This is a list of publications closely related to the JLESC. Please feel free to add any missing publications through a pull request on GitHub .

If you publish something during your work within JLESC, please acknowledge JLESC support e.g. via "This research is partially supported by the NCSA-Inria-ANL-BSC-JSC-Riken Joint-Laboratory on Extreme Scale Computing (JLESC)."


  1. Calhoun, Jon, Franck Cappello, Luke N. Olson, Marc Snir, and William D. Gropp. 2018. “Exploring The Feasibility of Lossy Compression for PDE Simulations.” Int. J. High Perform. Comput. Appl. 27. Sage Publications, Inc.
    @article{Calhoun18,
      author = {Calhoun, Jon and Cappello, Franck and Olson, Luke N. and Snir, Marc and Gropp, William D.},
      journal = {Int. J. High Perform. Comput. Appl.},
      publisher = {Sage Publications, Inc.},
      title = {Exploring the Feasibility of Lossy Compression for PDE Simulations},
      volume = {27},
      year = {2018}
    }
    
  2. Matri, Pierre, María S Pérez, Alexandru Costan, and Gabriel Antoniu. 2018. “TýrFS: Increasing Small Files Access Performance With Dynamic Metadata Replication.” In 2018 IEEE International Conference On Cluster Cloud and Grid Computing (CCGrid’18). IEEE.
    @inproceedings{MatriEtAl2018,
      title = {{TýrFS: Increasing Small Files Access Performance with Dynamic Metadata Replication}},
      author = {Matri, Pierre and Pérez, María S and Costan, Alexandru and Antoniu, Gabriel},
      booktitle = {2018 IEEE International Conference on Cluster Cloud and Grid Computing (CCGrid'18)},
      year = {2018},
      organization = {IEEE}
    }
    
  3. Subasi, Omer, Sheng Di, Leonardo Bautista-Gomez, Prasanna Balaprakash, Osman Unsal, Jesus Labarta, Adrian Cristal, Sriram Krishnamoorthy, and Franck Cappello. 2018. “Exploring The Capabilities of Support Vector Machines in Detecting Silent Data Corruptions .” Sustainable Computing: Informatics And Systems . doi:https://doi.org/10.1016/j.suscom.2018.01.004.
    @article{Subasi2018,
      title = {Exploring the Capabilities of Support Vector Machines in Detecting Silent Data Corruptions },
      journal = {Sustainable Computing: Informatics and Systems },
      volume = {},
      number = {},
      year = {2018},
      note = {},
      issn = {2210-5379},
      doi = {https://doi.org/10.1016/j.suscom.2018.01.004},
      url = {https://www.sciencedirect.com/science/article/pii/S2210537917300896},
      author = {Subasi, Omer and Di, Sheng and Bautista-Gomez, Leonardo and Balaprakash, Prasanna and Unsal, Osman and Labarta, Jesus and Cristal, Adrian and Krishnamoorthy, Sriram and Cappello, Franck},
      keywords = {HPC Applications }
    }
    
  4. Calhoun, Jon. 2017. “From Detection to Optimization: Impact of Soft Errors on High-Performance Computing Applications.” Ph. D. Manuscript: Https://Www.Ideals.Illinois.Edu/Handle/2142/98379.
    @unpublished{Calhoun17,
      author = {Calhoun, Jon},
      journal = {Ph. D. Manuscript: https://www.ideals.illinois.edu/handle/2142/98379},
      title = {From detection to optimization: impact of soft errors on high-performance computing applications},
      year = {2017}
    }
    
  5. Benoit, Anne, Aurélien Cavelan, Franck Cappello, Padma Raghavan, Yves Robert, and Hongyang Sun. 2017. “Identifying The Right Replication Level to Detect and Correct Silent Errors at Scale.” In Proceedings Of the 7th Workshop on Fault Tolerance for HPC at EXtreme Scale (FTXS).
    @inproceedings{benoitEtAl2017identifying,
      title = {Identifying the right replication level to detect and correct silent errors at scale},
      author = {Benoit, Anne and Cavelan, Aur{\'e}lien and Cappello, Franck and Raghavan, Padma and Robert, Yves and Sun, Hongyang},
      year = {2017},
      booktitle = {Proceedings of the 7th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)},
      keywords = {mine,Workshop}
    }
    
  6. Benoit, Anne, Aurélien Cavelan, Valentin Le Fèvre, and Yves Robert. 2017. “Optimal Checkpointing Period with Replicated Execution on Heterogeneous Platforms.” In Proceedings Of the 7th Workshop on Fault Tolerance for HPC at EXtreme Scale (FTXS).
    @inproceedings{benoitEtAl2017optimal,
      title = {Optimal checkpointing period with replicated execution on heterogeneous platforms},
      author = {Benoit, Anne and Cavelan, Aur{\'e}lien and Le F{\`e}vre, Valentin and Robert, Yves},
      booktitle = {Proceedings of the 7th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)},
      year = {2017},
      keywords = {mine,Workshop}
    }
    
  7. Bleuse, Raphaël, Sascha Hunold, Safia Kedad-Sidhoum, Florence Monna, Grégory Mounié, and Denis Trystram. 2017. “Scheduling Independent Moldable Tasks On Multi-Cores with GPUs.” IEEE Transactions On Parallel and Distributed Systems. IEEE. doi:10.1109/TPDS.2017.2675891.
    @article{BleuseR2017Scheduling,
      note = {in print},
      author = {Bleuse, Rapha{\"{e}}l and Hunold, Sascha and Kedad{-}Sidhoum, Safia and Monna, Florence and Mouni{\'{e}}, Gr{\'{e}}gory and Trystram, Denis},
      title = {{Scheduling Independent Moldable Tasks on Multi-Cores
      	       with GPUs}},
      journal = {IEEE Transactions on Parallel and Distributed Systems},
      volume = {},
      number = {},
      pages = {},
      year = {2017},
      doi = {10.1109/TPDS.2017.2675891},
      publisher = {IEEE},
      issn = {1045-9219},
      language = english
    }
    
  8. Dorier, Matthieu, Justin Wozniak, and Robert Ross. 2017. “Supporting Task-Level Fault-Tolerance in HPC Workflows by Launching MPI Jobs inside MPI Jobs.” Workshop. In Proceedings Of the WORKS 2017 Workshop (SC17). https://dl.acm.org/citation.cfm?id=3151001.
    @inproceedings{DorierWORKS2017,
      title = {{Supporting Task-level Fault-Tolerance in HPC Workflows by Launching MPI Jobs inside MPI Jobs}},
      author = {Dorier, Matthieu and Wozniak, Justin and Ross, Robert},
      booktitle = {{Proceedings of the WORKS 2017 workshop (SC17)}},
      year = {2017},
      type = {workshop},
      url = {https://dl.acm.org/citation.cfm?id=3151001},
      pdf = {http://delivery.acm.org/10.1145/3160000/3151001/a5-dorier.pdf}
    }
    
  9. Matri, Pierre, Yevhen Alforov, Alvaro Brandon, Michael Kuhn, Philip Carns, and Thomas Ludwig. 2017. “Could Blobs Fuel Storage-Based Convergence Between HPC And Big Data?” In CLUSTER 2017 - IEEE International Conference On Cluster Computing, 81–86. Honolulu, United States. doi:10.1109/CLUSTER.2017.63.
    @inproceedings{MatriEtAl2017,
      title = {{Could Blobs Fuel Storage-Based Convergence Between HPC and Big Data?}},
      author = {Matri, Pierre and Alforov, Yevhen and Brandon, Alvaro and Kuhn, Michael and Carns, Philip and Ludwig, Thomas},
      url = {https://hal.inria.fr/hal-01617655},
      booktitle = {{CLUSTER 2017 -  IEEE International Conference on Cluster Computing}},
      address = {Honolulu, United States},
      pages = {81 - 86},
      year = {2017},
      month = sep,
      doi = {10.1109/CLUSTER.2017.63},
      pdf = {https://hal.inria.fr/hal-01617655/file/HPC_BD_Convergence___Short_Paper___Cluster_17%20%282%29.pdf},
      hal_id = {hal-01617655},
      hal_version = {v1}
    }
    
  10. Subasi, Omer, Gulay Yalcin, Ferad Zyulkyarov, Osman Unsal, and Jesus Labarta. 2017. “Designing And Modelling Selective Replication for Fault-Tolerant HPC Applications.” In 2017 IEEE International Conference On Cluster Cloud and Grid Computing (CCGrid’17). IEEE.
    @inproceedings{subasi2017rep,
      title = {Designing and Modelling Selective Replication for Fault-tolerant HPC Applications},
      author = {Subasi, Omer and Yalcin, Gulay and Zyulkyarov, Ferad and Unsal, Osman and Labarta, Jesus},
      booktitle = {2017 IEEE International Conference on Cluster Cloud and Grid Computing (CCGrid'17)},
      year = {2017},
      organization = {IEEE}
    }
    
  11. Tsuji, Miwako, William T. C. Kramer, and Mitsuhisa Sato. 2017. “A Performance Projection Of Mini-Applications onto Benchmarks Toward the Performance Projection of Real-Applications.” In 2017 IEEE International Conference On Cluster Computing (CLUSTER), Workshop on Representative Applications (WRAp), On Line. IEEE.
    @inproceedings{TsujEtAl2017,
      author = {Tsuji, Miwako and Kramer, William T. C. and Sato, Mitsuhisa},
      title = {A Performance Projection of Mini-Applications onto Benchmarks Toward the Performance Projection of Real-Applications},
      booktitle = {2017 IEEE International Conference on Cluster Computing (CLUSTER), Workshop on Representative Applications (WRAp)},
      publisher = {IEEE},
      year = {2017},
      pages = {On Line}
    }
    
  12. Tessier, François, Venkatram Vishwanath, and Emmanuel Jeannot. 2017. “TAPIOCA: An I/O Library For Optimized Topology-Aware Data Aggregation on Large-Scale Supercomputers.” In Cluster Computing (CLUSTER), 2017 IEEE International Conference On, 70–80. IEEE.
    @inproceedings{tvj17,
      title = {TAPIOCA: An I/O Library for Optimized Topology-Aware Data Aggregation on Large-Scale Supercomputers},
      author = {Tessier, Fran{\c{c}}ois and Vishwanath, Venkatram and Jeannot, Emmanuel},
      booktitle = {Cluster Computing (CLUSTER), 2017 IEEE International Conference on},
      pages = {70--80},
      year = {2017},
      organization = {IEEE}
    }
    
  13. Dreher, Matthieu, Kiran Sasikumar, Subramanian Sankaranarayanan, and Tom Peterka. 2017. “Manala: a Flexible Flow Control Library For Asynchronous Task Communication.” In Cluster Computing (CLUSTER), 2017 IEEE International Conference On, 509–19. IEEE.
    @inproceedings{drehercluster17,
      title = {Manala: a Flexible Flow Control Library for Asynchronous Task Communication},
      author = {Dreher, Matthieu and Sasikumar, Kiran and Sankaranarayanan, Subramanian and Peterka, Tom},
      booktitle = {Cluster Computing (CLUSTER), 2017 IEEE International Conference on},
      pages = {509--519},
      year = {2017},
      organization = {IEEE}
    }
    
  14. Mommessin, Clément, Matthieu Dreher, Bruno Raffin, and Tom Peterka. 2017. “Automatic Data Filtering For In Situ Workflows.” In Cluster Computing (CLUSTER), 2017 IEEE International Conference On, 370–78. IEEE.
    @inproceedings{mommessincluster17,
      title = {Automatic Data Filtering for In Situ Workflows},
      author = {Mommessin, Cl{\'e}ment and Dreher, Matthieu and Raffin, Bruno and Peterka, Tom},
      booktitle = {Cluster Computing (CLUSTER), 2017 IEEE International Conference on},
      pages = {370--378},
      year = {2017},
      organization = {IEEE}
    }
    
  15. Dorier, Matthieu, Matthieu Dreher, Tom Peterka, and Robert Ross. 2017. “CoSS: Proposing a Contract-Based Storage System For HPC.” In Proceedings Of PDSW SC17 Workshop.
    @inproceedings{dorierpdsw17,
      title = {CoSS: Proposing a Contract-Based Storage System for HPC},
      author = {Dorier, Matthieu and Dreher, Matthieu and Peterka, Tom and Ross, Robert},
      booktitle = {Proceedings of PDSW SC17 Workshop},
      year = {2017}
    }
    
  16. Dreher, Matthieu, Swann Perarnau, Tom Peterka, Kamil Iskra, and Pete Beckman. 2017. “In Situ Workflows At Exascale: System Software to the Rescue.” In Proceedings Of ISAV SC17 Workshop.
    @inproceedings{dreherisav17,
      title = {In Situ Workflows at Exascale: System Software to the Rescue},
      author = {Dreher, Matthieu and Perarnau, Swann and Peterka, Tom and Iskra, Kamil and Beckman, Pete},
      booktitle = {Proceedings of ISAV SC17 Workshop},
      year = {2017}
    }
    
  17. Kettimuthua, Rajkumar, Zhengchun Liua, David Wheelerd, Ian Fostera, Katrin Heitmanna, and Franck Cappello. 2017. “Transferring a Petabyte In a Day.” In IEEE/ACM SC17 Workshop On Innovating the Network for Data Intensive Science (INDIS 2017).
    @inproceedings{Kettimuthua17,
      title = {Transferring a Petabyte in a Day},
      author = {Kettimuthua, Rajkumar and Liua, Zhengchun and Wheelerd, David and Fostera, Ian and Heitmanna, Katrin and Cappello, Franck},
      booktitle = {IEEE/ACM SC17 Workshop on Innovating the Network for Data Intensive Science (INDIS 2017)},
      year = {2017}
    }
    
  18. Tessier, François, Preeti Malakar, Venkatram Vishwanath, Emmanuel Jeannot, and Florin Isaila. 2016. “Topology-Aware Data Aggregation For Intensive I/O on Large-Scale Supercomputers.” In 1st Workshop On Optimization of Communication in HPC Runtime Systems (IEEE COM-HPC16). Salt-Lake City, United States: IEEE. https://hal.inria.fr/hal-01394741.
    @inproceedings{tmv+16,
      title = {{Topology-Aware Data Aggregation for Intensive I/O on Large-Scale Supercomputers}},
      author = {Tessier, Fran{\c c}ois and Malakar, Preeti and Vishwanath, Venkatram and Jeannot, Emmanuel and Isaila, Florin},
      url = {https://hal.inria.fr/hal-01394741},
      booktitle = {{1st Workshop on Optimization of Communication in HPC runtime systems (IEEE COM-HPC16)}},
      address = {Salt-Lake City, United States},
      publisher = {{IEEE}},
      year = {2016},
      month = nov,
      pdf = {https://hal.inria.fr/hal-01394741/file/topoIO-paper.pdf},
      hal_id = {hal-01394741},
      hal_version = {v1}
    }
    
  19. Cappello, Franck, Kazutomo Yoshii, Hal Finkel, and Jason Cong. 2016. “Re-Form: FPGA-Powered True Codesign Flow For High-Performance Computing In The Post-Moore Era.” The 2016 Post-Moore’s Era Supercomputing (PMES) Workshop.
    @article{CappelloEtAl2016,
      author = {Cappello, Franck and Yoshii, Kazutomo and Finkel, Hal and Cong, Jason},
      booktitle = {{The 2016 Post-Moore's Era Supercomputing (PMES) Workshop}},
      title = {{Re-Form: FPGA-Powered True Codesign Flow for High-Performance Computing In The Post-Moore Era}},
      year = {2016}
    }
    
  20. Cheriere, Nathanael, and Matthieu Dorier. 2016. “Design And Evaluation of Topology-Aware Scatter and AllGather Algorithms for Dragonfly Networks.” In IEEE/ACM International Conference For High Performance Computing, Networking, Storage and Analysis (SC) - ACM Student Research Competition. http://sc16.supercomputing.org/sc-archive/src_poster/src_poster_pages/spost146.html.
    @inproceedings{CheriereEtAl2016,
      title = {{Design and Evaluation of Topology-aware Scatter and AllGather Algorithms for Dragonfly Networks}},
      author = {Cheriere, Nathanael and Dorier, Matthieu},
      booktitle = {{IEEE/ACM International Conference for High Performance Computing, Networking, Storage and Analysis (SC) - ACM Student Research Competition}},
      year = {2016},
      url = {http://sc16.supercomputing.org/sc-archive/src_poster/src_poster_pages/spost146.html},
      pdf = {http://sc16.supercomputing.org/sc-archive/src_poster/poster_files/spost146s2-file2.pdf}
    }
    
  21. Di, Sheng, and Franck Cappello. 2016. “ Adaptive-Impact Driven Detection Of Silent Data Corruption for HPC Applications.” IEEE Transactions On Parallel and Distributed Computing. Phoenix, United States.
    @article{ShengEtCappello2016,
      address = {Phoenix, United States},
      author = {Di, Sheng and Cappello, Franck},
      booktitle = {IEEE Transactions on Parallel and Distributed Computing},
      title = { Adaptive-Impact Driven Detection of Silent Data Corruption for HPC Applications},
      year = {2016}
    }
    
  22. Dorier, Matthieu, Robert Sisneros, Leonardo Bautista-Gomez, Tom Peterka, Leigh G Orf, Rob Ross, Lokman Rahmani, Gabriel Antoniu, and Luc Bougé. 2016. Performance-Constrained In Situ Visualization Of Atmospheric Simulations. Research Report RR-8855. INRIA Rennes - Bretagne Atlantique. https://hal.inria.fr/hal-01273718.
    @techreport{DorierEtAlRR2016,
      title = {{Performance-Constrained In Situ Visualization of Atmospheric Simulations}},
      author = {Dorier, Matthieu and Sisneros, Robert and Bautista-Gomez, Leonardo and Peterka, Tom and Orf, Leigh G and Ross, Rob and Rahmani, Lokman and Antoniu, Gabriel and Boug{\'e}, Luc},
      url = {https://hal.inria.fr/hal-01273718},
      type = {Research Report},
      number = {RR-8855},
      pages = {27},
      institution = {{INRIA Rennes - Bretagne Atlantique}},
      year = {2016},
      month = feb,
      keywords = { In Situ Visualization ;  Performance ; Exascale},
      pdf = {https://hal.inria.fr/hal-01273718/file/RR-8855.pdf},
      hal_id = {hal-01273718},
      hal_version = {v1}
    }
    
  23. Dorier, Matthieu, Robert Sisneros, Leonardo Bautista Gomez, Tom Peterka, Leigh Orf, Lokman Rahmani, Gabriel Antoniu, and Luc Bougé. 2016. “Adaptive Performance-Constrained In Situ Visualization Of Atmospheric Simulations.” In IEEE International Conference On Cluster Computing (CLUSTER). IEEE. https://hal.inria.fr/hal-01351919.
    @inproceedings{DorierEtAl2016a,
      title = {{Adaptive Performance-Constrained In Situ Visualization of Atmospheric Simulations}},
      author = {Dorier, Matthieu and Sisneros, Robert and Bautista Gomez, Leonardo and Peterka, Tom and Orf, Leigh and Rahmani, Lokman and Antoniu, Gabriel and Bougé, Luc},
      booktitle = {IEEE International Conference on Cluster Computing (CLUSTER)},
      year = {2016},
      organization = {IEEE},
      url = {https://hal.inria.fr/hal-01351919},
      pdf = {https://hal.inria.fr/hal-01351919/file/SmartViz-final-1.pdf}
    }
    
  24. Dorier, Matthieu, Gabriel Antoniu, Franck Cappello, Marc Snir, Robert Sisneros, Orcun Yildiz, Shadi Ibrahim, Tom Peterka, and Leigh Orf. 2016. “Damaris: Addressing Performance Variability In Data Management for Post-Petascale Simulations.” ACM Transactions On Parallel Computing (TOPC) 3 (3). ACM: 15.
    @article{DorierEtAl2016TOPC,
      title = {Damaris: Addressing Performance Variability in Data Management for Post-Petascale Simulations},
      author = {Dorier, Matthieu and Antoniu, Gabriel and Cappello, Franck and Snir, Marc and Sisneros, Robert and Yildiz, Orcun and Ibrahim, Shadi and Peterka, Tom and Orf, Leigh},
      journal = {ACM Transactions on Parallel Computing (TOPC)},
      volume = {3},
      number = {3},
      pages = {15},
      year = {2016},
      publisher = {ACM}
    }
    
  25. Dreher, Matthieu, and Tom Peterka. 2016. “Bredala: Semantic Data Redistribution For In Situ Applications.” In Cluster Computing (CLUSTER), 2016 IEEE International Conference On, 279–88. IEEE.
    @inproceedings{DreherEtAl2016,
      title = {Bredala: Semantic Data Redistribution for In Situ Applications},
      author = {Dreher, Matthieu and Peterka, Tom},
      booktitle = {Cluster Computing (CLUSTER), 2016 IEEE International Conference on},
      pages = {279--288},
      year = {2016},
      organization = {IEEE}
    }
    
  26. Guhur, Pierre-Louis, Hong Zhang, Tom Peterka, Emil Constantinescu, and Franck Cappello. 2016. “Lightweight And Accurate Silent Data Corruption Detection in Ordinary Differential Equation Solvers.” In European Conference On Parallel Processing, 644–56. Springer.
    @inproceedings{GuhurEtAl2016,
      title = {Lightweight and Accurate Silent Data Corruption Detection in Ordinary Differential Equation Solvers},
      author = {Guhur, Pierre-Louis and Zhang, Hong and Peterka, Tom and Constantinescu, Emil and Cappello, Franck},
      booktitle = {European Conference on Parallel Processing},
      pages = {644--656},
      year = {2016},
      organization = {Springer}
    }
    
  27. Narayanan, Sri Hari Krishna, and Laurent Hascoet. 2016. “Interfacing OpenAD And Tapenade.”
    @article{NarayananHascoet2016,
      author = {Narayanan, Sri Hari Krishna and Hascoet, Laurent},
      title = {Interfacing OpenAD and Tapenade},
      journal = {},
      year = {2016},
      volume = {},
      number = {},
      pages = {},
      notes = {submitted, also available as ANL/MCS-P5588-0316}
    }
    
  28. Peterka, Tom, Hadrien Croubois, Nan Li, Esteban Rangel, and Franck Cappello. 2016. “Self-Adaptive Density Estimation of Particle Data.” SIAM Journal On Scientific Computing 38 (5). SIAM: S646–S666.
    @article{PeterkaEtAl2016,
      title = {Self-adaptive density estimation of particle data},
      author = {Peterka, Tom and Croubois, Hadrien and Li, Nan and Rangel, Esteban and Cappello, Franck},
      journal = {SIAM Journal on Scientific Computing},
      volume = {38},
      number = {5},
      pages = {S646--S666},
      year = {2016},
      publisher = {SIAM}
    }
    
  29. Subasi, Omer, Sheng Di, Leonardo Bautista-Gomez, Prasanna Balaprakash, Osman Unsal, Jesus Labarta, Adrian Cristal, and Franck Cappello. 2016. “Spatial Support Vector Regression To Detect Silent Errors in the Exascale Era.” In Proceedings Of the 2016 IEEE/ACM International Symposium on Cluster Cloud And Grid Computing. IEEE.
    @inproceedings{SubasiEtAl2016,
      title = {Spatial Support Vector Regression to Detect Silent Errors in the Exascale Era},
      author = {Subasi, Omer and Di, Sheng and Bautista-Gomez, Leonardo and Balaprakash, Prasanna and Unsal, Osman and Labarta, Jesus and Cristal, Adrian and Cappello, Franck},
      booktitle = {Proceedings of the 2016 IEEE/ACM International Symposium on Cluster Cloud and
            Grid Computing},
      organization = {IEEE},
      year = {2016}
    }
    
  30. Bautista-Gomez, Leonardo, Anne Benoit, Aurélien Cavelan, Saurabh K Raina, Yves Robert, and Hongyang Sun. 2016. “Coping With Recall and Precision of Soft Error Detectors.” Journal Of Parallel and Distributed Computing 98. Elsevier: 8–24.
    @article{bautista2016coping,
      title = {Coping with recall and precision of soft error detectors},
      author = {Bautista-Gomez, Leonardo and Benoit, Anne and Cavelan, Aur{\'e}lien and Raina, Saurabh K and Robert, Yves and Sun, Hongyang},
      journal = {Journal of Parallel and Distributed Computing},
      volume = {98},
      pages = {8--24},
      year = {2016},
      publisher = {Elsevier}
    }
    
  31. Yildiz, Orcun, Matthieu Dorier, Shadi Ibrahim, Rob Ross, and Gabriel Antoniu. 2016. “On The Root Causes of Cross-Application I/O Interference in HPC Storage Systems.” In IPDPS - International Parallel And Distributed Processing Symposium. Chicago, United States. https://hal.inria.fr/hal-01270630.
    @inproceedings{YildizIPDPS2016,
      title = {{On the Root Causes of Cross-Application I/O Interference in HPC Storage Systems}},
      author = {Yildiz, Orcun and Dorier, Matthieu and Ibrahim, Shadi and Ross, Rob and Antoniu, Gabriel},
      url = {https://hal.inria.fr/hal-01270630},
      booktitle = {{IPDPS - International Parallel and Distributed Processing Symposium}},
      address = {Chicago, United States},
      year = {2016},
      month = may,
      keywords = {Exascale I/O ; Parallel File Systems ; Cross-Application Contention ; Interference},
      pdf = {https://hal.inria.fr/hal-01270630/file/IPDPS%2716-CR.pdf},
      hal_id = {hal-01270630},
      hal_version = {v1}
    }
    
  32. Yoshii, Kazutomo, Hal Finkel, and Franck Cappello. 2016. “Benchmarking Under The Hood of OpenCL FPGA Platforms.” Second International Workshop On Heterogeneous High-Performance Reconfigurable Computing.
    @article{YoshiiEtAl2016,
      author = {Yoshii, Kazutomo and Finkel, Hal and Cappello, Franck},
      booktitle = {{Second International Workshop on Heterogeneous High-performance Reconfigurable Computing}},
      title = {{Benchmarking Under the Hood of OpenCL FPGA Platforms}},
      year = {2016}
    }
    
  33. Subasi, Omer, Gulay Yalcin, Ferad Zyulkyarov, Osman Unsal, and Jesus Labarta. 2016. “A Runtime Heuristic to Selectively Replicate Tasks for Application-Specific Reliability Targets.” In 2016 IEEE International Conference On Cluster Computing (CLUSTER’16), 498–505. IEEE.
    @inproceedings{subasi2016run,
      title = {A runtime heuristic to selectively replicate tasks for application-specific reliability targets},
      author = {Subasi, Omer and Yalcin, Gulay and Zyulkyarov, Ferad and Unsal, Osman and Labarta, Jesus},
      booktitle = {2016 IEEE International Conference on Cluster Computing (CLUSTER'16)},
      pages = {498--505},
      year = {2016},
      organization = {IEEE}
    }
    
  34. Bautista-Gomez, Leonardo, Anne Benoit, Aurélien Cavelan, Saurabh K Raina, Yves Robert, and Hongyang Sun. 2015. “Which Verification For Soft Error Detection?” In Proceedings Of the 24th International Conference on High-Performance Performance Computing. IEEE.
    @inproceedings{BautEtAl2015b,
      title = {Which Verification for Soft Error Detection?},
      author = {Bautista-Gomez, Leonardo and Benoit, Anne and Cavelan, Aur{\'e}lien and Raina, Saurabh K and Robert, Yves and Sun, Hongyang},
      year = {2015},
      booktitle = {Proceedings of the 24th International Conference on High-Performance Performance Computing},
      organization = {IEEE}
    }
    
  35. Bautista-Gomez, Leonardo Arturo, and Franck Cappello. 2015. “Detecting And Correcting Data Corruption in Stencil Applications through Multivariate Interpolation.” In Proceedings Of the 2015 IEEE International Conference on Cluster Computing, 595–602. IEEE Computer Society.
    @inproceedings{BautEtAl2015,
      title = {Detecting and correcting data corruption in stencil applications through multivariate interpolation},
      author = {Bautista-Gomez, Leonardo Arturo and Cappello, Franck},
      booktitle = {Proceedings of the 2015 IEEE International Conference on Cluster Computing},
      pages = {595--602},
      year = {2015},
      organization = {IEEE Computer Society}
    }
    
  36. Dorier, Matthieu, Matthieu Dreher, Tom Peterka, Gabriel Antoniu, Bruno Raffin, and Justin M. Wozniak. 2015. “Lessons Learned From Building In Situ Coupling Frameworks.” In First Workshop On In Situ Infrastructures for Enabling Extreme-Scale Analysis And Visualization. Austin, United States. doi:10.1145/2828612.2828622.
    @inproceedings{DorierEtAl2015,
      title = {{Lessons Learned from Building In Situ Coupling Frameworks}},
      author = {Dorier, Matthieu and Dreher, Matthieu and Peterka, Tom and Antoniu, Gabriel and Raffin, Bruno and Wozniak, Justin M.},
      url = {https://hal.inria.fr/hal-01224846},
      booktitle = {{First Workshop on In Situ Infrastructures for Enabling Extreme-Scale Analysis and
            Visualization}},
      address = {Austin, United States},
      year = {2015},
      month = nov,
      doi = {10.1145/2828612.2828622},
      keywords = {Exascale ; In Situ Visualization ; Simulation ; Coupling ; Damaris ; Decaf ; FlowVR},
      pdf = {https://hal.inria.fr/hal-01224846/file/paper-no-cr.pdf},
      hal_id = {hal-01224846},
      hal_version = {v1}
    }
    
  37. Dorier, Matthieu, Shadi Ibrahim, Gabriel Antoniu, and Rob Ross. 2015. “Using Formal Grammars To Predict I/O Behaviors in HPC: the Omnisc’IO Approach.” IEEE Transactions On Parallel and Distributed Systems. Institute of Electrical and Electronics Engineers. doi:10.1109/TPDS.2015.2485980.
    @article{DorierTPDS2015,
      title = {{Using Formal Grammars to Predict I/O Behaviors in HPC: the Omnisc'IO Approach}},
      author = {Dorier, Matthieu and Ibrahim, Shadi and Antoniu, Gabriel and Ross, Rob},
      url = {https://hal.inria.fr/hal-01238103},
      journal = {{IEEE Transactions on Parallel and Distributed Systems}},
      publisher = {{Institute of Electrical and Electronics Engineers}},
      year = {2015},
      doi = {10.1109/TPDS.2015.2485980},
      keywords = {Omnisc'IO ; Grammar ; Prediction ; I/O ; Storage ; HPC},
      pdf = {https://hal.inria.fr/hal-01238103/file/paper.pdf},
      hal_id = {hal-01238103},
      hal_version = {v1}
    }
    
  38. Martsinkevich, Tatiana V., Omer Subasi, Osman S. Unsal, Franck Cappello, and Jesús Labarta. 2015. “Fault-Tolerant Protocol For Hybrid Task-Parallel Message-Passing Applications.” In 2015 IEEE International Conference On Cluster Computing, CLUSTER 2015, Chicago, IL, USA, September 8-11, 2015, 563–70. doi:10.1109/CLUSTER.2015.104.
    @inproceedings{MartsinkevichEtAl2015,
      author = {Martsinkevich, Tatiana V. and Subasi, Omer and Unsal, Osman S. and Cappello, Franck and Labarta, Jes{\'{u}}s},
      title = {Fault-Tolerant Protocol for Hybrid Task-Parallel Message-Passing Applications},
      booktitle = {2015 {IEEE} International Conference on Cluster Computing, {CLUSTER}
                     2015, Chicago, IL, USA, September 8-11, 2015},
      pages = {563--570},
      year = {2015},
      url = {http://dx.doi.org/10.1109/CLUSTER.2015.104},
      doi = {10.1109/CLUSTER.2015.104}
    }
    
  39. Pineda-Morales, Luis, Balaji Subramaniam, Kate Keahey, Gabriel Antoniu, Alexandru Costan, Shaowen Wang, Anand Padmanabhan, and Aiman Soliman. 2015. “Scaling Smart Appliances For Spatial Data Synthesis.” SC15 - ACM/IEEE International Conference in Supercomputing. https://hal.inria.fr/hal-01241718.
    @misc{PinedaEtAl2015,
      author = {Pineda-Morales, Luis and Subramaniam, Balaji and Keahey, Kate and Antoniu, Gabriel and Costan, Alexandru and Wang, Shaowen and Padmanabhan, Anand and Soliman, Aiman},
      hal_id = {hal-01241718},
      hal_version = {v1},
      howpublished = {{SC15 - ACM/IEEE International Conference in Supercomputing}},
      keywords = {spatial data ;  cloud computing ;  elastic provisioning},
      month = nov,
      note = {Poster},
      pdf = {https://hal.inria.fr/hal-01241718/file/Pineda-Morales_SC.pdf},
      title = {{Scaling Smart Appliances for Spatial Data Synthesis}},
      url = {https://hal.inria.fr/hal-01241718},
      year = {2015}
    }
    
  40. Subasi, O., J. Arias, O. Unsal, J. Labarta, and A. Cristal. 2015. “NanoCheckpoints: A Task-Based Asynchronous Dataflow Framework For Efficient and Scalable Checkpoint/Restart.” In 2015 23rd Euromicro International Conference On Parallel, Distributed and Network-Based Processing (PDP), 99–102. doi:10.1109/PDP.2015.17.
    @inproceedings{SubasiEtAl2015,
      author = {Subasi, O. and Arias, J. and Unsal, O. and Labarta, J. and Cristal, A.},
      booktitle = {2015 23rd Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},
      title = {NanoCheckpoints: A Task-Based Asynchronous Dataflow Framework for Efficient and Scalable Checkpoint/Restart},
      year = {2015},
      pages = {99-102},
      doi = {10.1109/PDP.2015.17},
      issn = {1066-6192},
      month = mar
    }
    
  41. Di, Sheng, Eduardo Berrocal, and Franck Cappello. 2015. “An Efficient Silent Data Corruption Detection Method with Error-Feedback Control and Even Sampling for HPC Applications.” In 2015 IEEE/ACM International Symposium On Cluster, Cloud and Grid Computing (CCGrid’15), 271–80. IEEE.
    @inproceedings{di2015detect,
      title = {An efficient silent data corruption detection method with error-feedback control and even sampling for HPC applications},
      author = {Di, Sheng and Berrocal, Eduardo and Cappello, Franck},
      booktitle = {2015 IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid'15)},
      pages = {271--280},
      year = {2015},
      organization = {IEEE}
    }
    
  42. Bautista-Gomez, Leonardo, Franck Cappello, Luigi Carro, Nathan DeBardeleben, Bo Fang, Sudhanva Gurumurthi, Karthik Pattabiraman, Paolo Rech, and M Sonza Reorda. 2014. “GPGPUs: How To Combine High Computational Power with High Reliability.” In Proceedings Of the Conference on Design, Automation &Amp; Test in Europe, 341. European Design and Automation Association.
    @inproceedings{BautEtAl2014,
      author = {Bautista-Gomez, Leonardo and Cappello, Franck and Carro, Luigi and DeBardeleben, Nathan and Fang, Bo and Gurumurthi, Sudhanva and Pattabiraman, Karthik and Rech, Paolo and Reorda, M Sonza},
      booktitle = {Proceedings of the conference on Design, Automation \& Test in Europe},
      organization = {European Design and Automation Association},
      pages = {341},
      title = {GPGPUs: How to combine high computational power with high reliability},
      year = {2014}
    }
    
  43. Di, Sheng, Leonardo Bautista-Gomez, and Franck Cappello. 2014. “Optimization Of a Multilevel Checkpoint Model with Uncertain Execution Scales.” In Proceedings Of the International Conference for High Performance Computing, Networking, Storage and Analysis, 907–18. SC ’14. Piscataway, NJ, USA: IEEE Press. doi:10.1109/SC.2014.79.
    @inproceedings{DiEtAl2014,
      acmid = {2683692},
      address = {Piscataway, NJ, USA},
      author = {Di, Sheng and Bautista-Gomez, Leonardo and Cappello, Franck},
      booktitle = {Proceedings of the International Conference for High Performance Computing,
          Networking, Storage and Analysis},
      doi = {10.1109/SC.2014.79},
      isbn = {978-1-4799-5500-8},
      location = {New Orleans, Louisana},
      numpages = {12},
      pages = {907--918},
      publisher = {IEEE Press},
      series = {SC '14},
      title = {Optimization of a Multilevel Checkpoint Model with Uncertain Execution Scales},
      year = {2014}
    }
    
  44. Dorier, Matthieu, Shadi Ibrahim, Gabriel Antoniu, and Rob Ross. 2014. “Omnisc’IO: A Grammar-Based Approach to Spatial and Temporal I/O Patterns Prediction.” In Proceedings Of the International Conference for High Performance Computing, Networking, Storage and Analysis, 623–34. SC ’14. Piscataway, NJ, USA: IEEE Press. doi:10.1109/SC.2014.56.
    @inproceedings{DorierEtAl2014a,
      acmid = {2683662},
      address = {Piscataway, NJ, USA},
      author = {Dorier, Matthieu and Ibrahim, Shadi and Antoniu, Gabriel and Ross, Rob},
      booktitle = {Proceedings of the International Conference for High Performance Computing,
          Networking, Storage and Analysis},
      doi = {10.1109/SC.2014.56},
      isbn = {978-1-4799-5500-8},
      keywords = {HPC, I/O, Omnisc'IO, exascale, grammar, prediction, storage},
      location = {New Orleans, Louisana},
      numpages = {12},
      pages = {623--634},
      publisher = {IEEE Press},
      series = {SC '14},
      title = {Omnisc'IO: A Grammar-based Approach to Spatial and Temporal I/O Patterns Prediction},
      year = {2014}
    }
    
  45. Dorier, Matthieu, Gabriel Antoniu, Robert Ross, Dries Kimpe, and Shadi Ibrahim. 2014. “CALCioM: Mitigating I/O Interference In HPC Systems through Cross-Application Coordination.” In IPDPS - International Parallel And Distributed Processing Symposium. Phoenix, United States. https://hal.inria.fr/hal-00916091.
    @inproceedings{DorierEtAl2014b,
      address = {Phoenix, United States},
      author = {Dorier, Matthieu and Antoniu, Gabriel and Ross, Robert and Kimpe, Dries and Ibrahim, Shadi},
      booktitle = {IPDPS - International Parallel and Distributed Processing Symposium},
      hal_id = {hal-00916091},
      hal_version = {v1},
      month = may,
      pdf = {https://hal.inria.fr/hal-00916091/file/CALCioM.pdf},
      title = {CALCioM: Mitigating I/O Interference in HPC Systems through Cross-Application
          Coordination},
      url = {https://hal.inria.fr/hal-00916091},
      year = {2014}
    }
    
  46. Tesser, Rafael Keller, Laercio Lima Pilla, Fabrice Dupros, Philippe Olivier Alexandre Navaux, Jean-Francois Mehaut, and Celso L. Mendes. 2014. “Improving The Performance of Seismic Wave Simulations with Dynamic Load Balancing.” In 22nd Euromicro International Conference On Parallel, Distributed, and Network-Based Processing, PDP 2014, Torino, Italy, February 12-14, 2014, 196–203. doi:10.1109/PDP.2014.37.
    @inproceedings{KellerTesserEtAl2014,
      author = {Tesser, Rafael Keller and Pilla, Laercio Lima and Dupros, Fabrice and Navaux, Philippe Olivier Alexandre and Mehaut, Jean-Francois and Mendes, Celso L.},
      bibsource = {dblp computer science bibliography, http://dblp.org},
      biburl = {http://dblp.uni-trier.de/rec/bib/conf/pdp/TesserPDNMM14},
      booktitle = {22nd Euromicro International Conference on Parallel, Distributed,
         and Network-Based Processing, {PDP} 2014, Torino, Italy, February 12-14, 2014},
      doi = {10.1109/PDP.2014.37},
      pages = {196--203},
      timestamp = {Tue, 03 Feb 2015 17:12:45 +0100},
      title = {Improving the Performance of Seismic Wave Simulations with Dynamic
         Load Balancing},
      url = {http://dx.doi.org/10.1109/PDP.2014.37},
      year = {2014}
    }
    
  47. ———. 2014. “Dynamic Load Balancing for Seismic Wave Propagation Models.” International Journal Of High Performance Computing Applications (Accepted).
    @article{KellerTesserEtAl2014a,
      title = {Dynamic load balancing for seismic wave propagation models},
      journal = {International Journal of High Performance Computing Applications (accepted)},
      author = {Tesser, Rafael Keller and Pilla, Laercio Lima and Dupros, Fabrice and Navaux, Philippe Olivier Alexandre and Mehaut, Jean-Francois and Mendes, Celso L.},
      year = {2014},
      note = {accepted}
    }
    
  48. Gainaru, Ana, Franck Cappello, Marc Snir, and William Kramer. 2013. “Failure Prediction For HPC Systems and Applications: Current Situation and Open Issues.” Int. J. High Perform. Comput. Appl. 27 (3). Thousand Oaks, CA, USA: Sage Publications, Inc.: 273–82. doi:10.1177/1094342013488258.
    @article{GainaruEtAl2013,
      acmid = {2509969},
      address = {Thousand Oaks, CA, USA},
      author = {Gainaru, Ana and Cappello, Franck and Snir, Marc and Kramer, William},
      doi = {10.1177/1094342013488258},
      issn = {1094-3420},
      issue_date = {August    2013},
      journal = {Int. J. High Perform. Comput. Appl.},
      keywords = {failure prediction, fault tolerance, signal analysis},
      month = aug,
      number = {3},
      numpages = {10},
      pages = {273--282},
      publisher = {Sage Publications, Inc.},
      title = {Failure Prediction for HPC Systems and Applications: Current Situation and Open Issues},
      volume = {27},
      year = {2013}
    }