BibTeX records: Aurelien Bouteiller

download as .bib file

@inproceedings{DBLP:conf/sc/LiBBN23,
  author       = {Jiali Li and
                  George Bosilca and
                  Aurelien Bouteiller and
                  Bogdan Nicolae},
  title        = {Elastic deep learning through resilient collective operations},
  booktitle    = {Proceedings of the {SC} '23 Workshops of The International Conference
                  on High Performance Computing, Network, Storage, and Analysis, {SC-W}
                  2023, Denver, CO, USA, November 12-17, 2023},
  pages        = {44--50},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3624062.3626080},
  doi          = {10.1145/3624062.3626080},
  timestamp    = {Tue, 28 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/LiBBN23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijnc/BosilcaBHFRD22,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Valentin Le F{\`{e}}vre and
                  Yves Robert and
                  Jack J. Dongarra},
  title        = {Comparing Distributed Termination Detection Algorithms for Modern
                  {HPC} Platforms},
  journal      = {Int. J. Netw. Comput.},
  volume       = {12},
  number       = {1},
  pages        = {26--46},
  year         = {2022},
  url          = {http://www.ijnc.org/index.php/ijnc/article/view/271},
  timestamp    = {Mon, 21 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijnc/BosilcaBHFRD22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/WhitlockMBBNTGS22,
  author       = {Matthew Whitlock and
                  Nicolas Morales and
                  George Bosilca and
                  Aurelien Bouteiller and
                  Bogdan Nicolae and
                  Keita Teranishi and
                  Elisabeth Giem and
                  Vivek Sarkar},
  title        = {Integrating process, control-flow, and data resiliency layers using
                  a hybrid Fenix/Kokkos approach},
  booktitle    = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2022,
                  Heidelberg, Germany, September 5-8, 2022},
  pages        = {418--428},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/CLUSTER51413.2022.00052},
  doi          = {10.1109/CLUSTER51413.2022.00052},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/cluster/WhitlockMBBNTGS22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ftxs/BouteillerB22,
  author       = {Aurelien Bouteiller and
                  George Bosilca},
  title        = {Implicit Actions and Non-blocking Failure Recovery with {MPI}},
  booktitle    = {12th {IEEE/ACM} Workshop on Fault Tolerance for {HPC} at eXtreme Scale,
                  FTXS@SC 2022, Dallas, TX, USA, November 13-18, 2022},
  pages        = {36--46},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/FTXS56515.2022.00009},
  doi          = {10.1109/FTXS56515.2022.00009},
  timestamp    = {Wed, 08 Feb 2023 17:46:15 +0100},
  biburl       = {https://dblp.org/rec/conf/ftxs/BouteillerB22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-08755,
  author       = {Aurelien Bouteiller and
                  George Bosilca},
  title        = {Implicit Actions and Non-blocking Failure Recovery with {MPI}},
  journal      = {CoRR},
  volume       = {abs/2212.08755},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.08755},
  doi          = {10.48550/ARXIV.2212.08755},
  eprinttype    = {arXiv},
  eprint       = {2212.08755},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-08755.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BosilcaBHFRD21,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Valentin Le F{\`{e}}vre and
                  Yves Robert and
                  Jack J. Dongarra},
  title        = {Revisiting Credit Distribution Algorithms for Distributed Termination
                  Detection},
  booktitle    = {{IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPS} Workshops 2021, Portland, OR, USA, June 17-21,
                  2021},
  pages        = {611--620},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/IPDPSW52791.2021.00095},
  doi          = {10.1109/IPDPSW52791.2021.00095},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/BosilcaBHFRD21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/LosadaGMBBT20,
  author       = {Nuria Losada and
                  Patricia Gonz{\'{a}}lez and
                  Mar{\'{\i}}a J. Mart{\'{\i}}n and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Keita Teranishi},
  title        = {Fault tolerance of {MPI} applications in exascale systems: The {ULFM}
                  solution},
  journal      = {Future Gener. Comput. Syst.},
  volume       = {106},
  pages        = {467--481},
  year         = {2020},
  url          = {https://doi.org/10.1016/j.future.2020.01.026},
  doi          = {10.1016/J.FUTURE.2020.01.026},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/fgcs/LosadaGMBBT20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/HoriYHBBI20,
  author       = {Atsushi Hori and
                  Kazumi Yoshinaga and
                  Thomas H{\'{e}}rault and
                  Aurelien Bouteiller and
                  George Bosilca and
                  Yutaka Ishikawa},
  title        = {Overhead of using spare nodes},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {34},
  number       = {2},
  year         = {2020},
  url          = {https://doi.org/10.1177/1094342020901885},
  doi          = {10.1177/1094342020901885},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijhpca/HoriYHBBI20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/CaoBWZBD20,
  author       = {Qinglei Cao and
                  George Bosilca and
                  Wei Wu and
                  Dong Zhong and
                  Aurelien Bouteiller and
                  Jack J. Dongarra},
  title        = {Flexible Data Redistribution in a Task-Based Runtime System},
  booktitle    = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2020,
                  Kobe, Japan, September 14-17, 2020},
  pages        = {221--225},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/CLUSTER49012.2020.00032},
  doi          = {10.1109/CLUSTER49012.2020.00032},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/CaoBWZBD20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/LosadaBBGM19,
  author       = {Nuria Losada and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Patricia Gonz{\'{a}}lez and
                  Mar{\'{\i}}a J. Mart{\'{\i}}n},
  title        = {Local rollback for resilient {MPI} applications with application-level
                  checkpointing and message logging},
  journal      = {Future Gener. Comput. Syst.},
  volume       = {91},
  pages        = {450--464},
  year         = {2019},
  url          = {https://doi.org/10.1016/j.future.2018.09.041},
  doi          = {10.1016/J.FUTURE.2018.09.041},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/fgcs/LosadaBBGM19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijnc/HeraultRBAFBD19,
  author       = {Thomas H{\'{e}}rault and
                  Yves Robert and
                  Aur{\'{e}}lien Bouteiller and
                  Dorian C. Arnold and
                  Kurt B. Ferreira and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Checkpointing Strategies for Shared High-Performance Computing Platforms},
  journal      = {Int. J. Netw. Comput.},
  volume       = {9},
  number       = {1},
  pages        = {28--52},
  year         = {2019},
  url          = {http://www.ijnc.org/index.php/ijnc/article/view/195},
  timestamp    = {Tue, 16 Feb 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijnc/HeraultRBAFBD19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/FevreHRBHBD19,
  author       = {Valentin Le F{\`{e}}vre and
                  Thomas H{\'{e}}rault and
                  Yves Robert and
                  Aur{\'{e}}lien Bouteiller and
                  Atsushi Hori and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Comparing the performance of rigid, moldable and grid-shaped applications
                  on failure-prone {HPC} platforms},
  journal      = {Parallel Comput.},
  volume       = {85},
  pages        = {1--12},
  year         = {2019},
  url          = {https://doi.org/10.1016/j.parco.2019.02.002},
  doi          = {10.1016/J.PARCO.2019.02.002},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/FevreHRBHBD19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/YamazakiCBD19,
  author       = {Ichitaro Yamazaki and
                  Edmond Chow and
                  Aur{\'{e}}lien Bouteiller and
                  Jack J. Dongarra},
  title        = {Performance of asynchronous optimized Schwarz with one-sided communication},
  journal      = {Parallel Comput.},
  volume       = {86},
  pages        = {66--81},
  year         = {2019},
  url          = {https://doi.org/10.1016/j.parco.2019.05.004},
  doi          = {10.1016/J.PARCO.2019.05.004},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/YamazakiCBD19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/ZhongBLB19,
  author       = {Dong Zhong and
                  Aur{\'{e}}lien Bouteiller and
                  Xi Luo and
                  George Bosilca},
  editor       = {Torsten Hoefler and
                  Jesper Larsson Tr{\"{a}}ff},
  title        = {Runtime level failure detection and propagation in {HPC} systems},
  booktitle    = {Proceedings of the 26th European {MPI} Users' Group Meeting, EuroMPI
                  2019, Z{\"{u}}rich, Switzerland, September 11-13, 2019},
  pages        = {14:1--14:11},
  publisher    = {{ACM}},
  year         = {2019},
  url          = {https://doi.org/10.1145/3343211.3343225},
  doi          = {10.1145/3343211.3343225},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/ZhongBLB19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/LosadaBB19,
  author       = {Nuria Losada and
                  Aur{\'{e}}lien Bouteiller and
                  George Bosilca},
  title        = {Asynchronous Receiver-Driven Replay for Local Rollback of {MPI} Applications},
  booktitle    = {9th {IEEE/ACM} Workshop on Fault Tolerance for {HPC} at eXtreme Scale,
                  FTXS@SC 2019, Denver, CO, USA, November 22, 2019},
  pages        = {1--10},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/FTXS49593.2019.00006},
  doi          = {10.1109/FTXS49593.2019.00006},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/LosadaBB19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/BosilcaBGHRSD18,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Amina Guermouche and
                  Thomas H{\'{e}}rault and
                  Yves Robert and
                  Pierre Sens and
                  Jack J. Dongarra},
  title        = {A failure detector for {HPC} platforms},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {32},
  number       = {1},
  pages        = {139--158},
  year         = {2018},
  url          = {https://doi.org/10.1177/1094342017711505},
  doi          = {10.1177/1094342017711505},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijhpca/BosilcaBGHRSD18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/CastainHBS18,
  author       = {Ralph H. Castain and
                  Joshua Hursey and
                  Aur{\'{e}}lien Bouteiller and
                  David G. Solt},
  title        = {PMIx: Process management for exascale environments},
  journal      = {Parallel Comput.},
  volume       = {79},
  pages        = {9--29},
  year         = {2018},
  url          = {https://doi.org/10.1016/j.parco.2018.08.002},
  doi          = {10.1016/J.PARCO.2018.08.002},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pc/CastainHBS18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/FevreBBHHRD18,
  author       = {Valentin Le F{\`{e}}vre and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Atsushi Hori and
                  Yves Robert and
                  Jack J. Dongarra},
  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        = {Do Moldable Applications Perform Better on Failure-Prone {HPC} Platforms?},
  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        = {787--799},
  publisher    = {Springer},
  year         = {2018},
  url          = {https://doi.org/10.1007/978-3-030-10549-5\_61},
  doi          = {10.1007/978-3-030-10549-5\_61},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/FevreBBHHRD18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/HeraultRBAFBD18,
  author       = {Thomas H{\'{e}}rault and
                  Yves Robert and
                  Aur{\'{e}}lien Bouteiller and
                  Dorian C. Arnold and
                  Kurt B. Ferreira and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Optimal Cooperative Checkpointing for Shared High-Performance Computing
                  Platforms},
  booktitle    = {2018 {IEEE} International Parallel and Distributed Processing Symposium
                  Workshops, {IPDPS} Workshops 2018, Vancouver, BC, Canada, May 21-25,
                  2018},
  pages        = {803--812},
  publisher    = {{IEEE} Computer Society},
  year         = {2018},
  url          = {https://doi.org/10.1109/IPDPSW.2018.00127},
  doi          = {10.1109/IPDPSW.2018.00127},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/HeraultRBAFBD18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/openshmem/BouteillerPBBV17,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Swaroop Pophale and
                  Swen Boehm and
                  Matthew B. Baker and
                  Manjunath Gorentla Venkata},
  editor       = {Manjunath Gorentla Venkata and
                  Neena Imam and
                  Swaroop Pophale},
  title        = {Evaluating Contexts in OpenSHMEM-X Reference Implementation},
  booktitle    = {OpenSHMEM and Related Technologies. Big Compute and Big Data Convergence
                  - 4th Workshop, OpenSHMEM 2017, Annapolis, MD, USA, August 7-9, 2017,
                  Revised Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {10679},
  pages        = {50--62},
  publisher    = {Springer},
  year         = {2017},
  url          = {https://doi.org/10.1007/978-3-319-73814-7\_4},
  doi          = {10.1007/978-3-319-73814-7\_4},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/openshmem/BouteillerPBBV17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/CastainSHB17,
  author       = {Ralph H. Castain and
                  David G. Solt and
                  Joshua Hursey and
                  Aur{\'{e}}lien Bouteiller},
  editor       = {Antonio J. Pe{\~{n}}a and
                  Pavan Balaji and
                  William Gropp and
                  Rajeev Thakur},
  title        = {PMIx: process management for exascale environments},
  booktitle    = {Proceedings of the 24th European {MPI} Users' Group Meeting, EuroMPI/USA
                  2017, Chicago, IL, USA, September 25-28, 2017},
  pages        = {14:1--14:10},
  publisher    = {{ACM}},
  year         = {2017},
  url          = {https://doi.org/10.1145/3127024.3127027},
  doi          = {10.1145/3127024.3127027},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/CastainSHB17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/supercomputer/KabirHTBD17,
  author       = {Khairul Kabir and
                  Azzam Haidar and
                  Stanimire Tomov and
                  Aur{\'{e}}lien Bouteiller and
                  Jack J. Dongarra},
  editor       = {Julian M. Kunkel and
                  Rio Yokota and
                  Pavan Balaji and
                  David E. Keyes},
  title        = {A Framework for Out of Memory {SVD} Algorithms},
  booktitle    = {High Performance Computing - 32nd International Conference, {ISC}
                  High Performance 2017, Frankfurt, Germany, June 18-22, 2017, Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {10266},
  pages        = {158--178},
  publisher    = {Springer},
  year         = {2017},
  url          = {https://doi.org/10.1007/978-3-319-58667-0\_9},
  doi          = {10.1007/978-3-319-58667-0\_9},
  timestamp    = {Mon, 03 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/supercomputer/KabirHTBD17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/openshmem/BouteillerBV16,
  author       = {Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Manjunath Gorentla Venkata},
  editor       = {Manjunath Gorentla Venkata and
                  Neena Imam and
                  Swaroop Pophale and
                  Tiffany M. Mintz},
  title        = {Surviving Errors with OpenSHMEM},
  booktitle    = {OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid
                  Environments - Third Workshop, OpenSHMEM 2016, Baltimore, MD, USA,
                  August 2-4, 2016, Revised Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {10007},
  pages        = {66--81},
  publisher    = {Springer},
  year         = {2016},
  url          = {https://doi.org/10.1007/978-3-319-50995-2\_5},
  doi          = {10.1007/978-3-319-50995-2\_5},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/openshmem/BouteillerBV16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BosilcaBGHRSD16,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Amina Guermouche and
                  Thomas H{\'{e}}rault and
                  Yves Robert and
                  Pierre Sens and
                  Jack J. Dongarra},
  editor       = {John West and
                  Cherri M. Pancake},
  title        = {Failure detection and propagation in {HPC} systems},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2016, Salt Lake City, UT, USA,
                  November 13-18, 2016},
  pages        = {312--322},
  publisher    = {{IEEE} Computer Society},
  year         = {2016},
  url          = {https://doi.org/10.1109/SC.2016.26},
  doi          = {10.1109/SC.2016.26},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/BosilcaBGHRSD16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijnc/BosilcaBHRD15,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Yves Robert and
                  Jack J. Dongarra},
  title        = {Composing resilience techniques: ABFT, periodic and incremental checkpointing},
  journal      = {Int. J. Netw. Comput.},
  volume       = {5},
  number       = {1},
  pages        = {2--25},
  year         = {2015},
  url          = {http://www.ijnc.org/index.php/ijnc/article/view/95},
  timestamp    = {Tue, 16 Feb 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijnc/BosilcaBHRD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/topc/BouteillerHBDD15,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca and
                  Peng Du and
                  Jack J. Dongarra},
  title        = {Algorithm-Based Fault Tolerance for Dense Matrix Factorizations, Multiple
                  Failures and Accuracy},
  journal      = {{ACM} Trans. Parallel Comput.},
  volume       = {1},
  number       = {2},
  pages        = {10:1--10:28},
  year         = {2015},
  url          = {https://doi.org/10.1145/2686892},
  doi          = {10.1145/2686892},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/topc/BouteillerHBDD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hoti/ShamisVLBHIDSGL15,
  author       = {Pavel Shamis and
                  Manjunath Gorentla Venkata and
                  M. Graham Lopez and
                  Matthew B. Baker and
                  Oscar R. Hernandez and
                  Yossi Itigin and
                  Mike Dubman and
                  Gilad Shainer and
                  Richard L. Graham and
                  Liran Liss and
                  Yiftah Shahar and
                  Sreeram Potluri and
                  Davide Rossetti and
                  Donald Becker and
                  Duncan Poole and
                  Christopher Lamb and
                  Sameer Kumar and
                  Craig B. Stunkel and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller},
  title        = {{UCX:} An Open Source Framework for {HPC} Network APIs and Beyond},
  booktitle    = {23rd {IEEE} Annual Symposium on High-Performance Interconnects, {HOTI}
                  2015, Santa Clara, CA, USA, August 26-28, 2015},
  pages        = {40--43},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/HOTI.2015.13},
  doi          = {10.1109/HOTI.2015.13},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hoti/ShamisVLBHIDSGL15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/WuBBFD15,
  author       = {Wei Wu and
                  Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Mathieu Faverge and
                  Jack J. Dongarra},
  title        = {Hierarchical {DAG} Scheduling for Hybrid Distributed Systems},
  booktitle    = {2015 {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2015, Hyderabad, India, May 25-29, 2015},
  pages        = {156--165},
  publisher    = {{IEEE} Computer Society},
  year         = {2015},
  url          = {https://doi.org/10.1109/IPDPS.2015.56},
  doi          = {10.1109/IPDPS.2015.56},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/WuBBFD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/openshmem/TangBHVB15,
  author       = {Chunyan Tang and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Manjunath Gorentla Venkata and
                  George Bosilca},
  editor       = {Manjunath Gorentla Venkata and
                  Pavel Shamis and
                  Neena Imam and
                  M. Graham Lopez},
  title        = {From {MPI} to OpenSHMEM: Porting {LAMMPS}},
  booktitle    = {OpenSHMEM and Related Technologies. Experiences, Implementations,
                  and Technologies - Second Workshop, OpenSHMEM 2015, Annapolis, MD,
                  USA, August 4-6, 2015. Revised Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {9397},
  pages        = {121--137},
  publisher    = {Springer},
  year         = {2015},
  url          = {https://doi.org/10.1007/978-3-319-26428-8\_8},
  doi          = {10.1007/978-3-319-26428-8\_8},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/openshmem/TangBHVB15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/BouteillerBD15,
  author       = {Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Jack J. Dongarra},
  editor       = {Jack J. Dongarra and
                  Alexandre Denis and
                  Brice Goglin and
                  Emmanuel Jeannot and
                  Guillaume Mercier},
  title        = {Plan {B:} Interruption of Ongoing {MPI} Operations to Support Failure
                  Recovery},
  booktitle    = {Proceedings of the 22nd European {MPI} Users' Group Meeting, EuroMPI
                  2015, Bordeaux, France, September 21-23, 2015},
  pages        = {11:1--11:9},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2802658.2802668},
  doi          = {10.1145/2802658.2802668},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/BouteillerBD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/HoriYHBBI15,
  author       = {Atsushi Hori and
                  Kazumi Yoshinaga and
                  Thomas H{\'{e}}rault and
                  Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Yutaka Ishikawa},
  editor       = {Jack J. Dongarra and
                  Alexandre Denis and
                  Brice Goglin and
                  Emmanuel Jeannot and
                  Guillaume Mercier},
  title        = {Sliding Substitution of Failed Nodes},
  booktitle    = {Proceedings of the 22nd European {MPI} Users' Group Meeting, EuroMPI
                  2015, Bordeaux, France, September 21-23, 2015},
  pages        = {14:1--14:10},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2802658.2802670},
  doi          = {10.1145/2802658.2802670},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/HoriYHBBI15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/HeraultBBGTPD15,
  author       = {Thomas H{\'{e}}rault and
                  Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Marc Gamell and
                  Keita Teranishi and
                  Manish Parashar and
                  Jack J. Dongarra},
  editor       = {Jackie Kern and
                  Jeffrey S. Vetter},
  title        = {Practical scalable consensus for pseudo-synchronous distributed systems},
  booktitle    = {Proceedings of the International Conference for High Performance Computing,
                  Networking, Storage and Analysis, {SC} 2015, Austin, TX, USA, November
                  15-20, 2015},
  pages        = {31:1--31:12},
  publisher    = {{ACM}},
  year         = {2015},
  url          = {https://doi.org/10.1145/2807591.2807665},
  doi          = {10.1145/2807591.2807665},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/HeraultBBGTPD15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/BosilcaBBCDGHRVZ14,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Elisabeth Brunet and
                  Franck Cappello and
                  Jack J. Dongarra and
                  Amina Guermouche and
                  Thomas H{\'{e}}rault and
                  Yves Robert and
                  Fr{\'{e}}d{\'{e}}ric Vivien and
                  Dounia Zaidouni},
  title        = {Unified model for assessing checkpointing protocols at extreme-scale},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {26},
  number       = {17},
  pages        = {2772--2791},
  year         = {2014},
  url          = {https://doi.org/10.1002/cpe.3173},
  doi          = {10.1002/CPE.3173},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/BosilcaBBCDGHRVZ14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BosilcaBHRD14,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Yves Robert and
                  Jack J. Dongarra},
  title        = {Assessing the Impact of {ABFT} and Checkpoint Composite Strategies},
  booktitle    = {2014 {IEEE} International Parallel {\&} Distributed Processing
                  Symposium Workshops, Phoenix, AZ, USA, May 19-23, 2014},
  pages        = {679--688},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/IPDPSW.2014.79},
  doi          = {10.1109/IPDPSW.2014.79},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/BosilcaBHRD14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pgas/BouteillerHB14,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca},
  editor       = {Allen D. Malony and
                  Jeff R. Hammond},
  title        = {A Multithreaded Communication Substrate for OpenSHMEM},
  booktitle    = {Proceedings of the 8th International Conference on Partitioned Global
                  Address Space Programming Models, {PGAS} 2014, Eugene, OR, USA, October
                  6-10, 2014},
  pages        = {16:1--16:2},
  publisher    = {{ACM}},
  year         = {2014},
  url          = {https://doi.org/10.1145/2676870.2676895},
  doi          = {10.1145/2676870.2676895},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pgas/BouteillerHB14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/DanalisBBHD14,
  author       = {Anthony Danalis and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Jack J. Dongarra},
  title        = {{PTG:} an abstraction for unhindered parallelism},
  booktitle    = {Proceedings of the Fourth International Workshop on Domain-Specific
                  Languages and High-Level Frameworks for High Performance Computing,
                  {WOLFHPC} '14, New Orleans, Louisiana, USA, November 16-21, 2014},
  pages        = {21--30},
  publisher    = {{IEEE} Computer Society},
  year         = {2014},
  url          = {https://doi.org/10.1109/WOLFHPC.2014.8},
  doi          = {10.1109/WOLFHPC.2014.8},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/DanalisBBHD14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computing/BlandBHHBD13,
  author       = {Wesley Bland and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Joshua Hursey and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {An evaluation of User-Level Failure Mitigation support in {MPI}},
  journal      = {Computing},
  volume       = {95},
  number       = {12},
  pages        = {1171--1184},
  year         = {2013},
  url          = {https://doi.org/10.1007/s00607-013-0331-3},
  doi          = {10.1007/S00607-013-0331-3},
  timestamp    = {Thu, 06 Aug 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/computing/BlandBHHBD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/BouteillerHBD13,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Correlated set coordination in fault tolerant message logging protocols
                  for many-core clusters},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {25},
  number       = {4},
  pages        = {572--585},
  year         = {2013},
  url          = {https://doi.org/10.1002/cpe.2859},
  doi          = {10.1002/CPE.2859},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/BouteillerHBD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/BlandDBHBD13,
  author       = {Wesley Bland and
                  Peng Du and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Extending the scope of the Checkpoint-on-Failure protocol for forward
                  recovery in standard {MPI}},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {25},
  number       = {17},
  pages        = {2381--2393},
  year         = {2013},
  url          = {https://doi.org/10.1002/cpe.3100},
  doi          = {10.1002/CPE.3100},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/BlandDBHBD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cse/BosilcaBDFHD13,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Anthony Danalis and
                  Mathieu Faverge and
                  Thomas H{\'{e}}rault and
                  Jack J. Dongarra},
  title        = {PaRSEC: Exploiting Heterogeneity to Enhance Scalability},
  journal      = {Comput. Sci. Eng.},
  volume       = {15},
  number       = {6},
  pages        = {36--45},
  year         = {2013},
  url          = {https://doi.org/10.1109/MCSE.2013.98},
  doi          = {10.1109/MCSE.2013.98},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/cse/BosilcaBDFHD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/BlandBHBD13,
  author       = {Wesley Bland and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Post-failure recovery of {MPI} communication capability: Design and
                  rationale},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {27},
  number       = {3},
  pages        = {244--254},
  year         = {2013},
  url          = {https://doi.org/10.1177/1094342013488238},
  doi          = {10.1177/1094342013488238},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ijhpca/BlandBHBD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jpdc/MaBBD13,
  author       = {Teng Ma and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Jack J. Dongarra},
  title        = {Kernel-assisted and topology-aware {MPI} collective communications
                  on multicore/many-core platforms},
  journal      = {J. Parallel Distributed Comput.},
  volume       = {73},
  number       = {7},
  pages        = {1000--1010},
  year         = {2013},
  url          = {https://doi.org/10.1016/j.jpdc.2013.01.015},
  doi          = {10.1016/J.JPDC.2013.01.015},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/jpdc/MaBBD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/BouteillerCDGHR13,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Franck Cappello and
                  Jack J. Dongarra and
                  Amina Guermouche and
                  Thomas H{\'{e}}rault and
                  Yves Robert},
  editor       = {Felix Wolf and
                  Bernd Mohr and
                  Dieter an Mey},
  title        = {Multi-criteria Checkpointing Strategies: Response-Time versus Resource
                  Utilization},
  booktitle    = {Euro-Par 2013 Parallel Processing - 19th International Conference,
                  Aachen, Germany, August 26-30, 2013. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {8097},
  pages        = {420--431},
  publisher    = {Springer},
  year         = {2013},
  url          = {https://doi.org/10.1007/978-3-642-40047-6\_43},
  doi          = {10.1007/978-3-642-40047-6\_43},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/BouteillerCDGHR13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/idaacs/TurchenkoBBD13,
  author       = {Volodymyr Turchenko and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Jack J. Dongarra},
  title        = {Efficient parallelization of batch pattern training algorithm on many-core
                  and cluster architectures},
  booktitle    = {{IEEE} 7th International Conference on Intelligent Data Acquisition
                  and Advanced Computing Systems, {IDAACS} 2013, Berlin, Germany, September
                  12-14, 2013},
  pages        = {692--698},
  publisher    = {{IEEE}},
  year         = {2013},
  url          = {https://doi.org/10.1109/IDAACS.2013.6663014},
  doi          = {10.1109/IDAACS.2013.6663014},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/idaacs/TurchenkoBBD13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pc/BosilcaBDHLD12,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Anthony Danalis and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Jack J. Dongarra},
  title        = {DAGuE: {A} generic distributed {DAG} engine for High Performance Computing},
  journal      = {Parallel Comput.},
  volume       = {38},
  number       = {1-2},
  pages        = {37--51},
  year         = {2012},
  url          = {https://doi.org/10.1016/j.parco.2011.10.003},
  doi          = {10.1016/J.PARCO.2011.10.003},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/pc/BosilcaBDHLD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/BosilcaBDHD12,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Anthony Danalis and
                  Thomas H{\'{e}}rault and
                  Jack J. Dongarra},
  editor       = {Christos Kaklamanis and
                  Theodore S. Papatheodorou and
                  Paul G. Spirakis},
  title        = {From Serial Loops to Parallel Execution on Distributed Systems},
  booktitle    = {Euro-Par 2012 Parallel Processing - 18th International Conference,
                  Euro-Par 2012, Rhodes Island, Greece, August 27-31, 2012. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {7484},
  pages        = {246--257},
  publisher    = {Springer},
  year         = {2012},
  url          = {https://doi.org/10.1007/978-3-642-32820-6\_25},
  doi          = {10.1007/978-3-642-32820-6\_25},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/BosilcaBDHD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/BlandDBHBD12,
  author       = {Wesley Bland and
                  Peng Du and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca and
                  Jack J. Dongarra},
  editor       = {Christos Kaklamanis and
                  Theodore S. Papatheodorou and
                  Paul G. Spirakis},
  title        = {A Checkpoint-on-Failure Protocol for Algorithm-Based Recovery in Standard
                  {MPI}},
  booktitle    = {Euro-Par 2012 Parallel Processing - 18th International Conference,
                  Euro-Par 2012, Rhodes Island, Greece, August 27-31, 2012. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {7484},
  pages        = {477--488},
  publisher    = {Springer},
  year         = {2012},
  url          = {https://doi.org/10.1007/978-3-642-32820-6\_48},
  doi          = {10.1007/978-3-642-32820-6\_48},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/BlandDBHBD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hpc/BosilcaBDHKLTD12,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Anthony Danalis and
                  Thomas H{\'{e}}rault and
                  Jakub Kurzak and
                  Piotr Luszczek and
                  Stanimire Tomov and
                  Jack J. Dongarra},
  editor       = {Erik H. D'Hollander and
                  Jack J. Dongarra and
                  Ian T. Foster and
                  Lucio Grandinetti and
                  Gerhard R. Joubert},
  title        = {Scalable Dense Linear Algebra on Heterogeneous Hardware},
  booktitle    = {Transition of {HPC} Towards Exascale Computing - Selected Papers from
                  the High Performance Computing Workshop, Cetraro, Italy, June 25-29,
                  2012},
  series       = {Advances in Parallel Computing},
  volume       = {24},
  pages        = {65--103},
  publisher    = {{IOS} Press},
  year         = {2012},
  url          = {https://doi.org/10.3233/978-1-61499-324-7-65},
  doi          = {10.3233/978-1-61499-324-7-65},
  timestamp    = {Mon, 03 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/hpc/BosilcaBDHKLTD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/MaBBD12,
  author       = {Teng Ma and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Jack J. Dongarra},
  title        = {HierKNEM: An Adaptive Framework for Kernel-Assisted and Topology-Aware
                  Collective Communications on Many-core Clusters},
  booktitle    = {26th {IEEE} International Parallel and Distributed Processing Symposium,
                  {IPDPS} 2012, Shanghai, China, May 21-25, 2012},
  pages        = {970--982},
  publisher    = {{IEEE} Computer Society},
  year         = {2012},
  url          = {https://doi.org/10.1109/IPDPS.2012.91},
  doi          = {10.1109/IPDPS.2012.91},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/MaBBD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ppopp/DuBBHD12,
  author       = {Peng Du and
                  Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Thomas H{\'{e}}rault and
                  Jack J. Dongarra},
  editor       = {J. Ramanujam and
                  P. Sadayappan},
  title        = {Algorithm-based fault tolerance for dense matrix factorizations},
  booktitle    = {Proceedings of the 17th {ACM} {SIGPLAN} Symposium on Principles and
                  Practice of Parallel Programming, {PPOPP} 2012, New Orleans, LA, USA,
                  February 25-29, 2012},
  pages        = {225--234},
  publisher    = {{ACM}},
  year         = {2012},
  url          = {https://doi.org/10.1145/2145816.2145845},
  doi          = {10.1145/2145816.2145845},
  timestamp    = {Mon, 28 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/ppopp/DuBBHD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/BlandBHHBD12,
  author       = {Wesley Bland and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Joshua Hursey and
                  George Bosilca and
                  Jack J. Dongarra},
  editor       = {Jesper Larsson Tr{\"{a}}ff and
                  Siegfried Benkner and
                  Jack J. Dongarra},
  title        = {An Evaluation of User-Level Failure Mitigation Support in {MPI}},
  booktitle    = {Recent Advances in the Message Passing Interface - 19th European {MPI}
                  Users' Group Meeting, EuroMPI 2012, Vienna, Austria, September 23-26,
                  2012. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {7490},
  pages        = {193--203},
  publisher    = {Springer},
  year         = {2012},
  url          = {https://doi.org/10.1007/978-3-642-33518-1\_24},
  doi          = {10.1007/978-3-642-33518-1\_24},
  timestamp    = {Sun, 25 Jul 2021 11:50:18 +0200},
  biburl       = {https://dblp.org/rec/conf/pvm/BlandBHHBD12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/BosilcaBHLSTD11,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Narapat Ohm Saengpatsa and
                  Stanimire Tomov and
                  Jack J. Dongarra},
  title        = {Performance Portability of a {GPU} Enabled Factorization with the
                  DAGuE Framework},
  booktitle    = {2011 {IEEE} International Conference on Cluster Computing (CLUSTER),
                  Austin, TX, USA, September 26-30, 2011},
  pages        = {395--402},
  publisher    = {{IEEE} Computer Society},
  year         = {2011},
  url          = {https://doi.org/10.1109/CLUSTER.2011.51},
  doi          = {10.1109/CLUSTER.2011.51},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/BosilcaBHLSTD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/BouteillerHBD11,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  George Bosilca and
                  Jack J. Dongarra},
  editor       = {Emmanuel Jeannot and
                  Raymond Namyst and
                  Jean Roman},
  title        = {Correlated Set Coordination in Fault Tolerant Message Logging Protocols},
  booktitle    = {Euro-Par 2011 Parallel Processing - 17th International Conference,
                  Euro-Par 2011, Bordeaux, France, August 29 - September 2, 2011, Proceedings,
                  Part {II}},
  series       = {Lecture Notes in Computer Science},
  volume       = {6853},
  pages        = {51--64},
  publisher    = {Springer},
  year         = {2011},
  url          = {https://doi.org/10.1007/978-3-642-23397-5\_6},
  doi          = {10.1007/978-3-642-23397-5\_6},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/BouteillerHBD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpp/MaBBGSD11,
  author       = {Teng Ma and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Brice Goglin and
                  Jeffrey M. Squyres and
                  Jack J. Dongarra},
  editor       = {Guang R. Gao and
                  Yu{-}Chee Tseng},
  title        = {Kernel Assisted Collective Intra-node {MPI} Communication among Multi-Core
                  and Many-Core CPUs},
  booktitle    = {International Conference on Parallel Processing, {ICPP} 2011, Taipei,
                  Taiwan, September 13-16, 2011},
  pages        = {532--541},
  publisher    = {{IEEE} Computer Society},
  year         = {2011},
  url          = {https://doi.org/10.1109/ICPP.2011.29},
  doi          = {10.1109/ICPP.2011.29},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icpp/MaBBGSD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BosilcaBDHLD11,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Anthony Danalis and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Jack J. Dongarra},
  title        = {DAGuE: {A} Generic Distributed {DAG} Engine for High Performance Computing},
  booktitle    = {25th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May 2011 - Workshop Proceedings},
  pages        = {1151--1158},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/IPDPS.2011.281},
  doi          = {10.1109/IPDPS.2011.281},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/BosilcaBDHLD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BosilcaBDFHHKLLLLYD11,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Anthony Danalis and
                  Mathieu Faverge and
                  Azzam Haidar and
                  Thomas H{\'{e}}rault and
                  Jakub Kurzak and
                  Julien Langou and
                  Pierre Lemarinier and
                  Hatem Ltaief and
                  Piotr Luszczek and
                  Asim YarKhan and
                  Jack J. Dongarra},
  title        = {Flexible Development of Dense Linear Algebra Algorithms on Massively
                  Parallel Architectures with {DPLASMA}},
  booktitle    = {25th {IEEE} International Symposium on Parallel and Distributed Processing,
                  {IPDPS} 2011, Anchorage, Alaska, USA, 16-20 May 2011 - Workshop Proceedings},
  pages        = {1432--1441},
  publisher    = {{IEEE}},
  year         = {2011},
  url          = {https://doi.org/10.1109/IPDPS.2011.299},
  doi          = {10.1109/IPDPS.2011.299},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/BosilcaBDFHHKLLLLYD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/MaBBD11,
  author       = {Teng Ma and
                  Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Jack J. Dongarra},
  editor       = {Yiannis Cotronis and
                  Anthony Danalis and
                  Dimitrios S. Nikolopoulos and
                  Jack J. Dongarra},
  title        = {Impact of Kernel-Assisted {MPI} Communication over Scientific Applications:
                  {CPMD} and {FFTW}},
  booktitle    = {Recent Advances in the Message Passing Interface - 18th European {MPI}
                  Users' Group Meeting, EuroMPI 2011, Santorini, Greece, September 18-21,
                  2011. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {6960},
  pages        = {247--254},
  publisher    = {Springer},
  year         = {2011},
  url          = {https://doi.org/10.1007/978-3-642-24449-0\_28},
  doi          = {10.1007/978-3-642-24449-0\_28},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/MaBBD11.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/concurrency/BouteillerBD10,
  author       = {Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Jack J. Dongarra},
  title        = {Redesigning the message logging model for high performance},
  journal      = {Concurr. Comput. Pract. Exp.},
  volume       = {22},
  number       = {16},
  pages        = {2196--2211},
  year         = {2010},
  url          = {https://doi.org/10.1002/cpe.1589},
  doi          = {10.1002/CPE.1589},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/concurrency/BouteillerBD10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/BosilcaBHLD10,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Jack J. Dongarra},
  editor       = {Rainer Keller and
                  Edgar Gabriel and
                  Michael M. Resch and
                  Jack J. Dongarra},
  title        = {Dodging the Cost of Unavoidable Memory Copies in Message Logging Protocols},
  booktitle    = {Recent Advances in the Message Passing Interface - 17th European {MPI}
                  Users' Group Meeting, EuroMPI 2010, Stuttgart, Germany, September
                  12-15, 2010. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {6305},
  pages        = {189--197},
  publisher    = {Springer},
  year         = {2010},
  url          = {https://doi.org/10.1007/978-3-642-15646-5\_20},
  doi          = {10.1007/978-3-642-15646-5\_20},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/pvm/BosilcaBHLD10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/MaBBD10,
  author       = {Teng Ma and
                  George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Jack J. Dongarra},
  editor       = {Rainer Keller and
                  Edgar Gabriel and
                  Michael M. Resch and
                  Jack J. Dongarra},
  title        = {Locality and Topology Aware Intra-node Communication among Multicore
                  CPUs},
  booktitle    = {Recent Advances in the Message Passing Interface - 17th European {MPI}
                  Users' Group Meeting, EuroMPI 2010, Stuttgart, Germany, September
                  12-15, 2010. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {6305},
  pages        = {265--274},
  publisher    = {Springer},
  year         = {2010},
  url          = {https://doi.org/10.1007/978-3-642-15646-5\_28},
  doi          = {10.1007/978-3-642-15646-5\_28},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/MaBBD10.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/BouteillerRBMD09,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Thomas Ropars and
                  George Bosilca and
                  Christine Morin and
                  Jack J. Dongarra},
  title        = {Reasons for a pessimistic or optimistic message logging protocol in
                  {MPI} uncoordinated failure, recovery},
  booktitle    = {Proceedings of the 2009 {IEEE} International Conference on Cluster
                  Computing, August 31 - September 4, 2009, New Orleans, Louisiana,
                  {USA}},
  pages        = {1--9},
  publisher    = {{IEEE} Computer Society},
  year         = {2009},
  url          = {https://doi.org/10.1109/CLUSTR.2009.5289157},
  doi          = {10.1109/CLUSTR.2009.5289157},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/BouteillerRBMD09.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/BouteillerD08,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Fr{\'{e}}d{\'{e}}ric Desprez},
  title        = {Fault Tolerance Management for a Hierarchical GridRPC Middleware},
  booktitle    = {8th {IEEE} International Symposium on Cluster Computing and the Grid
                  (CCGrid 2008), 19-22 May 2008, Lyon, France},
  pages        = {484--491},
  publisher    = {{IEEE} Computer Society},
  year         = {2008},
  url          = {https://doi.org/10.1109/CCGRID.2008.14},
  doi          = {10.1109/CCGRID.2008.14},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ccgrid/BouteillerD08.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pvm/BouteillerBD07,
  author       = {Aur{\'{e}}lien Bouteiller and
                  George Bosilca and
                  Jack J. Dongarra},
  editor       = {Franck Cappello and
                  Thomas H{\'{e}}rault and
                  Jack J. Dongarra},
  title        = {Retrospect: Deterministic Replay of {MPI} Applications for Interactive
                  Distributed Debugging},
  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        = {297--306},
  publisher    = {Springer},
  year         = {2007},
  url          = {https://doi.org/10.1007/978-3-540-75416-9\_41},
  doi          = {10.1007/978-3-540-75416-9\_41},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/pvm/BouteillerBD07.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/BouteillerBHLC06,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Hinde{-}Lilia Bouziane and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Franck Cappello},
  title        = {Hybrid Preemptive Scheduling of Message Passing Interface Applications
                  on Grids},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {20},
  number       = {1},
  pages        = {77--90},
  year         = {2006},
  url          = {https://doi.org/10.1177/1094342006062526},
  doi          = {10.1177/1094342006062526},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ijhpca/BouteillerBHLC06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpca/BouteillerHKLC06,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  G{\'{e}}raud Krawezik and
                  Pierre Lemarinier and
                  Franck Cappello},
  title        = {{MPICH-V} Project: {A} Multiprotocol Automatic Fault-Tolerant {MPI}},
  journal      = {Int. J. High Perform. Comput. Appl.},
  volume       = {20},
  number       = {3},
  pages        = {319--333},
  year         = {2006},
  url          = {https://doi.org/10.1177/1094342006067469},
  doi          = {10.1177/1094342006067469},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ijhpca/BouteillerHKLC06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/europar/AmarBBCCCCMDDDGS06,
  author       = {A. Amar and
                  Raphael Bolze and
                  Aur{\'{e}}lien Bouteiller and
                  Andr{\'{e}}ea Chis and
                  Yves Caniou and
                  Eddy Caron and
                  Pushpinder{-}Kaur Chouhan and
                  Ga{\"{e}}l Le Mahec and
                  Holly Dail and
                  Benjamin Depardon and
                  Fr{\'{e}}d{\'{e}}ric Desprez and
                  Jean{-}S{\'{e}}bastien Gay and
                  Alan Su},
  editor       = {Wolfgang Lehner and
                  Norbert Meyer and
                  Achim Streit and
                  Craig Stewart},
  title        = {Diet: New Developments and Recent Results},
  booktitle    = {Euro-Par 2006 Workshops: Parallel Processing, CoreGRID 2006, {UNICORE}
                  Summit 2006, Petascale Computational Biology and Bioinformatics, Dresden,
                  Germany, August 29-September 1, 2006, Revised Selected Papers},
  series       = {Lecture Notes in Computer Science},
  volume       = {4375},
  pages        = {150--170},
  publisher    = {Springer},
  year         = {2006},
  url          = {https://doi.org/10.1007/978-3-540-72337-0\_15},
  doi          = {10.1007/978-3-540-72337-0\_15},
  timestamp    = {Thu, 19 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/europar/AmarBBCCCCMDDDGS06.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ipps/BouteillerCHLC05,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Boris Collin and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Franck Cappello},
  title        = {Impact of Event Logger on Causal Message Logging Protocols for Fault
                  Tolerant {MPI}},
  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.2005.249},
  doi          = {10.1109/IPDPS.2005.249},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/ipps/BouteillerCHLC05.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijhpcn/LemarinierBKC04,
  author       = {Pierre Lemarinier and
                  Aur{\'{e}}lien Bouteiller and
                  G{\'{e}}raud Krawezik and
                  Franck Cappello},
  title        = {Coordinated checkpoint versus message log for fault tolerant {MPI}},
  journal      = {Int. J. High Perform. Comput. Netw.},
  volume       = {2},
  number       = {2/3/4},
  pages        = {146--155},
  year         = {2004},
  url          = {https://doi.org/10.1504/IJHPCN.2004.008899},
  doi          = {10.1504/IJHPCN.2004.008899},
  timestamp    = {Sun, 02 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ijhpcn/LemarinierBKC04.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/LemarinierBHKC04,
  author       = {Pierre Lemarinier and
                  Aur{\'{e}}lien Bouteiller and
                  Thomas H{\'{e}}rault and
                  G{\'{e}}raud Krawezik and
                  Franck Cappello},
  title        = {Improved message logging versus improved coordinated checkpointing
                  for fault tolerant {MPI}},
  booktitle    = {2004 {IEEE} International Conference on Cluster Computing {(CLUSTER}
                  2004), September 20-23 2004, San Diego, California, {USA}},
  pages        = {115--124},
  publisher    = {{IEEE} Computer Society},
  year         = {2004},
  url          = {https://doi.org/10.1109/CLUSTR.2004.1392609},
  doi          = {10.1109/CLUSTR.2004.1392609},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/LemarinierBHKC04.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/grid/BouteillerBHLC04,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Hinde{-}Lilia Bouziane and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Franck Cappello},
  editor       = {Rajkumar Buyya},
  title        = {Hybrid Preemptive Scheduling of {MPI} Applications on the Grids},
  booktitle    = {5th International Workshop on Grid Computing {(GRID} 2004), 8 November
                  2004, Pittsburgh, PA, USA, Proceedings},
  pages        = {130--137},
  publisher    = {{IEEE} Computer Society},
  year         = {2004},
  url          = {https://doi.org/10.1109/GRID.2004.39},
  doi          = {10.1109/GRID.2004.39},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/grid/BouteillerBHLC04.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cluster/BouteillerLKC03,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Pierre Lemarinier and
                  G{\'{e}}raud Krawezik and
                  Franck Cappello},
  title        = {Coordinated Checkpoint versus Message Log for Fault Tolerant {MPI}},
  booktitle    = {2003 {IEEE} International Conference on Cluster Computing {(CLUSTER}
                  2003), 1-4 December 2003, Kowloon, Hong Kong, China},
  pages        = {242--250},
  publisher    = {{IEEE} Computer Society},
  year         = {2003},
  url          = {https://doi.org/10.1109/CLUSTR.2003.1253321},
  doi          = {10.1109/CLUSTR.2003.1253321},
  timestamp    = {Thu, 23 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/cluster/BouteillerLKC03.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BouteillerCHKLM03,
  author       = {Aur{\'{e}}lien Bouteiller and
                  Franck Cappello and
                  Thomas H{\'{e}}rault and
                  G{\'{e}}raud Krawezik and
                  Pierre Lemarinier and
                  Fr{\'{e}}d{\'{e}}ric Magniette},
  title        = {{MPICH-V2:} a Fault Tolerant {MPI} for Volatile Nodes based on Pessimistic
                  Sender Based Message Logging},
  booktitle    = {Proceedings of the {ACM/IEEE} {SC2003} Conference on High Performance
                  Networking and Computing, 15-21 November 2003, Phoenix, AZ, USA, CD-Rom},
  pages        = {25},
  publisher    = {{ACM}},
  year         = {2003},
  url          = {https://doi.org/10.1145/1048935.1050176},
  doi          = {10.1145/1048935.1050176},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/BouteillerCHKLM03.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sc/BosilcaBCDFGHLLMNS02,
  author       = {George Bosilca and
                  Aur{\'{e}}lien Bouteiller and
                  Franck Cappello and
                  Samir Djilali and
                  Gilles Fedak and
                  C{\'{e}}cile Germain and
                  Thomas H{\'{e}}rault and
                  Pierre Lemarinier and
                  Oleg Lodygensky and
                  Fr{\'{e}}d{\'{e}}ric Magniette and
                  Vincent N{\'{e}}ri and
                  Anton Selikhov},
  editor       = {Roscoe C. Giles and
                  Daniel A. Reed and
                  Kathryn Kelley},
  title        = {{MPICH-V:} toward a scalable fault tolerant {MPI} for volatile nodes},
  booktitle    = {Proceedings of the 2002 {ACM/IEEE} conference on Supercomputing, Baltimore,
                  Maryland, USA, November 16-22, 2002, {CD-ROM}},
  pages        = {31:1--31:18},
  publisher    = {{IEEE} Computer Society},
  year         = {2002},
  url          = {https://doi.org/10.1109/SC.2002.10048},
  doi          = {10.1109/SC.2002.10048},
  timestamp    = {Fri, 24 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/sc/BosilcaBCDFGHLLMNS02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics