References

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-UTK Joint-Laboratory for Extreme Scale Computing (JLESC, https://jlesc.github.io/).”

BibTeX

  1. Monniot, Julien, François Tessier, Henri Casanova, and Gabriel Antoniu. 2024. “Simulation of Large-Scale HPC Storage Systems: Challenges and Methodologies.” In HiPC 2024 - 31st IEEE International Conference on High Performance Computing, Data, and Analytics, 1–11. Bangalore, India. https://inria.hal.science/hal-04784808. 
    @inproceedings{monniotEtAl2024,  title = {{Simulation of Large-Scale HPC Storage Systems: Challenges and Methodologies}},  author = {Monniot, Julien and Tessier, Fran{\c c}ois and Casanova, Henri and Antoniu, Gabriel},  url = {https://inria.hal.science/hal-04784808},  booktitle = {{HiPC 2024 - 31st IEEE International Conference on High Performance Computing, Data, and Analytics}},  address = {Bangalore, India},  pages = {1-11},  year = {2024},  month = dec,  keywords = {HPC ; Storage ; Modeling ; Simulation},  pdf = {https://inria.hal.science/hal-04784808v1/file/Simulation_based_Study_of_a_Large_Scale_Storage_System-2.pdf},  hal_id = {hal-04784808},  hal_version = {v1}}
  2. Jolivel, Théo, François Tessier, Julien Monniot, and Guillaume Pallez. 2024. “MOSAIC: Detection and Categorization of I/O Patterns in HPC Applications.” In PDSW 2024. Atlanta, United States. https://doi.org/10.1109/SCW63240.2024.00172. 
    @inproceedings{jolivelEtAl2024,  title = {{MOSAIC: Detection and Categorization of I/O Patterns in HPC Applications}},  author = {Jolivel, Th{\'e}o and Tessier, Fran{\c c}ois and Monniot, Julien and Pallez, Guillaume},  url = {https://hal.science/hal-04808300},  booktitle = {{PDSW 2024}},  address = {Atlanta, United States},  year = {2024},  month = nov,  doi = {10.1109/SCW63240.2024.00172},  keywords = {characterization ; analysis ; I/O ; HPC},  pdf = {https://hal.science/hal-04808300v1/file/PDSW24_Workshop_Paper-7.pdf},  hal_id = {hal-04808300},  hal_version = {v1}}
  3. Bouvier, Thomas, Bogdan Nicolae, Hugo Chaugier, Alexandru Costan, Ian Foster, and Gabriel Antoniu. 2024. “Efficient Data-Parallel Continual Learning with Asynchronous Distributed Rehearsal Buffers.” In CCGrid 2024 - IEEE 24th International Symposium on Cluster, Cloud and Internet Computing, 1–10. Philadelphia (PA), United States. https://doi.org/10.1109/CCGrid59990.2024.00036. 
    @inproceedings{bouvierEtAl2024,  address = {Philadelphia (PA), United States},  author = {Bouvier, Thomas and Nicolae, Bogdan and Chaugier, Hugo and Costan, Alexandru and Foster, Ian and Antoniu, Gabriel},  booktitle = {{CCGrid 2024 - IEEE 24th International Symposium on Cluster, Cloud and Internet      Computing}},  doi = {10.1109/CCGrid59990.2024.00036},  hal_id = {hal-04600107},  hal_version = {v1},  keywords = {continual learning ; data-parallel training ; experience replay ; distributed      rehearsal buffers ; asynchronous data management ; scalability},  month = may,  pages = {1-10},  pdf = {https://inria.hal.science/hal-04600107/file/paper.pdf},  title = {{Efficient Data-Parallel Continual Learning with Asynchronous Distributed Rehearsal      Buffers}},  url = {https://inria.hal.science/hal-04600107},  year = {2024}}
  4. Bouvier, Thomas, Bogdan Nicolae, Alexandru Costan, Tekin Bicer, Ian Foster, and Gabriel Antoniu. 2024. “Efficient Distributed Continual Learning for Steering Experiments in Real-Time.” Future Generation Computer Systems, July. https://doi.org/10.1016/j.future.2024.07.016. 
    @article{bouvierEtAl2024b,  author = {Bouvier, Thomas and Nicolae, Bogdan and Costan, Alexandru and Bicer, Tekin and Foster, Ian and Antoniu, Gabriel},  doi = {10.1016/j.future.2024.07.016},  hal_id = {hal-04664176},  hal_version = {v2},  journal = {{Future Generation Computer Systems}},  keywords = {continual learning ; data-parallel training ; experience replay ; distributed      rehearsal buffers ; asynchronous data management ; scalability ; streaming ; generative AI},  month = jul,  pdf = {https://inria.hal.science/hal-04664176v2/file/paper.pdf},  publisher = {{Elsevier}},  title = {{Efficient Distributed Continual Learning for Steering Experiments in Real-Time}},  url = {https://inria.hal.science/hal-04664176},  year = {2024}}
  5. Rudi, Johann, Youngjun Lee, Aidan H. Chadha, Mohamed Wahib, Klaus Weide, Jared P. O’Neal, and Anshu Dubey. 2024. “CG-Kit: Code Generation Toolkit for Performant and Maintainable Variants of Source Code Applied to Flash-X Hydrodynamics Simulations.” 
    @misc{rudi2024cgkit,  title = {CG-Kit: Code Generation Toolkit for Performant and Maintainable Variants of Source Code Applied to Flash-X Hydrodynamics Simulations},  author = {Rudi, Johann and Lee, Youngjun and Chadha, Aidan H. and Wahib, Mohamed and Weide, Klaus and O'Neal, Jared P. and Dubey, Anshu},  year = {2024},  eprint = {2401.03378},  archiveprefix = {arXiv},  note = {submitted to FGCS},  primaryclass = {cs.DC}}
  6. Gaikwad, Shreyas Sunil, Sri Hari Krishna Narayanan, Laurent Hascoet, Jean-Michel Campin, Helen Pillar, An Nguyen, Jan Hückelheim, Paul Hovland, and Patrick Heimbach. 2024. “MITgcm-AD v2: Open Source Tangent Linear and Adjoint Modeling Framework for the Oceans and Atmosphere Enabled by the Automatic Differentiation Tool Tapenade.” ArXiv e-Prints, January, arXiv:2401.11952. https://doi.org/10.48550/arXiv.2401.11952. 
    @article{GaikwadEtAl2024,  author = {{Gaikwad}, Shreyas Sunil and {Krishna Narayanan}, Sri Hari and {Hascoet}, Laurent and {Campin}, Jean-Michel and {Pillar}, Helen and {Nguyen}, An and {H{\"u}ckelheim}, Jan and {Hovland}, Paul and {Heimbach}, Patrick},  title = {{{MITgcm-AD} v2: Open source tangent linear and adjoint modeling framework for the oceans and atmosphere enabled by the Automatic Differentiation tool Tapenade}},  journal = {arXiv e-prints},  keywords = {Physics - Atmospheric and Oceanic Physics},  year = {2024},  month = jan,  eid = {arXiv:2401.11952},  pages = {arXiv:2401.11952},  doi = {10.48550/arXiv.2401.11952},  archiveprefix = {arXiv},  eprint = {2401.11952},  primaryclass = {physics.ao-ph}}
  7. Tan, Nigel and Luettgau, Jakob and Marquez, Jack and Teranishi, Keita and Morales, Nicolas and Bhowmick, Sanjukta and Cappello, Franck and Taufer, Michela and Nicolae, Bogdan. 2023. “Scalable Incremental Checkpointing Using GPU-Accelerated De-Duplication.” In Proceedings of the 52nd International Conference on Parallel Processing, 665–74. ICPP ’23. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3605573.3605639. 
    @inproceedings{TanEtAl2023,  address = {New York, NY, USA},  author = {{Tan, Nigel and Luettgau, Jakob and Marquez, Jack and Teranishi, Keita and Morales, Nicolas and Bhowmick, Sanjukta and Cappello, Franck and Taufer, Michela and Nicolae, Bogdan}},  booktitle = {{Proceedings of the 52nd International Conference on Parallel Processing}},  doi = {10.1145/3605573.3605639},  isbn = {9798400708435},  keywords = {incremental storage, de-duplication, data versioning, GPU parallelization, Checkpointing},  location = {Salt Lake City, UT, USA},  numpages = {10},  pages = {665–674},  publisher = {{Association for Computing Machinery}},  series = {ICPP '23},  title = {{Scalable Incremental Checkpointing using GPU-Accelerated De-Duplication}},  url = {https://doi.org/10.1145/3605573.3605639},  year = {2023}}
  8. Channing, Georgia and Patel, Ria and Olaya, Paula and Rorabaugh, Ariel and Miyashita, Osamu and Caino-Lores, Silvina and Schuman, Catherine and Tama, Florence and Taufer, Michela. 2023. “Composable Workflow for Accelerating Neural Architecture Search Using In Situ Analytics for Protein Classification.” In Proceedings of the 52nd International Conference on Parallel Processing, 1. ICPP ’23. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3605573.3605636. 
    @inproceedings{ChanningEtAl2023,  author = {{Channing, Georgia and Patel, Ria and Olaya, Paula and Rorabaugh, Ariel and Miyashita, Osamu and Caino-Lores, Silvina and Schuman, Catherine and Tama, Florence and Taufer, Michela}},  title = {{Composable Workflow for Accelerating Neural Architecture Search Using In Situ Analytics for Protein Classification}},  year = {2023},  isbn = {9798400708435},  publisher = {{Association for Computing Machinery}},  address = {New York, NY, USA},  url = {https://doi.org/10.1145/3605573.3605636},  doi = {10.1145/3605573.3605636},  booktitle = {{Proceedings of the 52nd International Conference on Parallel Processing}},  pages = {1},  numpages = {1},  keywords = {Deep learning, Early termination, Neural architecture search, Neural networks, Predictive modeling, Protein diffraction},  location = {Salt Lake City, UT, USA},  series = {ICPP '23}}
  9. Rosendo, Daniel, Kate Keahey, Alexandru Costan, Matthieu Simonin, Patrick Valduriez, and Gabriel Antoniu. 2023. “KheOps: Cost-Effective Repeatability, Reproducibility, and Replicability of Edge-to-Cloud Experiments.” In Proceedings of the 2023 ACM Conference on Reproducibility and Replicability, 62–73. ACM REP ’23. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3589806.3600032. 
    @inproceedings{RosendoEtAl2023,  author = {Rosendo, Daniel and Keahey, Kate and Costan, Alexandru and Simonin, Matthieu and Valduriez, Patrick and Antoniu, Gabriel},  title = {KheOps: Cost-effective Repeatability, Reproducibility, and Replicability of Edge-to-Cloud Experiments},  year = {2023},  isbn = {9798400701764},  publisher = {Association for Computing Machinery},  address = {New York, NY, USA},  url = {https://doi.org/10.1145/3589806.3600032},  doi = {10.1145/3589806.3600032},  booktitle = {Proceedings of the 2023 ACM Conference on Reproducibility and Replicability},  pages = {62–73},  numpages = {12},  keywords = {Workflows, Reproducibility, Replicability, Repeatability, Edge Computing, Computing Continuum, Cloud Computing},  location = {Santa Cruz, CA, USA},  series = {ACM REP '23}}
  10. Barbut, Quentin, Anne Benoit, Thomas Herault, Yves Robert, and Frédéric Vivien. 2023. “When to Checkpoint at the End of a Fixed-Length Reservation?” In Proceedings of Fault Tolerance for HPC at EXtreme Scales (FTXS) Workshop. https://inria.hal.science/hal-04215554. 
    @inproceedings{BarbutEtAl2023,  author = {Barbut, Quentin and Benoit, Anne and Herault, Thomas and Robert, Yves and Vivien, Frédéric},  title = {When to checkpoint at the end of a fixed-length reservation?},  booktitle = {Proceedings of Fault Tolerance for HPC at eXtreme Scales (FTXS) Workshop},  url = {https://inria.hal.science/hal-04215554},  location = {Denver, United States},  date = {2023-11-12},  year = {2023}}
  11. Yoshii, Kazutomo, John Tramm, Bryce Allen, Tomohiro Ueno, Kentaro Sano, Andrew Siegel, and Pete Beckman. 2023. “Hardware Specialization: Estimating Monte Carlo Cross-Section Lookup Kernel Performance and Area.” In Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, 1274–78. 
    @inproceedings{yoshii2023hardware,  title = {Hardware specialization: Estimating Monte Carlo cross-section lookup kernel performance and area},  author = {Yoshii, Kazutomo and Tramm, John and Allen, Bryce and Ueno, Tomohiro and Sano, Kentaro and Siegel, Andrew and Beckman, Pete},  booktitle = {Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis},  pages = {1274--1278},  year = {2023}}
  12. Yoshii, Kazutomo, Tomohiro Ueno, Kentaro Sano, Antonino Miceli, and Franck Cappello. 2023. “Streaming Hardware Compressor Generator Framework.” In Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, 289–97. 
    @inproceedings{yoshii2023streaming,  title = {Streaming Hardware Compressor Generator Framework},  author = {Yoshii, Kazutomo and Ueno, Tomohiro and Sano, Kentaro and Miceli, Antonino and Cappello, Franck},  booktitle = {Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis},  pages = {289--297},  year = {2023}}
  13. Mateevitsi, Victor A., Mathis Bode, Nicola Ferrier, Paul Fischer, Jens Henrik Göbbert, Joseph A. Insley, Yu-Hsiang Lan, et al. 2023. “Scaling Computational Fluid Dynamics: In Situ Visualization of NekRS Using SENSEI.” In Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis (SC-W 2023). https://doi.org/10.1145/3624062.3624159. 
    @inproceedings{MateevitsiEtAl2023,  author = {Mateevitsi, Victor A. and Bode, Mathis and Ferrier, Nicola and Fischer, Paul and G{\"{o}}bbert, Jens Henrik and Insley, Joseph A. and Lan, Yu-Hsiang and Min, Misun and Papka, Michael E. and Patel, Saumil and Rizzi, Silvio and Windgassen, Jonathan},  booktitle = {Workshops of The International Conference on High Performance Computing, Network,    Storage, and Analysis (SC-W 2023)},  title = {{Scaling Computational Fluid Dynamics: In Situ Visualization of NekRS using SENSEI}},  year = {2023},  doi = {10.1145/3624062.3624159}}
  14. “ROIBIN-SZ: Fast and Science-Preserving Compression for Serial Crystallography.” 2023. Synchrotron Radiation News 36 (4): 17–22. https://doi.org/10.1080/08940886.2023.2245722. 
    @article{UnderwoodEtAl2023,  author = {},  title = {ROIBIN-SZ: Fast and Science-Preserving Compression for Serial Crystallography},  journal = {Synchrotron Radiation News},  volume = {36},  number = {4},  pages = {17-22},  year = {2023},  publisher = {Taylor & Francis},  doi = {10.1080/08940886.2023.2245722},  url = {https://doi.org/10.1080/08940886.2023.2245722},  eprint = {https://doi.org/10.1080/08940886.2023.2245722}}
  15. “Integrating TEZip into LibPressio: A Acase Study of Integrating a Dynamic Application into a Static C Envionment.” 2023. 
    @misc{TalukdarEtAl2023,  author = {},  title = {Integrating TEZip into LibPressio: A Acase Study of Integrating a Dynamic Application into a Static C Envionment},  year = {2023}}
  16. Peterka, Tom, Dmitriy Morozov, Arnur Nigmetov, Orcun Yildiz, Bogdan Nicolae, and Philip E Davis. 2023. “LowFive: In Situ Data Transport for High-Performance Workflows.” In IPDPS’23: The 37th IEEE International Parallel and Distributed Processing Symposium. 
    @inproceedings{peterka2023lowfive,  title = {LowFive: In Situ Data Transport for High-Performance Workflows},  author = {Peterka, Tom and Morozov, Dmitriy and Nigmetov, Arnur and Yildiz, Orcun and Nicolae, Bogdan and Davis, Philip E},  booktitle = {IPDPS'23: The 37th IEEE International Parallel and Distributed Processing Symposium},  year = {2023}}
  17. O’Neal, Jared, Mohamed Wahib, Anshu Dubey, Klaus Weide, Tom Klosterman, and Johann Rudi. 2022. “Domain-Specific Runtime to Orchestrate Computation on Heterogeneous Platforms.” In European Conference on Parallel Processing, 154–65. Springer, Cham. 
    @inproceedings{onealEtAl2022,  title = {Domain-specific runtime to orchestrate computation on heterogeneous platforms},  author = {O’Neal, Jared and Wahib, Mohamed and Dubey, Anshu and Weide, Klaus and Klosterman, Tom and Rudi, Johann},  booktitle = {European Conference on Parallel Processing},  pages = {154--165},  year = {2022},  organization = {Springer, Cham}}
  18. Dubey, Anshu, Klaus Weide, Jared O’Neal, Akash Dhruv, Sean Couch, J Austin Harris, Tom Klosterman, et al. 2022. “Flash-X: A Multiphysics Simulation Software Instrument.” SoftwareX 19: 101168. 
    @article{dubeyEtAl2022,  title = {Flash-X: A multiphysics simulation software instrument},  author = {Dubey, Anshu and Weide, Klaus and O’Neal, Jared and Dhruv, Akash and Couch, Sean and Harris, J Austin and Klosterman, Tom and Jain, Rajeev and Rudi, Johann and Messer, Bronson and others},  journal = {SoftwareX},  volume = {19},  pages = {101168},  year = {2022},  publisher = {Elsevier}}
  19. Denoyelle, Nicolas, Swann Perarnau, Kamil Iskra, and Balazs Gerofi. 2022. “Rapid Execution Time Estimation for Heterogeneous Memory Systems Through Differential Tracing.” In High Performance Computing. Springer International Publishing. 
    @inproceedings{denoyelle2022isc,  author = {Denoyelle, Nicolas and Perarnau, Swann and Iskra, Kamil and Gerofi, Balazs},  title = {Rapid Execution Time Estimation for Heterogeneous Memory Systems  	  Through Differential Tracing},  booktitle = {High Performance Computing},  year = {2022},  publisher = {Springer International Publishing}}
  20. Hawila, Ismail, Sophie Cerf, Raphaël Bleuse, Swann Perarnau, and Éric Rutten. 2022. “Adaptive Power Control for Sober High-Performance Computing.” In 6th IEEE Conference on Control Technology and Applications. IEEE. 
    @inproceedings{hawila2022ccta,  author = {Hawila, Ismail and Cerf, Sophie and Bleuse, Rapha{\"e}l and Perarnau, Swann and Rutten, {\'E}ric},  booktitle = {6th IEEE Conference on Control Technology and Applications},  title = {Adaptive Power Control for Sober High-Performance Computing},  year = {2022},  publisher = {IEEE}}
  21. Rüttgers, Mario, Moritz Waldmann, Wolfgang Schröder, and Andreas Lintermann. 2022. “A Machine-Learning-Based Method for Automatizing Lattice-Boltzmann Simulations of Respiratory Flows.” Applied Intelligence, no. first online (January). https://doi.org/10.1007/s10489-021-02808-2. 
    @article{Ruttgers2022APIN,  author = {R{\"{u}}ttgers, Mario and Waldmann, Moritz and Schr{\"{o}}der, Wolfgang and Lintermann, Andreas},  doi = {10.1007/s10489-021-02808-2},  issn = {0924-669X},  journal = {Applied Intelligence},  month = jan,  number = {first online},  title = {{A machine-learning-based method for automatizing lattice-Boltzmann simulations of respiratory flows}},  url = {https://link.springer.com/10.1007/s10489-021-02808-2},  year = {2022}}
  22. Hückelheim, Jan, and Laurent Hascoët. 2022. “Source-to-Source Automatic Differentiation of OpenMP Parallel Loops.” ACM Trans. Math. Softw. 48 (1). https://doi.org/10.1145/3472796. 
    @article{HuckelheimHascoet2022,  author = {H\"{u}ckelheim, Jan and Hasco\"{e}t, Laurent},  title = {Source-to-Source Automatic Differentiation of OpenMP Parallel Loops},  year = {2022},  issue_date = {March 2022},  publisher = {Association for Computing Machinery},  address = {New York, NY, USA},  volume = {48},  number = {1},  issn = {0098-3500},  url = {https://doi.org/10.1145/3472796},  doi = {10.1145/3472796},  journal = {ACM Trans. Math. Softw.},  month = feb,  articleno = {7},  numpages = {32},  keywords = {Automatic differentiation, OpenMP, shared-memory parallel, multicore}}
    This article presents our work toward correct and efficient automatic differentiation of OpenMP parallel worksharing loops in forward and reverse mode. Automatic differentiation is a method to obtain gradients of numerical programs, which are crucial in optimization, uncertainty quantification, and machine learning. The computational cost to compute gradients is a common bottleneck in practice. For applications that are parallelized for multicore CPUs or GPUs using OpenMP, one also wishes to compute the gradients in parallel. We propose a framework to reason about the correctness of the generated derivative code, from which we justify our OpenMP extension to the differentiation model. We implement this model in the automatic differentiation tool Tapenade and present test cases that are differentiated following our extended differentiation procedure. Performance of the generated derivative programs in forward and reverse mode is better than sequential, although our reverse mode often scales worse than the input programs.
  23. ———. 2022. “POSTER: Automatic Differentiation of Parallel Loops with Formal Methods.” In Principles and Practice of Parallel Programming (PPoPP) 2022. 
    @conference{ppopp22-poster-ad-z3,  author = {{J}an {H}\"uckelheim and {L}aurent {H}asco\"et},  booktitle = {Principles and Practice of Parallel Programming (PPoPP) 2022},  date-added = {2022-03-15 08:59:01 -0500},  date-modified = {2022-03-15 09:01:06 -0500},  title = {{POSTER}: Automatic Differentiation of Parallel Loops with Formal Methods},  year = {2022}}
  24. Benoit, Anne, Yishu Du, Thomas Herault, Loris Marchal, Guillaume Pallez, Lucas Perotin, Yves Robert, Hongyang Sun, and Frederic Vivien. 2022. “Checkpointing à La Young/Daly: An Overview.” In Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing, 701–10. IC3-2022. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3549206.3549328. 
    @inproceedings{BenoitEtAl2022,  author = {Benoit, Anne and Du, Yishu and Herault, Thomas and Marchal, Loris and Pallez, Guillaume and Perotin, Lucas and Robert, Yves and Sun, Hongyang and Vivien, Frederic},  title = {Checkpointing \`{a} La Young/Daly: An Overview},  year = {2022},  isbn = {9781450396752},  publisher = {Association for Computing Machinery},  address = {New York, NY, USA},  url = {https://doi.org/10.1145/3549206.3549328},  doi = {10.1145/3549206.3549328},  booktitle = {Proceedings of the 2022 Fourteenth International Conference on Contemporary Computing},  pages = {701–710},  numpages = {10},  location = {Noida, India},  series = {IC3-2022}}
  25. Bosilca, George, Aurélien Bouteiller, Thomas Herault, Valentin Le Fèvre, Yves Robert, and Jack Dongarra. 2022. “Comparing Distributed Termination Detection Algorithms for Modern HPC Platforms.” Int. J. of Networking and Computing 12 (1): 26–46. 
    @article{BosilcaEtAl2022,  title = {{Comparing distributed termination detection algorithms for modern HPC platforms}},  author = {Bosilca, George and Bouteiller, Aurélien and Herault, Thomas and Fèvre, Valentin Le and Robert, Yves and Dongarra, Jack},  journal = {Int. J. of Networking and Computing},  year = {2022},  volume = {12},  number = {1},  pages = {26-46}}
  26. Du, Yishu, Guillaume Pallez, Loris Marchal, and Yves Robert. 2022. “Optimal Checkpointing Strategies for Iterative Applications.” IEEE Trans. Parallel Distributed Systems 33 (3): 507–22. 
    @article{DuEtAl2022,  author = {Du, Yishu and Pallez, Guillaume and Marchal, Loris and Robert, Yves},  journal = {IEEE Trans. Parallel Distributed Systems},  volume = {33},  pages = {507-522},  title = {Optimal checkpointing strategies for iterative applications},  number = {3},  year = {2022}}
  27. Rosendo, Daniel, Alexandru Costan, Patrick Valduriez, and Gabriel Antoniu. 2022. “Distributed Intelligence on the Edge-to-Cloud Continuum: A Systematic Literature Review.” Journal of Parallel and Distributed Computing. 
    @article{DanielEtAl2022,  title = {Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review},  author = {Rosendo, Daniel and Costan, Alexandru and Valduriez, Patrick and Antoniu, Gabriel},  journal = {Journal of Parallel and Distributed Computing},  year = {2022},  publisher = {Elsevier}}
  28. Olaya, Paula, Silvina Caíno-Lores, Vanessa Lama, Ria Patel, Ariel Keller Rorabaugh, Osamu Miyashita, Florence Tama, and Michela Taufer. 2022. “Identifying Structural Properties of Proteins from X-Ray Free Electron Laser Diffraction Patterns.” In 2022 IEEE 18th International Conference on e-Science (e-Science), 21–31. https://doi.org/10.1109/eScience55777.2022.00017. 
    @inproceedings{OlayaEtAl2022,  author = {Olaya, Paula and Caíno-Lores, Silvina and Lama, Vanessa and Patel, Ria and Rorabaugh, Ariel Keller and Miyashita, Osamu and Tama, Florence and Taufer, Michela},  booktitle = {2022 IEEE 18th International Conference on e-Science (e-Science)},  title = {Identifying Structural Properties of Proteins from X-ray Free Electron Laser Diffraction Patterns},  year = {2022},  volume = {},  number = {},  pages = {21-31},  doi = {10.1109/eScience55777.2022.00017}}
  29. Patel, Ria, Ariel Keller Rorabaugh, Paula Olaya, Silvina Caino-Lores, Georgia Channing, Catherine Schuman, Osamu Miyashita, Florence Tama, and Michela Taufer. 2022. “A Methodology to Generate Efficient Neural Networks for Classification of Scientific Datasets.” In 2022 IEEE 18th International Conference on e-Science (e-Science), 389–90. https://doi.org/10.1109/eScience55777.2022.00052. 
    @inproceedings{PatelEtAl2022,  author = {Patel, Ria and Rorabaugh, Ariel Keller and Olaya, Paula and Caino-Lores, Silvina and Channing, Georgia and Schuman, Catherine and Miyashita, Osamu and Tama, Florence and Taufer, Michela},  booktitle = {2022 IEEE 18th International Conference on e-Science (e-Science)},  title = {A Methodology to Generate Efficient Neural Networks for Classification of Scientific Datasets},  year = {2022},  volume = {},  number = {},  pages = {389-390},  doi = {10.1109/eScience55777.2022.00052}}
  30. Underwood, Robert, Victoriana Malvoso, Jon C. Calhoun, Sheng Di, and Franck Cappello. 2021. “Productive and Performant Generic Lossy Data Compression with LibPressio.” In 2021 7th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-7), 1–10. https://doi.org/10.1109/DRBSD754563.2021.00005. 
    @inproceedings{libpressio,  author = {Underwood, Robert and Malvoso, Victoriana and Calhoun, Jon C. and Di, Sheng and Cappello, Franck},  booktitle = {2021 7th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-7)},  title = {Productive and Performant Generic Lossy Data Compression with LibPressio},  year = {2021},  volume = {},  number = {},  pages = {1-10},  doi = {10.1109/DRBSD754563.2021.00005}}
  31. Ogoke, Francis, Kazem Meidani, Amirreza Hashemi, and Amir Barati Farimani. 2021. “Graph Convolutional Networks Applied to Unstructured Flow Field Data.” Machine Learning: Science and Technology 2 (September). https://doi.org/10.1088/2632-2153/ac1fc9. 
    @article{Ogoke2021,  author = {Ogoke, Francis and Meidani, Kazem and Hashemi, Amirreza and Barati Farimani, Amir},  year = {2021},  month = sep,  pages = {},  title = {Graph Convolutional Networks applied to unstructured flow field data},  volume = {2},  journal = {Machine Learning: Science and Technology},  doi = {10.1088/2632-2153/ac1fc9}}
  32. Yoshii, Kazutomo, Rajesh Sankaran, Sebastian Strempfer, Maksim Levental, Mike Hammer, and Antonino Miceli. 2021. “A Hardware Co-Design Workflow for Scientific Instruments at the Edge.” 
    @misc{yoshii2021hardware,  title = {A Hardware Co-design Workflow for Scientific Instruments at the Edge},  author = {Yoshii, Kazutomo and Sankaran, Rajesh and Strempfer, Sebastian and Levental, Maksim and Hammer, Mike and Miceli, Antonino},  year = {2021},  eprint = {2111.01380},  archiveprefix = {arXiv},  primaryclass = {physics.ins-det}}
  33. Ueno, Tomohiro, Atsushi Koshiba, and Kentaro Sano. 2021. “Virtual Circuit-Switching Network with Flexible Topology for High-Performance FPGA Cluster.” In 2021 IEEE 32nd International Conference on Application-Specific Systems, Architectures and Processors (ASAP), 41–48. IEEE. 
    @inproceedings{ueno2021virtual,  title = {Virtual Circuit-Switching Network with Flexible Topology for High-Performance FPGA Cluster},  author = {Ueno, Tomohiro and Koshiba, Atsushi and Sano, Kentaro},  booktitle = {2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP)},  pages = {41--48},  year = {2021},  organization = {IEEE}}
  34. Cerf, Sophie, Raphaël Bleuse, Valentin Reis, Swann Perarnau, and Éric Rutten. 2021. “Sustaining Performance While Reducing Energy Consumption: A Control Theory Approach.” In Euro-Par 2021: Parallel Processing. Springer International Publishing. https://doi.org/10.1007/978-3-030-85665-6_21. 
    @inproceedings{cerf2021europar,  title = {{Sustaining Performance While Reducing Energy Consumption: A Control Theory Approach}},  author = {Cerf, Sophie and Bleuse, Rapha{\"e}l and Reis, Valentin and Perarnau, Swann and Rutten, {\'E}ric},  booktitle = {Euro-Par 2021: Parallel Processing},  year = {2021},  doi = {10.1007/978-3-030-85665-6_21},  publisher = {Springer International Publishing}}
  35. Rüttgers, Mario, Moritz Waldmann, Wolfgang Schröder, and Andreas Lintermann. 2021. “Machine-Learning-Based Control of Perturbed and Heated Channel Flows.” In High Performance Computing, Proceedings of the 36th International Conference, ISC High Performance 2021, 7–22. Frankfurt/Main, Germany: Springer International Publishing. https://doi.org/10.1007/978-3-030-90539-2_1. 
    @incollection{Ruttgers2021ISC,  address = {Frankfurt/Main, Germany},  author = {R{\"{u}}ttgers, Mario and Waldmann, Moritz and Schr{\"{o}}der, Wolfgang and Lintermann, Andreas},  booktitle = {High Performance Computing, Proceedings of the 36th International Conference, ISC High Performance 2021},  doi = {10.1007/978-3-030-90539-2_1},  pages = {7--22},  publisher = {Springer International Publishing},  title = {{Machine-Learning-Based Control of Perturbed and Heated Channel Flows}},  url = {https://link.springer.com/10.1007/978-3-030-90539-2{\_}1},  year = {2021}}
  36. Ando, Kazuto, Keiji Onishi, Rahul Bale, Makoto Tsubokura, Akiyoshi Kuroda, and Kazuo Minami. 2021. “Nonlinear Mode Decomposition and Reduced-Order Modeling for Three-Dimensional Cylinder Flow by Distributed Learning on Fugaku.” In High Performance Computing, Proceedings of the 36th International Conference, ISC High Performance 2021, 122–37. Frankfurt/Main, Germany: Springer International Publishing. https://doi.org/10.1007/978-3-030-90539-2_8. 
    @incollection{Ando2021ISC,  address = {Frankfurt/Main, Germany},  author = {Ando, Kazuto and Onishi, Keiji and Bale, Rahul and Tsubokura, Makoto and Kuroda, Akiyoshi and Minami, Kazuo},  booktitle = {High Performance Computing, Proceedings of the 36th International Conference, ISC High Performance 2021},  doi = {10.1007/978-3-030-90539-2_8},  pages = {122--137},  publisher = {Springer International Publishing},  title = {{Nonlinear Mode Decomposition and Reduced-Order Modeling for Three-Dimensional Cylinder Flow by Distributed Learning on Fugaku}},  url = {https://link.springer.com/10.1007/978-3-030-90539-2{\_}8},  year = {2021}}
  37. Hori, Atsushi, Emmanuel Jeannot, George Bosilca, Takahiro Ogura, Balazs Gerofi, Jie Yin, and Yutaka Ishikawa. 2021. “An International Survey on MPI Users.” Parallel Computing. 
    @article{Hori21,  title = {{An International Survey on MPI Users}},  journal = {{Parallel Computing}},  publisher = {{Elsevier}},  author = {Hori, Atsushi and Jeannot, Emmanuel and Bosilca, George and Ogura, Takahiro and Gerofi, Balazs and Yin, Jie and Ishikawa, Yutaka},  year = {2021},  note = {(submitted)}}
  38. Tian, Jiannan, Cody Rivera, Sheng Di, Jieyang Chen, Liang Xin, Dingwen Tao, and Franck Cappello. 2021. “Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures.” In IPDPS’21: 35th IEEE International Parallel and Distributed Processing Symposium. 
    @inproceedings{Tian21,  title = {{Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures}},  author = {Tian, Jiannan and Rivera, Cody and Di, Sheng and Chen, Jieyang and Xin, Liang and Tao, Dingwen and Cappello, Franck},  booktitle = {{IPDPS'21: 35th IEEE International parallel and distributed processing symposium}},  year = {2021}}
  39. Yildiz, Orcun, Dmitriy Morozov, Bogdan Nicolae, and Tom Peterka. 2021. “Dynamic Heterogeneous Task Specification and Execution for In Situ Workflows.” In 2021 IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS), 25–32. IEEE Computer Society. 
    @inproceedings{yildiz2021dynamic,  title = {Dynamic Heterogeneous Task Specification and Execution for In Situ Workflows},  author = {Yildiz, Orcun and Morozov, Dmitriy and Nicolae, Bogdan and Peterka, Tom},  booktitle = {2021 IEEE Workshop on Workflows in Support of Large-Scale Science (WORKS)},  pages = {25--32},  year = {2021},  organization = {IEEE Computer Society}}
  40. Hascoët, Laurent, Jan Christian Hückelheim, Paul Hovland, and Sri Hari Krishna Narayanan. 2021. “SIAM CSE21 Minitutorial: Automatic Differentiation as a Tool for Computational Science.” https://github.com/sriharikrishna/siamcse21. 
    @misc{NarayananEtAl2021,  author = {Hasco{\"e}t, Laurent and H{\"u}ckelheim, Jan Christian and Hovland, Paul and Narayanan, Sri Hari Krishna},  title = {{SIAM} {CSE}21 {M}initutorial: {A}utomatic {D}ifferentiation as a {T}ool for {C}omputational {S}cience},  url = {https://github.com/sriharikrishna/siamcse21},  year = {2021}}
  41. Benoit, Anne, Valentin Le Fèvre, Lucas Perotin, Padma Raghavan, Yves Robert, and Hongyang Sun. 2021. “Resilient Scheduling of Moldable Parallel Jobs to Cope with Silent Errors.” IEEE Transactions on Computers. 
    @article{BenoitEtAl2021,  author = {Benoit, Anne and Fèvre, Valentin Le and Perotin, Lucas and Raghavan, Padma and Robert, Yves and Sun, Hongyang},  journal = {IEEE Transactions on Computers},  title = {Resilient scheduling of moldable parallel jobs to cope with silent errors},  year = {2021}}
  42. Hobson, Tanner, Orcun Yildiz, Bogdan Nicolae, Jian Huang, and Tom Peterka. 2021. “Shared-Memory Communication for Containerized Workflows.” In Proceedings of the 21st IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid). CCGrid ’21. IEEE/ACM. 
    @inproceedings{Hobson2020Dhmem,  author = {Hobson, Tanner and Yildiz, Orcun and Nicolae, Bogdan and Huang, Jian and Peterka, Tom},  title = {Shared-Memory Communication for Containerized Workflows},  booktitle = {Proceedings of the 21st IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},  series = {CCGrid '21},  year = {2021},  location = {Melbourne, Australia},  pages = {},  numpages = {},  url = {},  doi = {},  acmid = {},  publisher = {IEEE/ACM},  keywords = {shared memory, workflow systems, containers},  pdf = {}}
  43. Tsuji, Miwako, William T.C. Kramer, Jean-Christophe Weill, Jean-Philippe Nominé, and Mitsuhisa Sato. 2021. “A New Sustained System Performance Metric for Scientific Performance Evaluation.” The Journal of Supercomputing, 1–29. 
    @article{TsujEtAl2021,  title = {A new sustained system performance metric for scientific performance evaluation},  author = {Tsuji, Miwako and Kramer, William T.C. and Weill, Jean-Christophe and Nominé, Jean-Philippe and Sato, Mitsuhisa},  journal = {The Journal of Supercomputing},  volume = {},  pages = {1--29},  year = {2021},  publisher = {Springer}}
  44. Hori, Atsushi, Emmanuel Jeannot, George Bosilca, Takahiro Ogura, Balazs Gerofi, Jie Yin, and Yutaka Ishikawa. 2021. “An International Survey on MPI Users.” Parallel Computing 108: 102853. https://doi.org/https://doi.org/10.1016/j.parco.2021.102853. 
    @article{ahori-PARCO21-survey,  title = {An international survey on MPI users},  journal = {Parallel Computing},  volume = {108},  pages = {102853},  year = {2021},  issn = {0167-8191},  doi = {https://doi.org/10.1016/j.parco.2021.102853},  url = {https://www.sciencedirect.com/science/article/pii/S0167819121000983},  author = {Hori, Atsushi and Jeannot, Emmanuel and Bosilca, George and Ogura, Takahiro and Gerofi, Balazs and Yin, Jie and Ishikawa, Yutaka},  keywords = {Message Passing Interface (MPI), Survey}}
  45. Rosendo, Daniel, Alexandru Costan, Gabriel Antoniu, Matthieu Simonin, Jean-Christophe Lombardo, Alexis Joly, and Patrick Valduriez. 2021. “Reproducible Performance Optimization of Complex Applications on the Edge-to-Cloud Continuum.” In 2021 IEEE International Conference on Cluster Computing (CLUSTER), 23–34. IEEE. 
    @inproceedings{DanielEtAl2021,  title = {Reproducible performance optimization of complex applications on the edge-to-cloud continuum},  author = {Rosendo, Daniel and Costan, Alexandru and Antoniu, Gabriel and Simonin, Matthieu and Lombardo, Jean-Christophe and Joly, Alexis and Valduriez, Patrick},  booktitle = {2021 IEEE International Conference on Cluster Computing (CLUSTER)},  pages = {23--34},  year = {2021},  organization = {IEEE}}
  46. Lintermann, Andreas, Matthias Meinke, and Wolfgang Schröder. 2020. “Zonal Flow Solver (ZFS): a Highly Efficient Multi- Physics Simulation Framework.” International Journal of Computational Fluid Dynamics 34 (March). https://doi.org/10.1080/10618562.2020.1742328. 
    @article{Lintermann2020,  author = {Lintermann, Andreas and Meinke, Matthias and Schröder, Wolfgang},  year = {2020},  month = mar,  pages = {},  title = {Zonal Flow Solver (ZFS): a highly efficient multi- physics simulation framework},  volume = {34},  journal = {International Journal of Computational Fluid Dynamics},  doi = {10.1080/10618562.2020.1742328}}
  47. Tian, Jiannan, Sheng Di, Kai Zhao, Rivera Cody, Megan Hickman, Robert Underwood, Sian Jin, et al. 2020. “CuSZ: An Efficient GPU Based Error-Bounded Lossy Compression, Framework for Scientific Data.” In PACT’20: ACM International Conference on Parallel Architectures and Compilation Techniques. 
    @inproceedings{Tian20,  title = {{cuSZ: An Efficient GPU Based Error-Bounded Lossy Compression, Framework for Scientific Data}},  author = {Tian, Jiannan and Di, Sheng and Zhao, Kai and Cody, Rivera and Hickman, Megan and Underwood, Robert and Jin, Sian and Liang, Xin and Calhoun, Jon and Tao, Dingwen and Cappello, Franck},  booktitle = {{PACT'20: ACM International Conference on Parallel Architectures and Compilation Techniques}},  year = {2020}}
  48. Roy, Rupak, Kento Sato, Subhadeep Bhattacharya, Xingang Fang, Yasumasa Joti, Takaki Hatsui, Toshiyuki Hiraki, Jian Guo, and Weikuan Yu. 2020. “Compression of Time Evolutionary Image Data through Predictive Deep Neural Networks.” In CCGRID’21: IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing. 
    @inproceedings{Rupak21,  title = {{Compression of Time Evolutionary Image Data through Predictive Deep Neural Networks}},  author = {Roy, Rupak and Sato, Kento and Bhattacharya, Subhadeep and Fang, Xingang and Joti, Yasumasa and Hatsui, Takaki and Hiraki, Toshiyuki and Guo, Jian and Yu, Weikuan},  booktitle = {{CCGRID'21: IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing}},  year = {2020}}
  49. Agullo, Emmanuel, Franck Cappello, Sheng Di, Luc Giraud, Xin Liang, and Nick Schenkels. 2020. “Exploring Variable Accuracy Storage through Lossy Compression Techniques in Numerical Linear Algebra: a First Application to Flexible GMRES.” Research Report RR-9342. Inria Bordeaux Sud-Ouest. https://hal.inria.fr/hal-02572910. 
    @techreport{agullo:hal-02572910,  title = {{Exploring variable accuracy storage through lossy   compression techniques in numerical linear algebra: a first application   to flexible GMRES}},  author = {Agullo, Emmanuel and Cappello, Franck and Di, Sheng and Giraud, Luc and Liang, Xin and Schenkels, Nick},  url = {https://hal.inria.fr/hal-02572910},  type = {Research Report},  number = {RR-9342},  institution = {{Inria Bordeaux Sud-Ouest}},  year = {2020},  month = may,  keywords = {Mixed precision ; Lossy compression ; Flexible GMRES ;   Inexact Krylov ; Compression avec perte ; Pr{\'e}cision mixte},  pdf = {https://hal.inria.fr/hal-02572910v2/file/RR-9342.pdf},  hal_id = {hal-02572910},  hal_version = {v2}}
  50. Underwood, Robert, Sheng Di, Jon Calhoun, and Franck Cappello. 2020. “FRaZ: A Generic High-Fidelity Fixed-Ratio Lossy Compression Framework for Scientific Floating-Point Data.” In IPDPS20: 34th IEEE International Parallel and Distributed Processing Symposium. 
    @inproceedings{Underwood20,  title = {{FRaZ: A Generic High-Fidelity Fixed-Ratio Lossy Compression Framework for Scientific Floating-point Data}},  author = {Underwood, Robert and Di, Sheng and Calhoun, Jon and Cappello, Franck},  booktitle = {{IPDPS20: 34th IEEE International parallel and distributed processing symposium}},  year = {2020}}
  51. Schenkels, Nick, Emmanuel Agullo, Luc Giraud, Xin Liangy, Sheng Diy, and Franck Cappello. 2020. “Flexible Generalized Minimal Residual Method with a Compressed Search Space.” 
    @unpublished{Schenkels20,  author = {Schenkels, Nick and Agullo, Emmanuel and Giraud, Luc and Liangy, Xin and Diy, Sheng and Cappello, Franck},  title = {Flexible generalized minimal residual method with a compressed search space},  year = {2020},  note = {(to be submitted)}}
  52. Underwood, Robert, Jon Calhoun, Sheng Di, and Franck Cappello. 2020. “FRaZ: A Generic High-Fidelity Fixed-Ratio Lossy Compression Framework For Scientific Data.” In 2020 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2020, New Orleans, USA, May 18-22, 2020. IEEE. 
    @inproceedings{UnderwoodEtAl2020,  author = {Underwood, Robert and Calhoun, Jon and Di, Sheng and Cappello, Franck},  title = {FRaZ: A Generic High-Fidelity Fixed-Ratio Lossy Compression Framework for        Scientific Data},  booktitle = {2020 {IEEE} International Parallel and Distributed Processing Symposium,                 {IPDPS} 2020, New Orleans, USA, May 18-22, 2020},  pages = {},  publisher = {{IEEE}},  year = {2020},  url = {}}
  53. Fèvre, Valentin Le, Thomas Herault, Julien Langou, and Yves Robert. 2020. “A Comparison of Several Fault-Tolerance Methods for the Detection and Correction of Floating-Point Errorsin Matrix-Matrix Multiplication.” In Resilience: 13th Workshop on Resiliency in High Performance Computing in Clusters, Clouds, and Grids, Jointly Published with Euro-Par 2020. LNCS. Springer Verlag. 
    @inproceedings{LeFevreEtAl2020,  author = {Fèvre, Valentin Le and Herault, Thomas and Langou, Julien and Robert, Yves},  booktitle = {{Resilience}: 13th Workshop on Resiliency in High Performance Computing    in Clusters, Clouds, and Grids,                  jointly published with {Euro-Par 2020}},  title = {A comparison of several fault-tolerance methods for the detection and correction of floating-point errors  in matrix-matrix multiplication},  year = {2020},  series = {LNCS},  publisher = {Springer Verlag}}
  54. Cheriere, Nathanael, Matthieu Dorier, Gabriel Antiniu, Stefan M Wild, Sven Leyffer, and Robert Ross. 2020. “Pufferscale: Rescaling HPC Data Services for High Energy Physics Applications.” In Proceedings of the 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (Ccgrid). CCgrid ’20. IEEE/ACM. 
    @inproceedings{Cheriere2020Pufferscale,  author = {Cheriere, Nathanael and Dorier, Matthieu and Antiniu, Gabriel and Wild, Stefan M and Leyffer, Sven and Ross, Robert},  title = {Pufferscale: Rescaling HPC Data Services for High Energy Physics Applications},  booktitle = {Proceedings of the 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (Ccgrid)},  series = {CCgrid '20},  year = {2020},  location = {Melbourne, Australia},  pages = {},  numpages = {},  url = {},  doi = {},  acmid = {},  publisher = {IEEE/ACM},  keywords = {Distributed Storage System, Elasticity, Rescaling, Load balancing, High Energy Physics},  pdf = {}}
  55. Cheriere, Nathanael, Matthieu Dorier, and Gabriel Antoniu. 2020. “How Fast Can One Resize a Distributed File System?” Journal of Parallel and Distributed Computing. 
    @article{Cheriere2020HowFast,  title = {How Fast Can One Resize a Distributed File System?},  author = {Cheriere, Nathanael and Dorier, Matthieu and Antoniu, Gabriel},  journal = {Journal of Parallel and Distributed Computing},  volume = {},  pages = {},  year = {2020},  pdf = {},  url = {}}
  56. Rosendo, Daniel, Pedro Silva, Matthieu Simonin, Alexandru Costan, and Gabriel Antoniu. 2020. “E2clab: Exploring the Computing Continuum through Repeatable, Replicable and Reproducible Edge-to-Cloud Experiments.” In 2020 IEEE International Conference on Cluster Computing (CLUSTER), 176–86. IEEE. 
    @inproceedings{DanielEtAl2020,  title = {E2clab: Exploring the computing continuum through repeatable, replicable and reproducible edge-to-cloud experiments},  author = {Rosendo, Daniel and Silva, Pedro and Simonin, Matthieu and Costan, Alexandru and Antoniu, Gabriel},  booktitle = {2020 IEEE International Conference on Cluster Computing (CLUSTER)},  pages = {176--186},  year = {2020},  organization = {IEEE}}
  57. Rüttgers, Mario, Seong-Ryong Koh, Jenia Jitsev, Wolfgang Schröder, and Andreas Lintermann. 2020. “Prediction of Acoustic Fields Using a Lattice-Boltzmann Method and Deep Learning.” In High Performance Computing, Proceedings of the 35th International Conference, ISC High Performance 2020, 81–101. Frankfurt/Main, Germany: Springer International Publishing. https://doi.org/10.1007/978-3-030-59851-8_6. 
    @incollection{Ruttgers2020,  address = {Frankfurt/Main, Germany},  author = {R{\"{u}}ttgers, Mario and Koh, Seong-Ryong and Jitsev, Jenia and Schr{\"{o}}der, Wolfgang and Lintermann, Andreas},  booktitle = {High Performance Computing, Proceedings of the 35th International Conference, ISC High Performance 2020},  doi = {10.1007/978-3-030-59851-8_6},  pages = {81--101},  publisher = {Springer International Publishing},  title = {{Prediction of Acoustic Fields Using a Lattice-Boltzmann Method and Deep Learning}},  url = {http://link.springer.com/10.1007/978-3-030-59851-8{\_}6},  year = {2020}}
  58. Tseng, Shu-Mei, Bogdan Nicolae, George Bosilca, Emmanuel Jeannot, Aparna Chandramowlishwaran, and Franck Cappello. 2019. “Towards Portable Online Prediction of Network Utilization Using MPI-Level Monitoring.” In EuroPar’19: 25th International European Conference on Parallel and Distributed Systems. Goettingen, Germany. https://hal.inria.fr/hal-02184204. 
    @inproceedings{tnb19+,  title = {{Towards Portable Online Prediction of Network Utilization using MPI-level Monitoring}},  author = {Tseng, Shu-Mei and Nicolae, Bogdan and Bosilca, George and Jeannot, Emmanuel and Chandramowlishwaran, Aparna and Cappello, Franck},  url = {https://hal.inria.fr/hal-02184204},  booktitle = {{EuroPar'19: 25th International European Conference on Parallel and Distributed Systems}},  address = {Goettingen, Germany},  year = {2019},  month = aug,  keywords = {Work stealing ; Prediction of resource utilization ; Timeseries forecasting ; Network monitoring ; Online learning},  pdf = {https://hal.inria.fr/hal-02184204/file/paper.pdf},  hal_id = {hal-02184204},  hal_version = {v1}}
  59. Yildiz, O., J. Ejarque, H. Chan, S. Sankaranarayanan, R. M. Badia, and T. Peterka. 2019. “Heterogeneous Hierarchical Workflow Composition.” Computing in Science Engineering 21 (4): 76–86. https://doi.org/10.1109/MCSE.2019.2918766. 
    @article{Yildiz2019,  author = {{Yildiz}, O. and {Ejarque}, J. and {Chan}, H. and {Sankaranarayanan}, S. and {Badia}, R. M. and {Peterka}, T.},  journal = {Computing in Science Engineering},  title = {Heterogeneous Hierarchical Workflow Composition},  year = {2019},  volume = {21},  number = {4},  pages = {76-86},  keywords = {natural sciences computing;workflow management software;hierarchical heterogeneous workflow;heterogeneous hierarchical workflow composition;workflow systems;automated end-to-end path;single workflow system;end-to-end workflow;in situ workflows;subworkflows;data models;materials science use cases;Task analysis;Computational modeling;Workflow management software;Data models;Data visualization;Analytical models;Heterogeneous networks},  doi = {10.1109/MCSE.2019.2918766},  issn = {1558-366X},  month = jul}
  60. Roy, Rupak, Kento Sato, Jian Guo, Jens Domke, Weikuan Yu, Takaki Hatsui, and Yasumasa Joti. 2019. “Poster: Improving Data Compression with Deep Predictive Neural Network for Time Evolutional Data.” In SC’2019, the IEEE/ACM Conference on High Performance Computing Networking, Storage and Analysis. ACM Press. 
    @inproceedings{Rupak20,  author = {Roy, Rupak and Sato, Kento and Guo, Jian and Domke, Jens and Yu, Weikuan and Hatsui, Takaki and Joti, Yasumasa},  booktitle = {{SC'2019}, the IEEE/ACM Conference on High Performance Computing Networking, Storage and Analysis},  title = {Poster: Improving Data Compression with Deep Predictive Neural Network for Time Evolutional Data},  publisher = {ACM Press},  year = {2019}}
  61. Hori, Atsushi, George Bosilca, Emmanuel Jeannot, Takahiro Ogura, and Yutaka Ishikawa. 2019. “Is Japanese HPC Another Galapagos? - Interim Report of MPI International Survey -.” In SIGHPC. Information Processing Society of Japan. 
    @inproceedings{ahori-IPSJ-2019-July,  author = {Hori, Atsushi and Bosilca, George and Jeannot, Emmanuel and Ogura, Takahiro and Ishikawa, Yutaka},  title = {{Is Japanese HPC another Galapagos? - Interim Report of MPI International Survey -}},  journal = {SIGHPC},  issn = {},  publisher = {Information Processing Society of Japan},  year = {2019},  month = jul,  number = {34}}
  62. Reza, Tasmia, Jon Calhoun, Kristopher Keipert, Sheng Di, and Franck Cappello. 2019. “ Analyzing the Performance and Accuracy of Lossy Checkpointing on Sub-Iteration of NWChem.” In 2019 IEEE/ACM 5th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD). 
    @inproceedings{RezaEtAl2019,  author = {Reza, Tasmia and Calhoun, Jon and Keipert, Kristopher and Di, Sheng and Cappello, Franck},  title = { Analyzing the Performance and Accuracy of Lossy Checkpointing on Sub-Iteration        of NWChem},  booktitle = {2019 IEEE/ACM 5th International Workshop on Data Analysis and Reduction for Big        Scientific Data (DRBSD)},  year = {2019},  volume = {},  number = {},  pages = {},  doi = {},  issn = {},  month = nov}
  63. Elmore, Donald, and Jon Calhoun. 2019. “Evaluating Lossy Compressors for Inline Compression.” In Poster Session of the 2019 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis. SC ’19. Washington, DC, USA: IEEE Computer Society. 
    @inproceedings{ElmoreCalhoun2019,  title = {Evaluating Lossy Compressors for Inline Compression},  author = {Elmore, Donald and Calhoun, Jon},  booktitle = {Poster Session of the 2019 ACM/IEEE International Conference for High Performance        Computing, Networking, Storage and Analysis},  series = {SC '19},  year = {2019},  publisher = {IEEE Computer Society},  address = {Washington, DC, USA}}
  64. Benoit, Anne, Thomas Hérault, Valentin Le Fèvre, and Yves Robert. 2019. “Replication Is More Efficient than You Think.” In SC’2019, the IEEE/ACM Conference on High Performance Computing Networking, Storage and Analysis. ACM Press. 
    @inproceedings{BenoitEtAl2019,  author = {Benoit, Anne and Hérault, Thomas and Fèvre, Valentin Le and Robert, Yves},  booktitle = {{SC'2019}, the IEEE/ACM Conference on High Performance Computing Networking, Storage and Analysis},  title = {Replication is more efficient than you think},  publisher = {ACM Press},  year = {2019}}
  65. Wang, Chen, Nikoli Dryden, Franck Cappello, and Marc Snir. 2018. “Neural Network Based Silent Error Detector.” In IEEE International Conference on Cluster Computing, CLUSTER 2018, Belfast, UK, September 10-13, 2018, 168–78. 
    @inproceedings{clusterWangDCS18,  author = {Wang, Chen and Dryden, Nikoli and Cappello, Franck and Snir, Marc},  title = {Neural Network Based Silent Error Detector},  booktitle = {{IEEE} International Conference on Cluster Computing, {CLUSTER} 2018,                 Belfast, UK, September 10-13, 2018},  pages = {168--178},  year = {2018}}
  66. Tao, Dingwen, Sheng Di, Xin Liang, Zizhong Chen, and Franck Cappello. 2018. “Improving Performance of Iterative Methods by Lossy Checkponting.” In Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2018, Tempe, AZ, USA, June 11-15, 2018, 52–65. 
    @inproceedings{HPDC2018,  author = {Tao, Dingwen and Di, Sheng and Liang, Xin and Chen, Zizhong and Cappello, Franck},  title = {Improving performance of iterative methods by lossy checkponting},  booktitle = {Proceedings of the 27th International Symposium on High-Performance                 Parallel and Distributed Computing, {HPDC} 2018, Tempe, AZ, USA, June                 11-15, 2018},  pages = {52--65},  year = {2018}}
  67. 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. 
    @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}}
  68. Fèvre, Valentin Le, George Bosilca, Aurelien Bouteiller, Thomas Herault, Atsushi Hori, Yves Robert, and Jack Dongarra. 2018. “Do Moldable Applications Perform Betteron Failure-Prone HPC Platforms?” In Resilience: 11th Workshop on Resiliency in High Performance Computing in Clusters, Clouds, and Grids, Jointly Published with Euro-Par 2018. LNCS. Springer Verlag. 
    @inproceedings{LeFevreEtAl2018,  author = {Fèvre, Valentin Le and Bosilca, George and Bouteiller, Aurelien and Herault, Thomas and Hori, Atsushi and Robert, Yves and Dongarra, Jack},  booktitle = {{Resilience}: 11th Workshop on Resiliency in High Performance Computing    in Clusters, Clouds, and Grids,                  jointly published with {Euro-Par 2018}},  title = {{Do moldable applications perform better  on failure-prone HPC platforms?}},  year = {2018},  series = {LNCS},  publisher = {Springer Verlag}}
  69. Hérault, Thomas, Yves Robert, Aurélien Bouteiller, Dorian Arnold, Kurt Ferreira, George Bosilca, and Jack Dongarra. 2018. “Optimal Cooperative Checkpointing for Shared High-Performance Computing Platforms.” In 20th Workshop on Advances in Parallel and Distributed Computational Models APDCM 2018. IEEE Computer Society Press. 
    @inproceedings{HeraultEtAl2018,  author = {Hérault, Thomas and Robert, Yves and Bouteiller, Aurélien and Arnold, Dorian and Ferreira, Kurt and Bosilca, George and Dongarra, Jack},  booktitle = {20th Workshop on Advances in Parallel and Distributed                                Computational Models {APDCM 2018}},  publisher = {IEEE Computer Society Press},  title = {Optimal cooperative checkpointing for shared high-performance computing platforms},  year = {2018}}
  70. Benoit, Anne, Swann Perarnau, Loïc Pottier, and Yves Robert. 2018. “A Performance Model to Execute Workflows on High-Bandwidth Memory Architectures.” In ICPP’2018, the 47th Int. Conf. on Parallel Processing. IEEE Computer Society Press. 
    @inproceedings{BenoitEtAl2018b,  author = {Benoit, Anne and Perarnau, Swann and Pottier, Loïc and Robert, Yves},  booktitle = {{ICPP'2018}, the 47th Int. Conf. on Parallel Processing},  title = {A performance model to execute workflows on high-bandwidth memory architectures},  publisher = {{IEEE} Computer Society Press},  year = {2018}}
  71. Benoit, Anne, Aurélien Cavelan, Franck Cappello, Padma Raghavan, Yves Robert, and Hongyang Sun. 2018. “Coping with Silent and Fail-Stop Errors at Scale by Combining Replication and Checkpointing.” J. Parallel and Distributed Computing. 
    @article{BenoitEtAl2018,  author = {Benoit, Anne and Cavelan, Aurélien and Cappello, Franck and Raghavan, Padma and Robert, Yves and Sun, Hongyang},  journal = {J. Parallel and Distributed Computing},  title = {Coping with silent and fail-stop errors at scale by combining replication and checkpointing},  year = {2018},  badvolume = {98},  badpages = {8-24}}
  72. Cheriere, Nathanaël, Matthieu Dorier, and Gabriel Antoniu. 2018. “A Lower Bound for the Commission Times in Replication-Based Distributed Storage Systems.” Research Report RR-9186. Inria Rennes - Bretagne Atlantique. https://hal.archives-ouvertes.fr/hal-01817638. 
    @techreport{Cheriere2018LowerCommission,  title = {{A Lower Bound for the Commission Times in Replication-Based Distributed Storage Systems}},  author = {Cheriere, Nathana{\"e}l and Dorier, Matthieu and Antoniu, Gabriel},  url = {https://hal.archives-ouvertes.fr/hal-01817638},  type = {Research Report},  number = {RR-9186},  pages = {1-26},  institution = {{Inria Rennes - Bretagne Atlantique}},  year = {2018},  month = jun,  keywords = {Commission ; Elastic Storage ; Distributed File System ; Malleable File System ; Lower Bound},  pdf = {https://hal.archives-ouvertes.fr/hal-01817638/file/RR-9186.pdf},  hal_id = {hal-01817638},  hal_version = {v2}}
  73. ———. 2018. “Pufferbench: Evaluating and Optimizing Malleability of Distributed Storage.” In PDSW-DISCS 2018: 3rd Joint International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems, 1–10. Dallas, United States. https://hal.archives-ouvertes.fr/hal-01892713. 
    @inproceedings{Cheriere2018Pufferbench,  title = {{Pufferbench: Evaluating and Optimizing Malleability of Distributed Storage}},  author = {Cheriere, Nathana{\"e}l and Dorier, Matthieu and Antoniu, Gabriel},  url = {https://hal.archives-ouvertes.fr/hal-01892713},  booktitle = {{PDSW-DISCS 2018: 3rd Joint International workshop on Parallel Data Storage \& Data Intensive Scalable computing Systems}},  address = {Dallas, United States},  pages = {1-10},  year = {2018},  month = nov,  keywords = {Distributed Storage System Malleability ; Benchmark ; Pufferbench},  pdf = {https://hal.archives-ouvertes.fr/hal-01892713/file/Paper.pdf},  hal_id = {hal-01892713},  hal_version = {v1}}
  74. ———. 2018. “Lower Bounds for the Duration of Decommission Operations with Relaxed Fault Tolerance in Replication-Based Distributed Storage Systems.” Research Report RR-9229. Inria Rennes - Bretagne Atlantique. https://hal.archives-ouvertes.fr/hal-01943964. 
    @techreport{Cheriere2018LowerRelaxed,  title = {{Lower Bounds for the Duration of Decommission Operations with Relaxed Fault Tolerance in Replication-based Distributed Storage Systems}},  author = {Cheriere, Nathana{\"e}l and Dorier, Matthieu and Antoniu, Gabriel},  url = {https://hal.archives-ouvertes.fr/hal-01943964},  type = {Research Report},  number = {RR-9229},  pages = {1-28},  institution = {{Inria Rennes - Bretagne Atlantique}},  year = {2018},  month = dec,  keywords = {Distributed Storage Systems ; Malleable Storage ; Fault Tolerance ; Elastic Storage ; Syst{\`e}me de stockage distribu{\'e} ; Stockage {\'e}lastique ; Stockage mall{\'e}able ; D{\'e}commission ; Tol{\'e}rance aux pannes},  pdf = {https://hal.archives-ouvertes.fr/hal-01943964/file/Report.pdf},  hal_id = {hal-01943964},  hal_version = {v2}}
  75. 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}}
  76. Matri, Pierre, Philip Carns, Robert Ross, Alexandru Costan, María S Pérez, and Gabriel Antoniu. 2018. “SLoG: Large-Scale Logging Middleware for HPC and Big Data Convergence.” In 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS). IEEE. 
    @inproceedings{MatriEtAl2018Streaming,  title = {{SLoG: Large-Scale Logging Middleware for HPC and Big Data Convergence}},  author = {Matri, Pierre and Carns, Philip and Ross, Robert and Costan, Alexandru and Pérez, María S and Antoniu, Gabriel},  booktitle = {2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)},  year = {2018},  organization = {IEEE}}
  77. 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 . https://doi.org/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 }}
  78. “Report of the Third Global Experimentation for Future Internet (GEFI 2018) Workshop.” 2018. Tokyo, Japan. http://indico.rnp.br/conferenceDisplay.py?confId=260. 
    @misc{BermanEtAl,  title = {Report of the Third Global Experimentation for Future Internet (GEFI 2018) Workshop},  author = {},  address = {Tokyo, Japan},  url = {http://indico.rnp.br/conferenceDisplay.py?confId=260},  month = oct,  year = {2018}}
  79. 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}}
  80. 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}}
  81. 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}}
  82. 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. https://doi.org/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}
  83. Cheriere, Nathanaël, and Gabriel Antoniu. 2017. “How Fast Can One Scale Down a Distributed File System?” In BigData. Boston, United States. https://doi.org/10.1109/BigData.2017.8257922. 
    @inproceedings{Cheriere2017How,  title = {{How Fast Can One Scale Down a Distributed File System?}},  author = {Cheriere, Nathana{\"e}l and Antoniu, Gabriel},  url = {https://hal.archives-ouvertes.fr/hal-01644928},  booktitle = {{BigData}},  address = {Boston, United States},  year = {2017},  month = dec,  doi = {10.1109/BigData.2017.8257922},  keywords = {Decommission ; Model ; Malleable File System ; Distributed File System ; Elastic Storage},  pdf = {https://hal.archives-ouvertes.fr/hal-01644928/file/ModelingDecommision.pdf},  hal_id = {hal-01644928},  hal_version = {v1}}
  84. 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}}
  85. 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. https://doi.org/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}}
  86. 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}}
  87. 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}}
  88. 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}}
  89. 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}}
  90. 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}}
  91. 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}}
  92. 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}}
  93. 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}}
  94. 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}}
  95. 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}}
  96. 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}}
  97. Di, Sheng, and Franck Cappello. 2016. “ Adaptive-Impact Driven Detection of Silent Data Corruption for HPC Applications.” IEEE Transactions on Parallel and Distributed Computing. 
    @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}}
  98. 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}}
  99. 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}}
  100. 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): 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}}
  101. 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}}
  102. 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}}
  103. 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}}
  104. 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): 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}}
  105. 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}}
  106. 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: 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}}
  107. 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}}
  108. 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}}
  109. 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}}
  110. 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}}
  111. 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}}
  112. 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. https://doi.org/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}}
  113. 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. https://doi.org/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}}
  114. 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. https://doi.org/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}}
  115. 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}}
  116. 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. https://doi.org/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}
  117. 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}}
  118. 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 & 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}}
  119. 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. https://doi.org/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}}
  120. 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. https://doi.org/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}}
  121. 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}}
  122. 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. https://doi.org/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}}
  123. ———. 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}}
  124. 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): 273–82. https://doi.org/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}}