enrique S. Quintana{-}Ort{\'{\i}} and
Francesco Rizzi and
Ulrich R{\"{u}}de and
Martin Schulz and
Fred Fung and
Robert Speck and
Linda Stals and
Keita Teranishi and
Samuel Thibault and
Dominik Th{\"{o}}nnes and
Andreas Wagner and
Barbara I. Wohlmuth},
title = {Resiliency in Numerical Algorithm Design for Extreme Scale Simulations},
journal = {CoRR},
volume = {abs/2010.13342},
year = {2020},
url = {https://arxiv.org/abs/2010.13342},
eprinttype = {arXiv},
eprint = {2010.13342},
timestamp = {Wed, 04 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-13342.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwomp/EngelmannVP19,
author = {Christian Engelmann and
Geoffroy R. Vall{\'{e}}e and
Swaroop Pophale},
editor = {Xing Fan and
Bronis R. de Supinski and
Oliver Sinnen and
Nasser Giacaman},
title = {Concepts for OpenMP Target Offload Resilience},
booktitle = {OpenMP: Conquering the Full Hardware Spectrum - 15th International
Workshop on OpenMP, {IWOMP} 2019, Auckland, New Zealand, September
11-13, 2019, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {11718},
pages = {78--93},
publisher = {Springer},
year = {2019},
url = {https://doi.org/10.1007/978-3-030-28596-8\_6},
doi = {10.1007/978-3-030-28596-8\_6},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iwomp/EngelmannVP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/SaoEEGV19,
author = {Piyush Sao and
Christian Engelmann and
Srinivas Eswar and
Oded Green and
Richard W. Vuduc},
title = {Self-stabilizing Connected Components},
booktitle = {9th {IEEE/ACM} Workshop on Fault Tolerance for {HPC} at eXtreme Scale,
FTXS@SC 2019, Denver, CO, USA, November 22, 2019},
pages = {50--59},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/FTXS49593.2019.00011},
doi = {10.1109/FTXS49593.2019.00011},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/SaoEEGV19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/KattiFNE18,
author = {Amogh Katti and
Giuseppe Di Fatta and
Thomas J. Naughton and
Christian Engelmann},
title = {Epidemic failure detection and consensus for extreme parallelism},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {32},
number = {5},
pages = {729--743},
year = {2018},
url = {https://doi.org/10.1177/1094342017690910},
doi = {10.1177/1094342017690910},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpca/KattiFNE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bigdataconf/HuiAPE18,
author = {Yawei Hui and
Rizwan A. Ashraf and
Byung H. Park and
Christian Engelmann},
editor = {Naoki Abe and
Huan Liu and
Calton Pu and
Xiaohua Hu and
Nesreen K. Ahmed and
Mu Qiao and
Yang Song and
Donald Kossmann and
Bing Liu and
Kisung Lee and
Jiliang Tang and
Jingrui He and
Jeffrey S. Saltz},
title = {Real-Time Assessment of Supercomputer Status by a Comprehensive Informative
Metric through Streaming Processing},
booktitle = {{IEEE} International Conference on Big Data {(IEEE} BigData 2018),
Seattle, WA, USA, December 10-13, 2018},
pages = {5339--5341},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/BigData.2018.8621862},
doi = {10.1109/BIGDATA.2018.8621862},
timestamp = {Fri, 19 Nov 2021 16:08:20 +0100},
biburl = {https://dblp.org/rec/conf/bigdataconf/HuiAPE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/ParkHBALE18,
author = {Byung H. Park and
Yawei Hui and
Swen Boehm and
Rizwan A. Ashraf and
Christopher Layton and
Christian Engelmann},
title = {A Big Data Analytics Framework for {HPC} Log Data: Three Case Studies
Using the Titan Supercomputer Log},
booktitle = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2018,
Belfast, UK, September 10-13, 2018},
pages = {571--579},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/CLUSTER.2018.00073},
doi = {10.1109/CLUSTER.2018.00073},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/ParkHBALE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dsn/NieXGPEST18,
author = {Bin Nie and
Ji Xue and
Saurabh Gupta and
Tirthak Patel and
Christian Engelmann and
Evgenia Smirni and
Devesh Tiwari},
title = {Machine Learning Models for {GPU} Error Prediction in a Large Scale
{HPC} System},
booktitle = {48th Annual {IEEE/IFIP} International Conference on Dependable Systems
and Networks, {DSN} 2018, Luxembourg City, Luxembourg, June 25-28,
2018},
pages = {95--106},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/DSN.2018.00022},
doi = {10.1109/DSN.2018.00022},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dsn/NieXGPEST18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dsn/KumarGPWSFET18,
author = {Mohit Kumar and
Saurabh Gupta and
Tirthak Patel and
Michael Wilder and
Weisong Shi and
Song Fu and
Christian Engelmann and
Devesh Tiwari},
title = {Understanding and Analyzing Interconnect Errors and Network Congestion
on a Large Scale {HPC} System},
booktitle = {48th Annual {IEEE/IFIP} International Conference on Dependable Systems
and Networks, {DSN} 2018, Luxembourg City, Luxembourg, June 25-28,
2018},
pages = {107--114},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/DSN.2018.00023},
doi = {10.1109/DSN.2018.00023},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dsn/KumarGPWSFET18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/AshrafE18,
author = {Rizwan A. Ashraf and
Christian Engelmann},
editor = {Gabriele Mencagli and
Dora B. Heras and
Valeria Cardellini and
Emiliano Casalicchio and
Emmanuel Jeannot and
Felix Wolf and
Antonio Salis and
Claudio Schifanella and
Ravi Reddy Manumachu and
Laura Ricci and
Marco Beccuti and
Laura Antonelli and
Jos{\'{e}} Daniel Garc{\'{\i}}a S{\'{a}}nchez and
Stephen L. Scott},
title = {Performance Efficient Multiresilience Using Checkpoint Recovery in
Iterative Algorithms},
booktitle = {Euro-Par 2018: Parallel Processing Workshops - Euro-Par 2018 International
Workshops, Turin, Italy, August 27-28, 2018, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {11339},
pages = {813--825},
publisher = {Springer},
year = {2018},
url = {https://doi.org/10.1007/978-3-030-10549-5\_63},
doi = {10.1007/978-3-030-10549-5\_63},
timestamp = {Fri, 27 Dec 2019 21:26:53 +0100},
biburl = {https://dblp.org/rec/conf/europar/AshrafE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ldav/HuiPE18,
author = {Yawei Hui and
Byung{-}Hoon Park and
Christian Engelmann},
title = {A Comprehensive Informative Metric for Summarizing {HPC} System Status},
booktitle = {8th {IEEE} Symposium on Large Data Analysis and Visualization, {LDAV}
2018, Berlin, Germany, October 21, 2018},
pages = {102--103},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/LDAV.2018.8739234},
doi = {10.1109/LDAV.2018.8739234},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ldav/HuiPE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/AshrafHE18,
author = {Rizwan A. Ashraf and
Saurabh Hukerikar and
Christian Engelmann},
editor = {Ivan Merelli and
Pietro Li{\`{o}} and
Igor V. Kotenko},
title = {Shrink or Substitute: Handling Process Failures in {HPC} Systems Using
In-Situ Recovery},
booktitle = {26th Euromicro International Conference on Parallel, Distributed and
Network-based Processing, {PDP} 2018, Cambridge, United Kingdom, March
21-23, 2018},
pages = {178--185},
publisher = {{IEEE} Computer Society},
year = {2018},
url = {https://doi.org/10.1109/PDP2018.2018.00032},
doi = {10.1109/PDP2018.2018.00032},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/AshrafHE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HuiPE18,
author = {Yawei Hui and
Byung{-}Hoon Park and
Christian Engelmann},
title = {A Comprehensive Informative Metric for Analyzing {HPC} System Status
Using the LogSCAN Platform},
booktitle = {{IEEE/ACM} 8th Workshop on Fault Tolerance for {HPC} at eXtreme Scale,
FTXS@SC 2018, Dallas, TX, USA, November 16, 2018},
pages = {29--38},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/FTXS.2018.00007},
doi = {10.1109/FTXS.2018.00007},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/HuiPE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/AshrafE18,
author = {Rizwan A. Ashraf and
Christian Engelmann},
title = {Analyzing the Impact of System Reliability Events on Applications
in the Titan Supercomputer},
booktitle = {{IEEE/ACM} 8th Workshop on Fault Tolerance for {HPC} at eXtreme Scale,
FTXS@SC 2018, Dallas, TX, USA, November 16, 2018},
pages = {39--48},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/FTXS.2018.00008},
doi = {10.1109/FTXS.2018.00008},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/AshrafE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wosp/AshrafHE18,
author = {Rizwan A. Ashraf and
Saurabh Hukerikar and
Christian Engelmann},
editor = {Katinka Wolter and
William J. Knottenbelt and
Andr{\'{e}} van Hoorn and
Manoj Nambiar},
title = {Pattern-based Modeling of Multiresilience Solutions for High-Performance
Computing},
booktitle = {Proceedings of the 2018 {ACM/SPEC} International Conference on Performance
Engineering, {ICPE} 2018, Berlin, Germany, April 09-13, 2018},
pages = {80--87},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3184407.3184421},
doi = {10.1145/3184407.3184421},
timestamp = {Fri, 02 Jun 2023 16:15:08 +0200},
biburl = {https://dblp.org/rec/conf/wosp/AshrafHE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-04523,
author = {Rizwan A. Ashraf and
Saurabh Hukerikar and
Christian Engelmann},
title = {Shrink or Substitute: Handling Process Failures in {HPC} Systems using
In-situ Recovery},
journal = {CoRR},
volume = {abs/1801.04523},
year = {2018},
url = {http://arxiv.org/abs/1801.04523},
eprinttype = {arXiv},
eprint = {1801.04523},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-04523.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-08233,
author = {Rizwan A. Ashraf and
Saurabh Hukerikar and
Christian Engelmann},
title = {Pattern-based Modeling of Multiresilience Solutions for High-Performance
Computing},
journal = {CoRR},
volume = {abs/1802.08233},
year = {2018},
url = {http://arxiv.org/abs/1802.08233},
eprinttype = {arXiv},
eprint = {1802.08233},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-08233.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/superfri/HukerikarE17,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Resilience Design Patterns: {A} Structured Approach to Resilience
at Extreme Scale},
journal = {Supercomput. Front. Innov.},
volume = {4},
number = {3},
pages = {4--42},
year = {2017},
url = {https://doi.org/10.14529/jsfi170301},
doi = {10.14529/JSFI170301},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/superfri/HukerikarE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/ParkHAE17,
author = {Byung H. Park and
Saurabh Hukerikar and
Ryan Adamson and
Christian Engelmann},
title = {Big Data Meets {HPC} Log Analytics: Scalable Approach to Understanding
Systems at Extreme Scale},
booktitle = {2017 {IEEE} International Conference on Cluster Computing, {CLUSTER}
2017, Honolulu, HI, USA, September 5-8, 2017},
pages = {758--765},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/CLUSTER.2017.113},
doi = {10.1109/CLUSTER.2017.113},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/ParkHAE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/HukerikarE17,
author = {Saurabh Hukerikar and
Christian Engelmann},
editor = {Dora Blanco Heras and
Luc Boug{\'{e}} and
Gabriele Mencagli and
Emmanuel Jeannot and
Rizos Sakellariou and
Rosa M. Badia and
Jorge G. Barbosa and
Laura Ricci and
Stephen L. Scott and
Stefan Lankes and
Josef Weidendorfer},
title = {Pattern-Based Modeling of High-Performance Computing Resilience},
booktitle = {Euro-Par 2017: Parallel Processing Workshops - Euro-Par 2017 International
Workshops, Santiago de Compostela, Spain, August 28-29, 2017, Revised
Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {10659},
pages = {557--568},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-75178-8\_45},
doi = {10.1007/978-3-319-75178-8\_45},
timestamp = {Thu, 14 Oct 2021 10:28:38 +0200},
biburl = {https://dblp.org/rec/conf/europar/HukerikarE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europlop/HukerikarE17,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {A Pattern Language for High-Performance Computing Resilience},
booktitle = {Proceedings of the 22nd European Conference on Pattern Languages of
Programs, EuroPLoP 2017, Irsee, Germany, July 12-16, 2017},
pages = {12:1--12:16},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3147704.3147718},
doi = {10.1145/3147704.3147718},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/europlop/HukerikarE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/HukerikarAE17,
author = {Saurabh Hukerikar and
Rizwan A. Ashraf and
Christian Engelmann},
title = {Towards New Metrics for High-Performance Computing Resilience},
booktitle = {Proceedings of the {ACM} Workshop on Fault-Tolerance for {HPC} at
Extreme Scale, FTXS@HPDC 2017, Washington, DC, USA, June, 2017},
pages = {23--30},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3086157.3086163},
doi = {10.1145/3086157.3086163},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/HukerikarAE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mascots/NieXGEST17,
author = {Bin Nie and
Ji Xue and
Saurabh Gupta and
Christian Engelmann and
Evgenia Smirni and
Devesh Tiwari},
title = {Characterizing Temperature, Power, and Soft-Error Behaviors in Data
Center Systems: Insights, Challenges, and Opportunities},
booktitle = {25th {IEEE} International Symposium on Modeling, Analysis, and Simulation
of Computer and Telecommunication Systems, {MASCOTS} 2017, Banff,
AB, Canada, September 20-22, 2017},
pages = {22--31},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/MASCOTS.2017.12},
doi = {10.1109/MASCOTS.2017.12},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mascots/NieXGEST17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/GuptaPET17,
author = {Saurabh Gupta and
Tirthak Patel and
Christian Engelmann and
Devesh Tiwari},
editor = {Bernd Mohr and
Padma Raghavan},
title = {Failures in large scale systems: long-term measurement, analysis,
and implications},
booktitle = {Proceedings of the International Conference for High Performance Computing,
Networking, Storage and Analysis, {SC} 2017, Denver, CO, USA, November
12 - 17, 2017},
pages = {44},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3126908.3126937},
doi = {10.1145/3126908.3126937},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/GuptaPET17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-06884,
author = {Byung H. Park and
Saurabh Hukerikar and
Ryan Adamson and
Christian Engelmann},
title = {Big Data Meets {HPC} Log Analytics: Scalable Approach to Understanding
Systems at Extreme Scale},
journal = {CoRR},
volume = {abs/1708.06884},
year = {2017},
url = {http://arxiv.org/abs/1708.06884},
eprinttype = {arXiv},
eprint = {1708.06884},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-06884.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-07422,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Resilience Design Patterns: {A} Structured Approach to Resilience
at Extreme Scale},
journal = {CoRR},
volume = {abs/1708.07422},
year = {2017},
url = {http://arxiv.org/abs/1708.07422},
eprinttype = {arXiv},
eprint = {1708.07422},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-07422.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-02627,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Pattern-based Modeling of High-Performance Computing Resilience},
journal = {CoRR},
volume = {abs/1710.02627},
year = {2017},
url = {http://arxiv.org/abs/1710.02627},
eprinttype = {arXiv},
eprint = {1710.02627},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-02627.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-09074,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {A Pattern Language for High-Performance Computing Resilience},
journal = {CoRR},
volume = {abs/1710.09074},
year = {2017},
url = {http://arxiv.org/abs/1710.09074},
eprinttype = {arXiv},
eprint = {1710.09074},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-09074.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/EngelmannN16,
author = {Christian Engelmann and
Thomas J. Naughton},
title = {A new deadlock resolution protocol and message matching algorithm
for the extreme-scale simulator},
journal = {Concurr. Comput. Pract. Exp.},
volume = {28},
number = {12},
pages = {3369--3389},
year = {2016},
url = {https://doi.org/10.1002/cpe.3805},
doi = {10.1002/CPE.3805},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/concurrency/EngelmannN16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dsn/TangTGHLEH16,
author = {Kun Tang and
Devesh Tiwari and
Saurabh Gupta and
Ping Huang and
Qiqi Lu and
Christian Engelmann and
Xubin He},
title = {Power-Capping Aware Checkpointing: On the Interplay Among Power-Capping,
Temperature, Reliability, Performance, and Energy},
booktitle = {46th Annual {IEEE/IFIP} International Conference on Dependable Systems
and Networks, {DSN} 2016, Toulouse, France, June 28 - July 1, 2016},
pages = {311--322},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/DSN.2016.36},
doi = {10.1109/DSN.2016.36},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dsn/TangTGHLEH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dsrt/LagadapatiME16,
author = {Mahesh Lagadapati and
Frank Mueller and
Christian Engelmann},
title = {Benchmark Generation and Simulation at Extreme Scale},
booktitle = {20th {IEEE/ACM} International Symposium on Distributed Simulation
and Real Time Applications, {DS-RT} 2016, London, United Kingdom,
September 21-23, 2016},
pages = {9--18},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/DS-RT.2016.18},
doi = {10.1109/DS-RT.2016.18},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dsrt/LagadapatiME16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/NaughtonEVAS16,
author = {Thomas J. Naughton and
Christian Engelmann and
Geoffroy Vall{\'{e}}e and
Ferrol Aderholdt and
Stephen L. Scott},
editor = {Fr{\'{e}}d{\'{e}}ric Desprez and
Pierre{-}Fran{\c{c}}ois Dutot and
Christos Kaklamanis and
Loris Marchal and
Korbinian Molitorisz and
Laura Ricci and
Vittorio Scarano and
Miguel A. Vega{-}Rodr{\'{\i}}guez and
Ana Lucia Varbanescu and
Sascha Hunold and
Stephen L. Scott and
Stefan Lankes and
Josef Weidendorfer},
title = {A Cooperative Approach to Virtual Machine Based Fault Injection},
booktitle = {Euro-Par 2016: Parallel Processing Workshops - Euro-Par 2016 International
Workshops, Grenoble, France, August 24-26, 2016, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {10104},
pages = {671--682},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-58943-5\_54},
doi = {10.1007/978-3-319-58943-5\_54},
timestamp = {Sun, 12 Nov 2023 02:07:45 +0100},
biburl = {https://dblp.org/rec/conf/europar/NaughtonEVAS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpdc/ParchmanVNEBS16,
author = {Zachary W. Parchman and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Christian Engelmann and
David E. Bernholdt and
Stephen L. Scott},
editor = {Nathan DeBardeleben},
title = {Adding Fault Tolerance to {NPB} Benchmarks Using {ULFM}},
booktitle = {Proceedings of the {ACM} Workshop on Fault-Tolerance for {HPC} at
Extreme Scale, FTXS@HPDC 2016, Kyoto, Japan, May 31, 2016},
pages = {27--34},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2909428.2909434},
doi = {10.1145/2909428.2909434},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpdc/ParchmanVNEBS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpec/HukerikarE16,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Havens: Explicit reliable memory regions for {HPC} applications},
booktitle = {2016 {IEEE} High Performance Extreme Computing Conference, {HPEC}
2016, Waltham, MA, USA, September 13-15, 2016},
pages = {1--6},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/HPEC.2016.7761593},
doi = {10.1109/HPEC.2016.7761593},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/hpec/HukerikarE16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/FialaMFE16,
author = {David Fiala and
Frank Mueller and
Kurt B. Ferreira and
Christian Engelmann},
editor = {Ozcan Ozturk and
Kemal Ebcioglu and
Mahmut T. Kandemir and
Onur Mutlu},
title = {Mini-Ckpts: Surviving {OS} Failures in Persistent Memory},
booktitle = {Proceedings of the 2016 International Conference on Supercomputing,
{ICS} 2016, Istanbul, Turkey, June 1-3, 2016},
pages = {7:1--7:14},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2925426.2926295},
doi = {10.1145/2925426.2926295},
timestamp = {Mon, 22 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/FialaMFE16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/Bautista-GomezG16,
author = {Leonardo Arturo Bautista{-}Gomez and
Ana Gainaru and
Swann Perarnau and
Devesh Tiwari and
Saurabh Gupta and
Christian Engelmann and
Franck Cappello and
Marc Snir},
title = {Reducing Waste in Extreme Scale Systems through Introspective Analysis},
booktitle = {2016 {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2016, Chicago, IL, USA, May 23-27, 2016},
pages = {212--221},
publisher = {{IEEE} Computer Society},
year = {2016},
url = {https://doi.org/10.1109/IPDPS.2016.100},
doi = {10.1109/IPDPS.2016.100},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/Bautista-GomezG16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lcpc/HukerikarE16,
author = {Saurabh Hukerikar and
Christian Engelmann},
editor = {Chen Ding and
John Criswell and
Peng Wu},
title = {Language Support for Reliable Memory Regions},
booktitle = {Languages and Compilers for Parallel Computing - 29th International
Workshop, {LCPC} 2016, Rochester, NY, USA, September 28-30, 2016,
Revised Papers},
series = {Lecture Notes in Computer Science},
volume = {10136},
pages = {73--87},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-52709-3\_6},
doi = {10.1007/978-3-319-52709-3\_6},
timestamp = {Tue, 28 Jul 2020 07:46:49 +0200},
biburl = {https://dblp.org/rec/conf/lcpc/HukerikarE16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HukerikarE16,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Havens: Explicit Reliable Memory Regions for {HPC} Applications},
journal = {CoRR},
volume = {abs/1610.08494},
year = {2016},
url = {http://arxiv.org/abs/1610.08494},
eprinttype = {arXiv},
eprint = {1610.08494},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HukerikarE16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HukerikarE16a,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Resilience Design Patterns - {A} Structured Approach to Resilience
at Extreme Scale},
journal = {CoRR},
volume = {abs/1611.02717},
year = {2016},
url = {http://arxiv.org/abs/1611.02717},
eprinttype = {arXiv},
eprint = {1611.02717},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HukerikarE16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HukerikarE16b,
author = {Saurabh Hukerikar and
Christian Engelmann},
title = {Language Support for Reliable Memory Regions},
journal = {CoRR},
volume = {abs/1611.02823},
year = {2016},
url = {http://arxiv.org/abs/1611.02823},
eprinttype = {arXiv},
eprint = {1611.02823},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HukerikarE16b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/KattiFNE15,
author = {Amogh Katti and
Giuseppe Di Fatta and
Thomas J. Naughton and
Christian Engelmann},
editor = {Jack J. Dongarra and
Alexandre Denis and
Brice Goglin and
Emmanuel Jeannot and
Guillaume Mercier},
title = {Scalable and Fault Tolerant Failure Detection and Consensus},
booktitle = {Proceedings of the 22nd European {MPI} Users' Group Meeting, EuroMPI
2015, Bordeaux, France, September 21-23, 2015},
pages = {13:1--13:9},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2802658.2802660},
doi = {10.1145/2802658.2802660},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/KattiFNE15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/Engelmann14,
author = {Christian Engelmann},
title = {Scaling to a million cores and beyond: Using light-weight simulation
to understand the challenges ahead on the road to exascale},
journal = {Future Gener. Comput. Syst.},
volume = {30},
pages = {59--65},
year = {2014},
url = {https://doi.org/10.1016/j.future.2013.04.014},
doi = {10.1016/J.FUTURE.2013.04.014},
timestamp = {Wed, 19 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/fgcs/Engelmann14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/SnirWAABBBBCCCCDDEEFGGJKLLMMSSH14,
author = {Marc Snir and
Robert W. Wisniewski and
Jacob A. Abraham and
Sarita V. Adve and
Saurabh Bagchi and
Pavan Balaji and
James F. Belak and
Pradip Bose and
Franck Cappello and
Bill Carlson and
Andrew A. Chien and
Paul Coteus and
Nathan DeBardeleben and
Pedro C. Diniz and
Christian Engelmann and
Mattan Erez and
Saverio Fazzari and
Al Geist and
Rinku Gupta and
Fred Johnson and
Sriram Krishnamoorthy and
Sven Leyffer and
Dean Liberty and
Subhasish Mitra and
Todd S. Munson and
Rob Schreiber and
Jon Stearley and
Eric Van Hensbergen},
title = {Addressing failures in exascale computing},
journal = {Int. J. High Perform. Comput. Appl.},
volume = {28},
number = {2},
pages = {129--173},
year = {2014},
url = {https://doi.org/10.1177/1094342014522573},
doi = {10.1177/1094342014522573},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijhpca/SnirWAABBBBCCCCDDEEFGGJKLLMMSSH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dsrt/EngelmannN14,
author = {Christian Engelmann and
Thomas J. Naughton},
title = {Improving the Performance of the Extreme-Scale Simulator},
booktitle = {18th {IEEE/ACM} International Symposium on Distributed Simulation
and Real Time Applications, {DS-RT} 2014, Toulouse, France, October
1-3, 2014},
pages = {198--207},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/DS-RT.2014.32},
doi = {10.1109/DS-RT.2014.32},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dsrt/EngelmannN14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/NaughtonSEVAS14,
author = {Thomas J. Naughton and
Garry Smith and
Christian Engelmann and
Geoffroy Vall{\'{e}}e and
Ferrol Aderholdt and
Stephen L. Scott},
editor = {Lu{\'{\i}}s M. B. Lopes and
Julius Zilinskas and
Alexandru Costan and
Roberto G. Cascella and
Gabor Kecskemeti and
Emmanuel Jeannot and
Mario Cannataro and
Laura Ricci and
Siegfried Benkner and
Salvador Petit and
Vittorio Scarano and
Jos{\'{e}} Gracia and
Sascha Hunold and
Stephen L. Scott and
Stefan Lankes and
Christian Lengauer and
Jes{\'{u}}s Carretero and
Jens Breitbart and
Michael Alexander},
title = {What Is the Right Balance for Performance and Isolation with Virtualization
in HPC?},
booktitle = {Euro-Par 2014: Parallel Processing Workshops - Euro-Par 2014 International
Workshops, Porto, Portugal, August 25-26, 2014, Revised Selected Papers,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {8805},
pages = {570--581},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-14325-5\_49},
doi = {10.1007/978-3-319-14325-5\_49},
timestamp = {Sun, 12 Nov 2023 02:07:45 +0100},
biburl = {https://dblp.org/rec/conf/europar/NaughtonSEVAS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/NaughtonEVB14,
author = {Thomas J. Naughton and
Christian Engelmann and
Geoffroy Vall{\'{e}}e and
Swen B{\"{o}}hm},
title = {Supporting the Development of Resilient Message Passing Applications
Using Simulation},
booktitle = {22nd Euromicro International Conference on Parallel, Distributed,
and Network-Based Processing, {PDP} 2014, Torino, Italy, February
12-14, 2014},
pages = {271--278},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/PDP.2014.74},
doi = {10.1109/PDP.2014.74},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/NaughtonEVB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/sc/2014scala,
editor = {Vassil Alexandrov and
Al Geist and
Christian Engelmann},
title = {Proceedings of the 5th Workshop on Latest Advances in Scalable Algorithms
for Large-Scale Systems, ScalA '14, New Orleans, Louisiana, USA, November
16-21, 2014},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://ieeexplore.ieee.org/xpl/conhome/7015710/proceeding},
isbn = {978-1-4799-7562-4},
timestamp = {Wed, 12 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sc/2014scala.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/NaughtonBEV13,
author = {Thomas J. Naughton and
Swen B{\"{o}}hm and
Christian Engelmann and
Geoffroy Vall{\'{e}}e},
editor = {Dieter an Mey and
Michael Alexander and
Paolo Bientinesi and
Mario Cannataro and
Carsten Clauss and
Alexandru Costan and
Gabor Kecskemeti and
Christine Morin and
Laura Ricci and
Julio Sahuquillo and
Martin Schulz and
Vittorio Scarano and
Stephen L. Scott and
Josef Weidendorfer},
title = {Using Performance Tools to Support Experiments in {HPC} Resilience},
booktitle = {Euro-Par 2013: Parallel Processing Workshops - BigDataCloud, DIHC,
FedICI, HeteroPar, HiBB, LSDVE, MHPC, OMHI, PADABS, PROPER, Resilience,
ROME, and {UCHPC} 2013, Aachen, Germany, August 26-27, 2013. Revised
Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {8374},
pages = {727--736},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-54420-0\_71},
doi = {10.1007/978-3-642-54420-0\_71},
timestamp = {Wed, 19 Feb 2020 14:52:57 +0100},
biburl = {https://dblp.org/rec/conf/europar/NaughtonBEV13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ic-nc/ValleeNBE13,
author = {Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Swen B{\"{o}}hm and
Christian Engelmann},
editor = {Juan E. Guerrero},
title = {A Runtime Environment for Supporting Research in Resilient {HPC} System
Software {\&} Tools},
booktitle = {The First International Symposium on Computing and Networking - Across
Practical Development and Theoretical Research, Dogo {SPA} Resort,
Matsuyama, Japan, December 4-6, 2013},
pages = {213--219},
publisher = {{IEEE} Computer Society},
year = {2013},
url = {https://doi.org/10.1109/CANDAR.2013.38},
doi = {10.1109/CANDAR.2013.38},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ic-nc/ValleeNBE13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/EngelmannN13,
author = {Christian Engelmann and
Thomas J. Naughton},
title = {Toward a Performance/Resilience Tool for Hardware/Software Co-design
of High-Performance Computing Systems},
booktitle = {42nd International Conference on Parallel Processing, {ICPP} 2013,
Lyon, France, October 1-4, 2013},
pages = {960--969},
publisher = {{IEEE} Computer Society},
year = {2013},
url = {https://doi.org/10.1109/ICPP.2013.114},
doi = {10.1109/ICPP.2013.114},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpp/EngelmannN13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ptw/LagadapatiME13,
author = {Mahesh Lagadapati and
Frank Mueller and
Christian Engelmann},
editor = {Andreas Kn{\"{u}}pfer and
Jos{\'{e}} Gracia and
Wolfgang E. Nagel and
Michael M. Resch},
title = {Tools for Simulation and Benchmark Generation at Exascale},
booktitle = {Tools for High Performance Computing 2013, Proceedings of the 7th
International Workshop on Parallel Tools for High Performance Computing,
September 2013, ZIH, Dresden, Germany},
pages = {19--24},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-319-08144-1\_2},
doi = {10.1007/978-3-319-08144-1\_2},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ptw/LagadapatiME13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jpdc/WangMES12,
author = {Chao Wang and
Frank Mueller and
Christian Engelmann and
Stephen L. Scott},
title = {Proactive process-level live migration and back migration in {HPC}
environments},
journal = {J. Parallel Distributed Comput.},
volume = {72},
number = {2},
pages = {254--267},
year = {2012},
url = {https://doi.org/10.1016/j.jpdc.2011.10.009},
doi = {10.1016/J.JPDC.2011.10.009},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jpdc/WangMES12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdcs/ElliottKFMFE12,
author = {James Elliott and
Kishor Kharbas and
David Fiala and
Frank Mueller and
Kurt B. Ferreira and
Christian Engelmann},
title = {Combining Partial Redundancy and Checkpointing for {HPC}},
booktitle = {2012 {IEEE} 32nd International Conference on Distributed Computing
Systems, Macau, China, June 18-21, 2012},
pages = {615--626},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/ICDCS.2012.56},
doi = {10.1109/ICDCS.2012.56},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdcs/ElliottKFMFE12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/WangVMMKE12,
author = {Chao Wang and
Sudharshan S. Vazhkudai and
Xiaosong Ma and
Fei Meng and
Youngjae Kim and
Christian Engelmann},
title = {NVMalloc: Exposing an Aggregate {SSD} Store as a Memory Partition
in Extreme-Scale Machines},
booktitle = {26th {IEEE} International Parallel and Distributed Processing Symposium,
{IPDPS} 2012, Shanghai, China, May 21-25, 2012},
pages = {957--968},
publisher = {{IEEE} Computer Society},
year = {2012},
url = {https://doi.org/10.1109/IPDPS.2012.90},
doi = {10.1109/IPDPS.2012.90},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/WangVMMKE12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/BohmE12,
author = {Swen B{\"{o}}hm and
Christian Engelmann},
editor = {Rainer Stotzka and
Michael Schiffers and
Yannis Cotronis},
title = {File {I/O} for {MPI} Applications in Redundant Execution Scenarios},
booktitle = {Proceedings of the 20th Euromicro International Conference on Parallel,
Distributed and Network-Based Processing, {PDP} 2012, Munich, Germany,
February 15-17, 2012},
pages = {112--119},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/PDP.2012.22},
doi = {10.1109/PDP.2012.22},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/BohmE12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/FialaMERFB12,
author = {David Fiala and
Frank Mueller and
Christian Engelmann and
Rolf Riesen and
Kurt B. Ferreira and
Ron Brightwell},
editor = {Jeffrey K. Hollingsworth},
title = {Detection and correction of silent data corruption for large-scale
high-performance computing},
booktitle = {{SC} Conference on High Performance Computing Networking, Storage
and Analysis, {SC} '12, Salt Lake City, UT, {USA} - November 11 -
15, 2012},
pages = {78},
publisher = {{IEEE/ACM}},
year = {2012},
url = {https://doi.org/10.1109/SC.2012.49},
doi = {10.1109/SC.2012.49},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/FialaMERFB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/NaughtonVES11,
author = {Thomas J. Naughton and
Geoffroy Vall{\'{e}}e and
Christian Engelmann and
Stephen L. Scott},
editor = {Michael Alexander and
Pasqua D'Ambra and
Adam Belloum and
George Bosilca and
Mario Cannataro and
Marco Danelutto and
Beniamino Di Martino and
Michael Gerndt and
Emmanuel Jeannot and
Raymond Namyst and
Jean Roman and
Stephen L. Scott and
Jesper Larsson Tr{\"{a}}ff and
Geoffroy Vall{\'{e}}e and
Josef Weidendorfer},
title = {A Case for Virtual Machine Based Fault Injection in a High-Performance
Computing Environment},
booktitle = {Euro-Par 2011: Parallel Processing Workshops - CCPI, CGWS, HeteroPar,
HiBB, HPCVirt, HPPC, HPSS, MDGS, ProPer, Resilience, UCHPC, VHPC,
Bordeaux, France, August 29 - September 2, 2011, Revised Selected
Papers, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {7155},
pages = {234--243},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-29737-3\_27},
doi = {10.1007/978-3-642-29737-3\_27},
timestamp = {Wed, 19 Feb 2020 14:52:57 +0100},
biburl = {https://dblp.org/rec/conf/europar/NaughtonVES11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/FialaFME11,
author = {David Fiala and
Kurt B. Ferreira and
Frank Mueller and
Christian Engelmann},
editor = {Michael Alexander and
Pasqua D'Ambra and
Adam Belloum and
George Bosilca and
Mario Cannataro and
Marco Danelutto and
Beniamino Di Martino and
Michael Gerndt and
Emmanuel Jeannot and
Raymond Namyst and
Jean Roman and
Stephen L. Scott and
Jesper Larsson Tr{\"{a}}ff and
Geoffroy Vall{\'{e}}e and
Josef Weidendorfer},
title = {A Tunable, Software-Based {DRAM} Error Detection and Correction Library
for {HPC}},
booktitle = {Euro-Par 2011: Parallel Processing Workshops - CCPI, CGWS, HeteroPar,
HiBB, HPCVirt, HPPC, HPSS, MDGS, ProPer, Resilience, UCHPC, VHPC,
Bordeaux, France, August 29 - September 2, 2011, Revised Selected
Papers, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {7156},
pages = {251--261},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-29740-3\_29},
doi = {10.1007/978-3-642-29740-3\_29},
timestamp = {Mon, 22 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/europar/FialaFME11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icppw/JonesE11,
author = {Ian S. Jones and
Christian Engelmann},
editor = {Jang{-}Ping Sheu and
Cho{-}Li Wang},
title = {Simulation of Large-Scale {HPC} Architectures},
booktitle = {2011 International Conference on Parallel Processing Workshops, {ICPPW}
2011, Taipei, Taiwan, Sept. 13-16, 2011},
pages = {447--456},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/ICPPW.2011.44},
doi = {10.1109/ICPPW.2011.44},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icppw/JonesE11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ieeehpcs/BohmE11,
author = {Swen B{\"{o}}hm and
Christian Engelmann},
editor = {Waleed W. Smari and
John P. McIntire},
title = {xSim: The extreme-scale simulator},
booktitle = {2011 International Conference on High Performance Computing {\&}
Simulation, {HPCS} 2012, Istanbul, Turkey, July 4-8, 2011},
pages = {280--286},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/HPCSim.2011.5999835},
doi = {10.1109/HPCSIM.2011.5999835},
timestamp = {Tue, 28 Jul 2020 13:09:02 +0200},
biburl = {https://dblp.org/rec/conf/ieeehpcs/BohmE11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/FialaMERF11,
author = {David Fiala and
Frank Mueller and
Christian Engelmann and
Rolf Riesen and
Kurt B. Ferreira},
editor = {Scott A. Lathrop and
Jim Costa and
William Kramer},
title = {Poster: detection and correction of silent data corruption for large-scale
high-performance computing},
booktitle = {Conference on High Performance Computing Networking, Storage and Analysis
- Companion Volume, {SC} 2011, Seattle, WA, USA, November 12-18, 2011},
pages = {47--48},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2148600.2148625},
doi = {10.1145/2148600.2148625},
timestamp = {Mon, 22 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/FialaMERF11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/FialaFME11,
author = {David Fiala and
Kurt B. Ferreira and
Frank Mueller and
Christian Engelmann},
editor = {Scott A. Lathrop and
Jim Costa and
William Kramer},
title = {Poster: a tunable, software-based {DRAM} error detection and correction
library for {HPC}},
booktitle = {Conference on High Performance Computing Networking, Storage and Analysis
- Companion Volume, {SC} 2011, Seattle, WA, USA, November 12-18, 2011},
pages = {49--50},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2148600.2148626},
doi = {10.1145/2148600.2148626},
timestamp = {Mon, 22 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/FialaFME11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/ScottVNTEO10,
author = {Stephen L. Scott and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Anand Tikotekar and
Christian Engelmann and
Hong Ong},
title = {System-level virtualization research at Oak Ridge National Laboratory},
journal = {Future Gener. Comput. Syst.},
volume = {26},
number = {3},
pages = {304--307},
year = {2010},
url = {https://doi.org/10.1016/j.future.2009.07.001},
doi = {10.1016/J.FUTURE.2009.07.001},
timestamp = {Wed, 19 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/fgcs/ScottVNTEO10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpcc/BohmES10,
author = {Swen B{\"{o}}hm and
Christian Engelmann and
Stephen L. Scott},
title = {Aggregation of Real-Time System Monitoring Data for Analyzing Large-Scale
Parallel and Distributed Computing Environments},
booktitle = {12th {IEEE} International Conference on High Performance Computing
and Communications, {HPCC} 2010, 1-3 September 2010, Melbourne, Australia},
pages = {72--78},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/HPCC.2010.32},
doi = {10.1109/HPCC.2010.32},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/hpcc/BohmES10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpads/WangMES10,
author = {Chao Wang and
Frank Mueller and
Christian Engelmann and
Stephen L. Scott},
title = {Hybrid Checkpointing for {MPI} Jobs in {HPC} Environments},
booktitle = {16th {IEEE} International Conference on Parallel and Distributed Systems,
{ICPADS} 2010, Shanghai, China, December 8-10, 2010},
pages = {524--533},
publisher = {{IEEE} Computer Society},
year = {2010},
url = {https://doi.org/10.1109/ICPADS.2010.48},
doi = {10.1109/ICPADS.2010.48},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpads/WangMES10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/LiVBMMKES10,
author = {Min Li and
Sudharshan S. Vazhkudai and
Ali Raza Butt and
Fei Meng and
Xiaosong Ma and
Youngjae Kim and
Christian Engelmann and
Galen M. Shipman},
title = {Functional Partitioning to Optimize End-to-End Performance on Many-core
Architectures},
booktitle = {Conference on High Performance Computing Networking, Storage and Analysis,
{SC} 2010, New Orleans, LA, USA, November 13-19, 2010},
pages = {1--12},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/SC.2010.28},
doi = {10.1109/SC.2010.28},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/LiVBMMKES10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jpdc/HeOECS09,
author = {Xubin He and
Li Ou and
Christian Engelmann and
Xin Chen and
Stephen L. Scott},
title = {Symmetric active/active metadata service for high availability parallel
file systems},
journal = {J. Parallel Distributed Comput.},
volume = {69},
number = {12},
pages = {961--973},
year = {2009},
url = {https://doi.org/10.1016/j.jpdc.2009.08.004},
doi = {10.1016/J.JPDC.2009.08.004},
timestamp = {Sun, 22 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jpdc/HeOECS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEares/TaeratNCELOSE09,
author = {Narate Taerat and
Nichamon Naksinehaboon and
Clayton Chandler and
James Elliott and
Chokchai Leangsuksun and
George Ostrouchov and
Stephen L. Scott and
Christian Engelmann},
title = {Blue Gene/L Log Analysis and Time to Interrupt Estimation},
booktitle = {Proceedings of the The Forth International Conference on Availability,
Reliability and Security, {ARES} 2009, March 16-19, 2009, Fukuoka,
Japan},
pages = {173--180},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/ARES.2009.105},
doi = {10.1109/ARES.2009.105},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEares/TaeratNCELOSE09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eurosys/TikotekarOAVNES09,
author = {Anand Tikotekar and
Hong Ong and
Sadaf R. Alam and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Christian Engelmann and
Stephen L. Scott},
editor = {Stephen L. Scott and
Geoffroy Vall{\'{e}}e},
title = {Performance comparison of two virtual machine scenarios using an {HPC}
application: a case study using molecular dynamics simulations},
booktitle = {Proceedings of the 3rd {ACM} Workshop on System-level Virtualization
for High Performance Computing, HPCVirt '09, Nuremburg, Germany, March
31, 2009},
pages = {33--40},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1519138.1519143},
doi = {10.1145/1519138.1519143},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eurosys/TikotekarOAVNES09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/ValentiniBBPPE09,
author = {Alessandro Valentini and
Christian Di Biagio and
Fabrizio Batino and
Guido Pennella and
Fabrizio Palma and
Christian Engelmann},
editor = {Didier El Baz and
Fran{\c{c}}ois Spies and
Tom Gross},
title = {High Performance Computing with Harness over InfiniBand},
booktitle = {Proceedings of the 17th Euromicro International Conference on Parallel,
Distributed and Network-Based Processing, {PDP} 2009, Weimar, Germany,
18-20 Febuary 2009},
pages = {151--154},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/PDP.2009.64},
doi = {10.1109/PDP.2009.64},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/ValentiniBBPPE09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/EngelmannVNS09,
author = {Christian Engelmann and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Stephen L. Scott},
editor = {Didier El Baz and
Fran{\c{c}}ois Spies and
Tom Gross},
title = {Proactive Fault Tolerance Using Preemptive Migration},
booktitle = {Proceedings of the 17th Euromicro International Conference on Parallel,
Distributed and Network-Based Processing, {PDP} 2009, Weimar, Germany,
18-20 Febuary 2009},
pages = {252--257},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/PDP.2009.31},
doi = {10.1109/PDP.2009.31},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/EngelmannVNS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/ScottEVNTOLNNPMWNV09,
author = {Stephen L. Scott and
Christian Engelmann and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Anand Tikotekar and
George Ostrouchov and
Chokchai Leangsuksun and
Nichamon Naksinehaboon and
Raja Nassar and
Mihaela Paun and
Frank Mueller and
Chao Wang and
Arun Babu Nagarajan and
Jyothish Varma},
editor = {Daniel A. Reed and
Vivek Sarkar},
title = {A tunable holistic resiliency approach for high-performance computing
systems},
booktitle = {Proceedings of the 14th {ACM} {SIGPLAN} Symposium on Principles and
Practice of Parallel Programming, {PPOPP} 2009, Raleigh, NC, USA,
February 14-18, 2009},
pages = {305--306},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1504176.1504227},
doi = {10.1145/1504176.1504227},
timestamp = {Sun, 12 Jun 2022 19:46:08 +0200},
biburl = {https://dblp.org/rec/conf/ppopp/ScottEVNTOLNNPMWNV09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEares/EngelmannSLH08,
author = {Christian Engelmann and
Stephen L. Scott and
Chokchai Leangsuksun and
Xubin He},
title = {Symmetric Active/Active Replication for Dependent Services},
booktitle = {Proceedings of the The Third International Conference on Availability,
Reliability and Security, {ARES} 2008, March 4-7, 2008, Technical
University of Catalonia, Barcelona , Spain},
pages = {260--267},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/ARES.2008.64},
doi = {10.1109/ARES.2008.64},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEares/EngelmannSLH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEares/ValleeCETLNS08,
author = {Geoffroy Vall{\'{e}}e and
Kulathep Charoenpornwattana and
Christian Engelmann and
Anand Tikotekar and
Chokchai Leangsuksun and
Thomas J. Naughton and
Stephen L. Scott},
title = {A Framework for Proactive Fault Tolerance},
booktitle = {Proceedings of the The Third International Conference on Availability,
Reliability and Security, {ARES} 2008, March 4-7, 2008, Technical
University of Catalonia, Barcelona , Spain},
pages = {659--664},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/ARES.2008.171},
doi = {10.1109/ARES.2008.171},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEares/ValleeCETLNS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/EngelmannSLH08,
author = {Christian Engelmann and
Stephen L. Scott and
Chokchai Leangsuksun and
Xubin He},
title = {Symmetric Active/Active High Availability for High-Performance Computing
System Services: Accomplishments and Limitations},
booktitle = {8th {IEEE} International Symposium on Cluster Computing and the Grid
(CCGrid 2008), 19-22 May 2008, Lyon, France},
pages = {813--818},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/CCGRID.2008.78},
doi = {10.1109/CCGRID.2008.78},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ccgrid/EngelmannSLH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/TikotekarVNOES08,
author = {Anand Tikotekar and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Hong Ong and
Christian Engelmann and
Stephen L. Scott},
editor = {Eduardo C{\'{e}}sar and
Michael Alexander and
Achim Streit and
Jesper Larsson Tr{\"{a}}ff and
Christophe C{\'{e}}rin and
Andreas Kn{\"{u}}pfer and
Dieter Kranzlm{\"{u}}ller and
Shantenu Jha},
title = {An Analysis of {HPC} Benchmarks in Virtual Machine Environments},
booktitle = {Euro-Par 2008 Workshops - Parallel Processing, {VHPC} 2008, {UNICORE}
2008, {HPPC} 2008, {SGS} 2008, {PROPER} 2008, {ROIA} 2008, and {DPA}
2008, Las Palmas de Gran Canaria, Spain, August 25-26, 2008, Revised
Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {5415},
pages = {63--71},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-642-00955-6\_8},
doi = {10.1007/978-3-642-00955-6\_8},
timestamp = {Tue, 07 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/europar/TikotekarVNOES08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eurosys/TikotekarVNOESF08,
author = {Anand Tikotekar and
Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Hong Ong and
Christian Engelmann and
Stephen L. Scott and
Anthony M. Filippi},
editor = {Stephen L. Scott and
Geoffroy Vall{\'{e}}e},
title = {Effects of virtualization on a scientific application running a hyperspectral
radiative transfer code on virtual machines},
booktitle = {Proceedings of the 2nd Workshop on System-Level Virtualization for
High Performance Computing, HPCVirt '08, Glasgow, Scotland, USA, March
31, 2008},
pages = {16--23},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1435452.1435455},
doi = {10.1145/1435452.1435455},
timestamp = {Tue, 07 Nov 2023 11:31:29 +0100},
biburl = {https://dblp.org/rec/conf/eurosys/TikotekarVNOESF08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/KonningESG08,
author = {Bj{\"{o}}rn K{\"{o}}nning and
Christian Engelmann and
Stephen L. Scott and
Al Geist},
title = {Virtualized Environments for the Harness High Performance Computing
Workbench},
booktitle = {16th Euromicro International Conference on Parallel, Distributed and
Network-Based Processing {(PDP} 2008), 13-15 February 2008, Toulouse,
France},
pages = {133--140},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/PDP.2008.14},
doi = {10.1109/PDP.2008.14},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/KonningESG08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pdp/ValleeNEOS08,
author = {Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Christian Engelmann and
Hong Ong and
Stephen L. Scott},
title = {System-Level Virtualization for High Performance Computing},
booktitle = {16th Euromicro International Conference on Parallel, Distributed and
Network-Based Processing {(PDP} 2008), 13-15 February 2008, Toulouse,
France},
pages = {636--643},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/PDP.2008.85},
doi = {10.1109/PDP.2008.85},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pdp/ValleeNEOS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/WangMES08,
author = {Chao Wang and
Frank Mueller and
Christian Engelmann and
Stephen L. Scott},
title = {Proactive process-level live migration in {HPC} environments},
booktitle = {Proceedings of the {ACM/IEEE} Conference on High Performance Computing,
{SC} 2008, November 15-21, 2008, Austin, Texas, {USA}},
pages = {43},
publisher = {{IEEE/ACM}},
year = {2008},
url = {https://doi.org/10.1109/SC.2008.5222634},
doi = {10.1109/SC.2008.5222634},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/sc/WangMES08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/svm2/ValleeNOTEBAS08,
author = {Geoffroy Vall{\'{e}}e and
Thomas J. Naughton and
Hong Ong and
Anand Tikotekar and
Christian Engelmann and
Wesley Bland and
Ferrol Aderholdt and
Stephen L. Scott},
editor = {Latifa Boursas and
Mark Carlson and
Wolfgang Hommel and
Michelle Sibilla and
Kes Wold},
title = {Virtual System Environments},
booktitle = {Systems and Virtualization Management. Standards and New Technologies
- Second International Workshop, {SVM} 2008, Munich, Germany, October,
21-22, 2008 Proceedings},
series = {Communications in Computer and Information Science},
volume = {18},
pages = {72--83},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-88708-9\_7},
doi = {10.1007/978-3-540-88708-9\_7},
timestamp = {Tue, 07 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/svm2/ValleeNOTEBAS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpcn/HeOKSE07,
author = {Xubin (Ben) He and
Li Ou and
Martha J. Kosa and
Stephen L. Scott and
Christian Engelmann},
title = {A unified multiple-level cache for high performance storage systems},
journal = {Int. J. High Perform. Comput. Netw.},
volume = {5},
number = {1/2},
pages = {97--109},
year = {2007},
url = {https://doi.org/10.1504/IJHPCN.2007.015768},
doi = {10.1504/IJHPCN.2007.015768},
timestamp = {Thu, 09 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijhpcn/HeOKSE07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEares/EngelmannSLH07,
author = {Christian Engelmann and
Stephen L. Scott and
Chokchai Leangsuksun and
Xubin He},
title = {On Programming Models for Service-Level High Availability},
booktitle = {Proceedings of the The Second International Conference on Availability,
Reliability and Security, {ARES} 2007, The International Dependability
Conference - Bridging Theory and Practice, April 10-13 2007, Vienna,
Austria},
pages = {999--1008},
publisher = {{IEEE} Computer Society},
year = {2007},
url = {https://doi.org/10.1109/ARES.2007.109},
doi = {10.1109/ARES.2007.109},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEares/EngelmannSLH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/EngelmannSLH07,
author = {Christian Engelmann and
Stephen L. Scott and
Chokchai Leangsuksun and
Xubin He},
title = {Transparent Symmetric Active/Active Replication for Service-Level
High Availability},
booktitle = {Seventh {IEEE} International Symposium on Cluster Computing and the
Grid (CCGrid 2007), 14-17 May 2007, Rio de Janeiro, Brazil},
pages = {755--760},
publisher = {{IEEE} Computer Society},
year = {2007},
url = {https://doi.org/10.1109/CCGRID.2007.116},
doi = {10.1109/CCGRID.2007.116},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ccgrid/EngelmannSLH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccS/EngelmannOS07,
author = {Christian Engelmann and
Hong Ong and
Stephen L. Scott},
editor = {Yong Shi and
G. Dick van Albada and
Jack J. Dongarra and
Peter M. A. Sloot},
title = {Middleware in Modern High Performance Computing System Architectures},
booktitle = {Computational Science - {ICCS} 2007, 7th International Conference,
Beijing, China, May 27 - 30, 2007, Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {4488},
pages = {784--791},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-72586-2\_111},
doi = {10.1007/978-3-540-72586-2\_111},
timestamp = {Tue, 08 Nov 2022 08:34:34 +0100},
biburl = {https://dblp.org/rec/conf/iccS/EngelmannOS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icccn/OuHES07,
author = {Li Ou and
Xubin He and
Christian Engelmann and
Stephen L. Scott},
title = {A Fast Delivery Protocol for Total Order Broadcasting},
booktitle = {Proceedings of the 16th International Conference on Computer Communications
and Networks, {IEEE} {ICCCN} 2007, Turtle Bay Resort, Honolulu, Hawaii,
USA, August 13-16, 2007},
pages = {730--734},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICCCN.2007.4317904},
doi = {10.1109/ICCCN.2007.4317904},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/icccn/OuHES07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/NagarajanMES07,
author = {Arun Babu Nagarajan and
Frank Mueller and
Christian Engelmann and
Stephen L. Scott},
editor = {Burton J. Smith},
title = {Proactive fault tolerance for {HPC} with Xen virtualization},
booktitle = {Proceedings of the 21th Annual International Conference on Supercomputing,
{ICS} 2007, Seattle, Washington, USA, June 17-21, 2007},
pages = {23--32},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1274971.1274978},
doi = {10.1145/1274971.1274978},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/NagarajanMES07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/WangMES07,
author = {Chao Wang and
Frank Mueller and
Christian Engelmann and
Stephen L. Scott},
title = {A Job Pause Service under {LAM/MPI+BLCR} for Transparent Fault Tolerance},
booktitle = {21th International Parallel and Distributed Processing Symposium {(IPDPS}
2007), Proceedings, 26-30 March 2007, Long Beach, California, {USA}},
pages = {1--10},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/IPDPS.2007.370307},
doi = {10.1109/IPDPS.2007.370307},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/WangMES07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/SaverioCBPE07,
author = {Emanuele Di Saverio and
Marco Cesati and
Christian Di Biagio and
Guido Pennella and
Christian Engelmann},
editor = {Franck Cappello and
Thomas H{\'{e}}rault and
Jack J. Dongarra},
title = {Distributed Real-Time Computing with Harness},
booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface,
14th European {PVM/MPI} User's Group Meeting, Paris, France, September
30 - October 3, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4757},
pages = {281--288},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-75416-9\_39},
doi = {10.1007/978-3-540-75416-9\_39},
timestamp = {Tue, 07 May 2024 20:11:00 +0200},
biburl = {https://dblp.org/rec/conf/pvm/SaverioCBPE07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jcp/EngelmannSLH06,
author = {Christian Engelmann and
Stephen L. Scott and
Chokchai Leangsuksun and
Xubin (Ben) He},
title = {Symmetric Active/Active High Availability for High-Performance Computing
System Services},
journal = {J. Comput.},
volume = {1},
number = {8},
pages = {43--54},
year = {2006},
url = {http://www.jcomputers.us/index.php?m=content\&\#38;c=index\&\#38;a=show\&\#38;catid=95\&\#38;id=1222},
doi = {10.4304/JCP.1.8.43-54},
timestamp = {Thu, 25 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jcp/EngelmannSLH06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigops/EngelmannSBGLVWMSS06,
author = {Christian Engelmann and
Stephen L. Scott and
David E. Bernholdt and
Narasimha Raju Gottumukkala and
Chokchai Leangsuksun and
Jyothish Varma and
Chao Wang and
Frank Mueller and
Aniruddha G. Shet and
P. Sadayappan},
title = {{MOLAR:} adaptive runtime support for high-end computing operating
and runtime systems},
journal = {{ACM} {SIGOPS} Oper. Syst. Rev.},
volume = {40},
number = {2},
pages = {63--72},
year = {2006},
url = {https://doi.org/10.1145/1131322.1131337},
doi = {10.1145/1131322.1131337},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/sigops/EngelmannSBGLVWMSS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEares/EngelmannSLH06,
author = {Christian Engelmann and
Stephen L. Scott and
Chokchai Leangsuksun and
Xubin (Ben) He},
title = {Active/Active Replication for Highly Available {HPC} System Services},
booktitle = {Proceedings of the The First International Conference on Availability,
Reliability and Security, {ARES} 2006, The International Dependability
Conference - Bridging Theory and Practice, April 20-22 2006, Vienna
University of Technology, Austria},
pages = {639--645},
publisher = {{IEEE} Computer Society},
year = {2006},
url = {https://doi.org/10.1109/ARES.2006.23},
doi = {10.1109/ARES.2006.23},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEares/EngelmannSLH06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/UhlemannES06,
author = {Kai Uhlemann and
Christian Engelmann and
Stephen L. Scott},
title = {{JOSHUA:} Symmetric Active/Active Replication for Highly Available
{HPC} Job and Resource Management},
booktitle = {Proceedings of the 2006 {IEEE} International Conference on Cluster
Computing, September 25-28, 2006, Barcelona, Spain},
publisher = {{IEEE} Computer Society},
year = {2006},
url = {https://doi.org/10.1109/CLUSTR.2006.311855},
doi = {10.1109/CLUSTR.2006.311855},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/UhlemannES06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpcc/BaumannEG06,
author = {Ronald Baumann and
Christian Engelmann and
Al Geist},
editor = {Michael Gerndt and
Dieter Kranzlm{\"{u}}ller},
title = {A Parallel Plug-In Programming Paradigm},
booktitle = {High Performance Computing and Communications, Second International
Conference, {HPCC} 2006, Munich, Germany, September 13-15, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4208},
pages = {823--832},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11847366\_85},
doi = {10.1007/11847366\_85},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/hpcc/BaumannEG06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccS/EngelmannG06,
author = {Christian Engelmann and
Al Geist},
editor = {Vassil N. Alexandrov and
G. Dick van Albada and
Peter M. A. Sloot and
Jack J. Dongarra},
title = {{RMIX:} {A} Dynamic, Heterogeneous, Reconfigurable Communication Framework},
booktitle = {Computational Science - {ICCS} 2006, 6th International Conference,
Reading, UK, May 28-31, 2006, Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {3992},
pages = {573--580},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11758525\_77},
doi = {10.1007/11758525\_77},
timestamp = {Tue, 14 May 2019 10:00:48 +0200},
biburl = {https://dblp.org/rec/conf/iccS/EngelmannG06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ics/VarmaWMES06,
author = {Jyothish Varma and
Chao Wang and
Frank Mueller and
Christian Engelmann and
Stephen L. Scott},
editor = {Gregory K. Egan and
Yoichi Muraoka},
title = {Scalable, fault tolerant membership for {MPI} tasks on {HPC} systems},
booktitle = {Proceedings of the 20th Annual International Conference on Supercomputing,
{ICS} 2006, Cairns, Queensland, Australia, June 28 - July 01, 2006},
pages = {219--228},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1183401.1183433},
doi = {10.1145/1183401.1183433},
timestamp = {Tue, 23 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ics/VarmaWMES06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/LimayeLGSELC05,
author = {Kshitij Limaye and
Box Leangsuksun and
Zeno Greenwood and
Stephen L. Scott and
Christian Engelmann and
Richard Libby and
Kasidit Chanchio},
title = {Job-Site Level Fault Tolerance for Cluster and Grid environments},
booktitle = {2005 {IEEE} International Conference on Cluster Computing {(CLUSTER}
2005), September 26 - 30, 2005, Boston, Massachusetts, {USA}},
pages = {1--9},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/CLUSTR.2005.347043},
doi = {10.1109/CLUSTR.2005.347043},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cluster/LimayeLGSELC05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccS/EngelmannG05,
author = {Christian Engelmann and
Al Geist},
editor = {Vaidy S. Sunderam and
G. Dick van Albada and
Peter M. A. Sloot and
Jack J. Dongarra},
title = {Super-Scalable Algorithms for Computing on 100, 000 Processors},
booktitle = {Computational Science - {ICCS} 2005, 5th International Conference,
Atlanta, GA, USA, May 22-25, 2005, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {3514},
pages = {313--321},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11428831\_39},
doi = {10.1007/11428831\_39},
timestamp = {Tue, 14 May 2019 10:00:48 +0200},
biburl = {https://dblp.org/rec/conf/iccS/EngelmannG05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/EngelmannG05,
author = {Christian Engelmann and
Al Geist},
title = {A Lightweight Kernel for the Harness Metacomputing Framework},
booktitle = {19th International Parallel and Distributed Processing Symposium {(IPDPS}
2005), {CD-ROM} / Abstracts Proceedings, 4-8 April 2005, Denver, CO,
{USA}},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/IPDPS.2005.34},
doi = {10.1109/IPDPS.2005.34},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ipps/EngelmannG05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/serp/SongLNLES05,
author = {Hertong Song and
Chokchai Leangsuksun and
Raja Nassar and
Yudan Liu and
Christian Engelmann and
Stephen L. Scott},
editor = {Hamid R. Arabnia and
Hassan Reza},
title = {UML-based Beowulf Cluster Availability Modeling},
booktitle = {Proceedings of the International Conference on Software Engineering
Research and Practice, {SERP} 2005, Las Vegas, Nevada, USA, June 27-29,
2005, Volume 1},
pages = {161--167},
publisher = {{CSREA} Press},
year = {2005},
timestamp = {Tue, 31 Jan 2006 11:57:16 +0100},
biburl = {https://dblp.org/rec/conf/serp/SongLNLES05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/clade/EngelmannG03,
author = {Christian Engelmann and
Al Geist},
title = {A Diskless Checkpointing Algorithm for Super-scale Architectures Applied
to the Fast Fourier Transform},
booktitle = {1st International Workshop on Challenges of Large Applications in
Distributed Environments, CLADE@HPDC 2003, Seattle, WA, USA, June
21, 2003},
pages = {47},
publisher = {{IEEE} Computer Society},
year = {2003},
url = {https://doi.org/10.1109/CLADE.2003.1209999},
doi = {10.1109/CLADE.2003.1209999},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/clade/EngelmannG03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccS/EngelmannSG02,
author = {Christian Engelmann and
Stephen L. Scott and
George Al Geist II},
editor = {Peter M. A. Sloot and
Chih Jeng Kenneth Tan and
Jack J. Dongarra and
Alfons G. Hoekstra},
title = {Distributed Peer-to-Peer Control in Harness},
booktitle = {Computational Science - {ICCS} 2002, International Conference, Amsterdam,
The Netherlands, April 21-24, 2002. Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {2330},
pages = {720--728},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-46080-2\_76},
doi = {10.1007/3-540-46080-2\_76},
timestamp = {Tue, 14 May 2019 10:00:48 +0200},
biburl = {https://dblp.org/rec/conf/iccS/EngelmannSG02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-05-08 23:44 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
