All publications sorted by year

Table of Contents

2022

  1. Emmanuel Agullo, Alfredo Buttari, Abdou Guermouche, Julien Herrmann, and Antoine Jego
    Task-Based Parallel Programming for Scalable Algorithms: application to Matrix Multiplication
    Research Report 9461, Inria Bordeaux - Sud-Ouest, February 2022
    [WWW] [PDF] Keyword(s): Papers related to StarPU, Mathematical software, parallelism, task-based programming, scalability, communication patterns, matrix multiplication, Logiciels mathématiques, parallélisme, programmation à base de tâches, passage à l'échelle, schémas de communication, multiplication matricielle
    [bibtex-key = agullo:hal-03588491]

    @techreport{agullo:hal-03588491,
    TITLE = {{Task-Based Parallel Programming for Scalable Algorithms: application to Matrix Multiplication}},
    AUTHOR = {Agullo, Emmanuel and Buttari, Alfredo and Guermouche, Abdou and Herrmann, Julien and Jego, Antoine},
    URL = {https://hal.inria.fr/hal-03588491},
    TYPE = {Research Report},
    NUMBER = {9461},
    PAGES = {26},
    INSTITUTION = {{Inria Bordeaux - Sud-Ouest}},
    YEAR = {2022},
    MONTH = Feb,
    KEYWORDS = {Papers related to StarPU ; Mathematical software ; parallelism ; task-based programming ; scalability ; communication patterns ; matrix multiplication ; Logiciels math{\'e}matiques ; parall{\'e}lisme ; programmation {\`a} base de t{\^a}ches ; passage {\`a} l'{\'e}chelle ; sch{\'e}mas de communication ; multiplication matricielle},
    PDF = {https://hal.inria.fr/hal-03588491/file/RR-9461.pdf},
    HAL_ID = {hal-03588491},
    HAL_VERSION = {v1},
    
    }
    
  2. Mathieu Faverge, Nathalie Furmento, Gwenolé Lucas, Abdou Guermouche, Raymond Namyst, Samuel Thibault, and Pierre-André Wacrenier
    Programming Heterogeneous Architectures Using Hierarchical Tasks
    Research Report RR-9466, Inria Bordeaux Sud-Ouest, March 2022
    [WWW] [PDF] Keyword(s): On Hierarchical Tasks, Multicore, accelerator, GPU, heterogeneous computing, task graph, programming model, runtime system, dense linear algebra, Multi-c$÷$urs, Accélérateurs, GPU, Calcul hétérogène, Graphe de tâches, Modèle de programmation, Support d'exécution, Algèbre linéaire dense
    [bibtex-key = faverge:hal-03609275]

    @techreport{faverge:hal-03609275,
    TITLE = {{Programming Heterogeneous Architectures Using Hierarchical Tasks}},
    AUTHOR = {Faverge, Mathieu and Furmento, Nathalie and Lucas, Gwenol{\'e} and Guermouche, Abdou and Namyst, Raymond and Thibault, Samuel and Wacrenier, Pierre-Andr{\'e}},
    URL = {https://hal.inria.fr/hal-03609275},
    TYPE = {Research Report},
    NUMBER = {RR-9466},
    INSTITUTION = {{Inria Bordeaux Sud-Ouest}},
    YEAR = {2022},
    MONTH = Mar,
    KEYWORDS = {On Hierarchical Tasks ; Multicore ; accelerator ; GPU ; heterogeneous computing ; task graph ; programming model ; runtime system ; dense linear algebra ; Multi-c$\div$urs ; Acc{\'e}l{\'e}rateurs ; GPU ; Calcul h{\'e}t{\'e}rog{\`e}ne ; Graphe de t{\^a}ches ; Mod{\`e}le de programmation ; Support d'ex{\'e}cution ; Alg{\`e}bre lin{\'e}aire dense},
    PDF = {https://hal.inria.fr/hal-03609275/file/RR-9466.pdf},
    HAL_ID = {hal-03609275},
    HAL_VERSION = {v1},
    
    }
    

2021

  1. Emmanuel Agullo, Mirco Altenbernd, Hartwig Anzt, Leonardo Bautista-Gomez, Tommaso Benacchio, Luca Bonaventura, Hans-Joachim Bungartz, Sanjay Chatterjee, Florina M Ciorba, Nathan Debardeleben, Daniel Drzisga, Sebastian Eibl, Christian Engelmann, Wilfried N Gansterer, Luc Giraud, Dominik Göddeke, Marco Heisig, Fabienne Jézéquel, Nils Kohl, Sherry Xiaoye, Romain Lion, Miriam Mehl, Paul Mycek, Michael Obersteiner, Enrique S Quintana-Ortì, Francesco Rizzi, Ulrich Rüde, Martin Schulz, Fred Fung, Robert Speck, Linda Stals, Keita Teranishi, Samuel Thibault, Dominik Thönnes, Andreas Wagner, and Barbara Wohlmuth
    Resiliency in numerical algorithm design for extreme scale simulations
    International Journal of High Performance Computing Applications, September 2021
    [WWW] [PDF] Keyword(s): On MPI Support, Fault tolerance, Task-based programming, Checkpoint-restart, Buddy in-memory
    [bibtex-key = agullo:hal-03348787]

    @article{agullo:hal-03348787,
    TITLE = {{Resiliency in numerical algorithm design for extreme scale simulations}},
    AUTHOR = {Agullo, Emmanuel and Altenbernd, Mirco and Anzt, Hartwig and Bautista-Gomez, Leonardo and Benacchio, Tommaso and Bonaventura, Luca and Bungartz, Hans-Joachim and Chatterjee, Sanjay and Ciorba, Florina M and Debardeleben, Nathan and Drzisga, Daniel and Eibl, Sebastian and Engelmann, Christian and Gansterer, Wilfried N and Giraud, Luc and G{\"o}ddeke, Dominik and Heisig, Marco and J{\'e}z{\'e}quel, Fabienne and Kohl, Nils and Xiaoye, Sherry and Lion, Romain and Mehl, Miriam and Mycek, Paul and Obersteiner, Michael and Quintana-Ort{\'i}, Enrique S and Rizzi, Francesco and R{\"u}de, Ulrich and Schulz, Martin and Fung, Fred and Speck, Robert and Stals, Linda and Teranishi, Keita and Thibault, Samuel and Th{\"o}nnes, Dominik and Wagner, Andreas and Wohlmuth, Barbara},
    URL = {https://hal.inria.fr/hal-03348787},
    JOURNAL = {{International Journal of High Performance Computing Applications}},
    PUBLISHER = {{SAGE Publications}},
    YEAR = {2021},
    MONTH = Sep,
    PDF = {https://hal.inria.fr/hal-03348787/file/2010.13342.pdf},
    KEYWORDS = {On MPI Support ; Fault tolerance ; Task-based programming ; Checkpoint-restart ; Buddy in-memory},
    HAL_ID = {hal-03348787},
    HAL_VERSION = {v1},
    
    }
    
  2. Lazaros Papadopoulos, Dimitrios Soudris, Christoph Kessler, August Ernstsson, Johan Ahlqvist, Nikos Vasilas, Athanasios I Papadopoulos, Panos Seferlis, Charles Prouveur, Matthieu Haefele, Samuel Thibault, Athanasios Salamanis, Theodoros Ioakimidis, and Dionysios Kehagias
    EXA2PRO: A Framework for High Development Productivity on Heterogeneous Computing Systems
    IEEE Transactions on Parallel and Distributed Systems, August 2021
    [WWW] [PDF] [doi:10.1109/TPDS.2021.3104257] Keyword(s): On Applications, programming models, skeleton programming, task-based runtime systems, programming productivity, heterogeneous systems, exascale computing
    [bibtex-key = papadopoulos:hal-03318644]

    @article{papadopoulos:hal-03318644,
    TITLE = {{EXA2PRO: A Framework for High Development Productivity on Heterogeneous Computing Systems}},
    AUTHOR = {Papadopoulos, Lazaros and Soudris, Dimitrios and Kessler, Christoph and Ernstsson, August and Ahlqvist, Johan and Vasilas, Nikos and Papadopoulos, Athanasios I and Seferlis, Panos and Prouveur, Charles and Haefele, Matthieu and Thibault, Samuel and Salamanis, Athanasios and Ioakimidis, Theodoros and Kehagias, Dionysios},
    URL = {https://hal.inria.fr/hal-03318644},
    JOURNAL = {{IEEE Transactions on Parallel and Distributed Systems}},
    PUBLISHER = {{Institute of Electrical and Electronics Engineers}},
    SERIES = {Special Section on Innovative R\\&D toward the Exascale Era},
    YEAR = {2021},
    MONTH = Aug,
    DOI = {10.1109/TPDS.2021.3104257},
    KEYWORDS = {On Applications, programming models ; skeleton programming ; task-based runtime systems ; programming productivity ; heterogeneous systems ; exascale computing},
    PDF = {https://hal.inria.fr/hal-03318644/file/EXA2PRO___TPDS.pdf},
    HAL_ID = {hal-03318644},
    HAL_VERSION = {v1},
    
    }
    
  3. Alexandre Denis, Emmanuel Jeannot, and Philippe Swartvagher
    Interferences between Communications and Computations in Distributed HPC Systems
    In ICPP 2021 - 50th International Conference on Parallel Processing, Chicago / Virtual, United States, pages 11, August 2021
    [WWW] [PDF] [doi:10.1145/3472456.3473516] Keyword(s): Papers related to StarPU, Processor frequency, Memory contention, MPI, HPC, Runtime system
    [bibtex-key = denis:hal-03290121]

    @inproceedings{denis:hal-03290121,
    TITLE = {{Interferences between Communications and Computations in Distributed HPC Systems}},
    AUTHOR = {Denis, Alexandre and Jeannot, Emmanuel and Swartvagher, Philippe},
    URL = {https://hal.inria.fr/hal-03290121},
    BOOKTITLE = {{ICPP 2021 - 50th International Conference on Parallel Processing}},
    ADDRESS = {Chicago / Virtual, United States},
    PAGES = {11},
    YEAR = {2021},
    MONTH = Aug,
    DOI = {10.1145/3472456.3473516},
    KEYWORDS = {Papers related to StarPU ; Processor frequency ; Memory contention ; MPI ; HPC ; Runtime system},
    PDF = {https://hal.inria.fr/hal-03290121/file/rr.pdf},
    HAL_ID = {hal-03290121},
    HAL_VERSION = {v1},
    
    }
    
  4. Maxime Gonthier, Loris Marchal, and Samuel Thibault
    Locality-Aware Scheduling of Independent Tasks for Runtime Systems
    In COLOC: 5th workshop on data locality - 7th International European Conference on Parallel and Distributed Computing Workshops, Lisbon, Portugal, August 2021
    [WWW] [PDF] Keyword(s): On Scheduling, Memory-aware scheduling, Eviction policy, Tasks sharing data, Runtime systems, Ordonnancement sous contrainte mémoire, Politique d'éviction, Tâches partageant des données, Support d'exécution
    [bibtex-key = gonthier:hal-03290998]

    @inproceedings{gonthier:hal-03290998,
    TITLE = {{Locality-Aware Scheduling of Independent Tasks for Runtime Systems}},
    AUTHOR = {Gonthier, Maxime and Marchal, Loris and Thibault, Samuel},
    URL = {https://hal.archives-ouvertes.fr/hal-03290998},
    BOOKTITLE = {{COLOC: 5th workshop on data locality - 7th International European Conference on Parallel and Distributed Computing Workshops}},
    ADDRESS = {Lisbon, Portugal},
    YEAR = {2021},
    MONTH = Aug,
    KEYWORDS = {On Scheduling, Memory-aware scheduling ; Eviction policy ; Tasks sharing data ; Runtime systems ; Ordonnancement sous contrainte m{\'e}moire ; Politique d'{\'e}viction ; T{\^a}ches partageant des donn{\'e}es ; Support d'ex{\'e}cution},
    PDF = {https://hal.archives-ouvertes.fr/hal-03290998/file/coloc-cameraready-submitted.pdf},
    HAL_ID = {hal-03290998},
    HAL_VERSION = {v1},
    
    }
    
  5. Vinicius Garcia Pinto, Lucas Leandro Nesi, Marcelo Cogo Miletto, and Lucas Mello Schnorr
    Providing In-depth Performance Analysis for Heterogeneous Task-based Applications with StarVZ
    In 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), May 2021
    [WWW] Keyword(s): On Scheduling
    [bibtex-key = pintohwc2021]

    @inproceedings{pintohwc2021,
    TITLE = {{Providing In-depth Performance Analysis for Heterogeneous Task-based Applications with StarVZ}},
    AUTHOR = {Pinto, Vinicius Garcia and Nesi, Lucas Leandro and Miletto, Marcelo Cogo and Schnorr, Lucas Mello },
    booktitle={2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
    URL = {https://drive.google.com/file/d/18IYdLW9eiSDzwMM3RJV0Flp83OcBWp5R/view?usp=sharing},
    YEAR = {2021},
    MONTH = May,
    KEYWORDS = {On Scheduling},
    
    }
    
  6. Maxime Gonthier, Loris Marchal, and Samuel Thibault
    Locality-Aware Scheduling of Independant Tasks for Runtime Systems
    Research Report RR-9394, Inria, 2021
    [WWW] [PDF] Keyword(s): On Scheduling, Tasks sharing data, Eviction policy, Memory-aware scheduling, Runtime systems, Ordonnancement sous contrainte mémoire, Politique d'éviction, Tâches partageant des données, Support d'exécution
    [bibtex-key = gonthier:hal-03144290]

    @techreport{gonthier:hal-03144290,
    TITLE = {{Locality-Aware Scheduling of Independant Tasks for Runtime Systems}},
    AUTHOR = {Gonthier, Maxime and Marchal, Loris and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-03144290},
    TYPE = {Research Report},
    NUMBER = {RR-9394},
    PAGES = {22},
    INSTITUTION = {{Inria}},
    YEAR = {2021},
    KEYWORDS = {On Scheduling, Tasks sharing data ; Eviction policy ; Memory-aware scheduling ; Runtime systems ; Ordonnancement sous contrainte m{\'e}moire ; Politique d'{\'e}viction ; T{\^a}ches partageant des donn{\'e}es ; Support d'ex{\'e}cution},
    PDF = {https://hal.inria.fr/hal-03144290v5/file/RR_coloc2021-submitted.pdf},
    HAL_ID = {hal-03144290},
    HAL_VERSION = {v5},
    
    }
    

2020

  1. Idriss Daoudi, Philippe Virouleau, Thierry Gautier, Samuel Thibault, and Olivier Aumage
    sOMP: Simulating OpenMP Task-Based Applications with NUMA Effects
    In IWOMP 2020 - 16th International Workshop on OpenMP, volume 12295 of LNCS, Austin, USA, September 2020
    Springer
    [WWW] [PDF] [doi:10.1007/978-3-030-58144-2_13] Keyword(s): On The Simulation Support through SimGrid, OpenMP tasks, NUMA architecture, Performance modeling, Simulation
    [bibtex-key = daoudi:hal-02933803]

    @inproceedings{daoudi:hal-02933803,
    TITLE = {{sOMP: Simulating OpenMP Task-Based Applications with NUMA Effects}},
    AUTHOR = {Daoudi, Idriss and Virouleau, Philippe and Gautier, Thierry and Thibault, Samuel and Aumage, Olivier},
    URL = {https://hal.inria.fr/hal-02933803},
    BOOKTITLE = {{IWOMP 2020 - 16th International Workshop on OpenMP}},
    ADDRESS = {Austin, USA},
    PUBLISHER = {{Springer}},
    SERIES = {LNCS},
    VOLUME = {12295},
    YEAR = {2020},
    MONTH = Sep,
    DOI = {10.1007/978-3-030-58144-2\_13},
    KEYWORDS = {On The Simulation Support through SimGrid; OpenMP tasks ; NUMA architecture ; Performance modeling ; Simulation},
    PDF = {https://hal.inria.fr/hal-02933803/file/p05_daoudi.pdf},
    HAL_ID = {hal-02933803},
    HAL_VERSION = {v1},
    
    }
    
  2. Alexandre Denis, Emmanuel Jeannot, Philippe Swartvagher, and Samuel Thibault
    Using Dynamic Broadcasts to improve Task-Based Runtime Performances
    In Euro-Par - 26th International European Conference on Parallel and Distributed Computing, Warsaw, Poland, August 2020
    Rzadca and Malawski, Springer
    [WWW] [PDF] [doi:10.1007/978-3-030-57675-2_28] Keyword(s): On MPI Support, Task-based runtime system, communications, collective, broadcast
    [bibtex-key = denis:hal-02872765]

    @inproceedings{denis:hal-02872765,
    TITLE = {{Using Dynamic Broadcasts to improve Task-Based Runtime Performances}},
    AUTHOR = {Denis, Alexandre and Jeannot, Emmanuel and Swartvagher, Philippe and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-02872765},
    BOOKTITLE = {{Euro-Par - 26th International European Conference on Parallel and Distributed Computing}},
    ADDRESS = {Warsaw, Poland},
    ORGANIZATION = {{Rzadca and Malawski}},
    PUBLISHER = {{Springer}},
    YEAR = {2020},
    MONTH = Aug,
    DOI = {10.1007/978-3-030-57675-2_28},
    KEYWORDS = {On MPI Support ; Task-based runtime system ; communications ; collective ; broadcast},
    PDF = {https://hal.inria.fr/hal-02872765/file/dynamic_broadcasts.pdf},
    HAL_ID = {hal-02872765},
    HAL_VERSION = {v1},
    
    }
    
  3. Romain Lion and Samuel Thibault
    From tasks graphs to asynchronous distributed checkpointing with local restart
    In 2020 IEEE/ACM 10th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS), Atlanta, USA, November 2020
    [WWW] [PDF] [doi:10.1109/FTXS51974.2020.00009] Keyword(s): On MPI Support, Fault tolerance, Task-based programming, Checkpoint-restart, Buddy in-memory
    [bibtex-key = lion:hal-02970529]

    @inproceedings{lion:hal-02970529,
    TITLE = {{From tasks graphs to asynchronous distributed checkpointing with local restart}},
    AUTHOR = {Lion, Romain and Thibault, Samuel},
    URL = {https://hal.archives-ouvertes.fr/hal-02970529},
    BOOKTITLE = {{2020 IEEE/ACM 10th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)}},
    ADDRESS = {Atlanta, USA},
    YEAR = {2020},
    MONTH = Nov,
    DOI = {10.1109/FTXS51974.2020.00009},
    KEYWORDS = {On MPI Support ; Fault tolerance ; Task-based programming ; Checkpoint-restart ; Buddy in-memory},
    PDF = {https://hal.archives-ouvertes.fr/hal-02970529/file/2020001221.pdf},
    HAL_ID = {hal-02970529},
    HAL_VERSION = {v1},
    
    }
    
  4. Rafael Alvares da Silva Lopes, Samuel Thibault, and Alba Cristina Magalhães Alves de Melo
    MASA-StarPU: Parallel Sequence Comparison with Multiple Scheduling Policies and Pruning
    In SBAC-PAD 2020 - IEEE 32nd International Symposium on Computer Architecture and High Performance Computing, Porto, Portugal, September 2020
    [WWW] [PDF] [doi:10.1109/SBAC-PAD49847.2020.00039] Keyword(s): On Applications, Parallel sequence comparison, parallel programming environment, dynamic programming
    [bibtex-key = lopes:hal-02914793]

    @inproceedings{lopes:hal-02914793,
    TITLE = {{MASA-StarPU: Parallel Sequence Comparison with Multiple Scheduling Policies and Pruning}},
    AUTHOR = {Lopes, Rafael Alvares da Silva and Thibault, Samuel and Melo, Alba Cristina Magalh{\~a}es Alves de},
    URL = {https://hal.inria.fr/hal-02914793},
    BOOKTITLE = {{SBAC-PAD 2020 - IEEE 32nd International Symposium on Computer Architecture and High Performance Computing}},
    ADDRESS = {Porto, Portugal},
    YEAR = {2020},
    MONTH = Sep,
    DOI = {10.1109/SBAC-PAD49847.2020.00039},
    KEYWORDS = {On Applications ; Parallel sequence comparison ; parallel programming environment ; dynamic programming},
    PDF = {https://hal.inria.fr/hal-02914793/file/lopes_rafael_paper25_sbacpad2020.pdf},
    HAL_ID = {hal-02914793},
    HAL_VERSION = {v1},
    
    }
    
  5. Elliott Slaughter, Wei Wu, Yuankun Fu, Legend Brandenburg, Nicolai Garcia, Wilhem Kautz, Emily Marx, Kaleb S. Morris, Qinglei Cao, George Bosilca, Seema Mirchandaney, Wonchan Lee, Sean Treichler, Patrick McCormick, and Alex Aiken
    Task Bench: A Parameterized Benchmark for Evaluating Parallel Runtime Performance
    In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC '20, 2020
    IEEE Press
    ISBN: 9781728199986
    [WWW] [PDF] [doi:10.5555/3433701.3433783] Keyword(s): Papers related to StarPU
    <center> <table border=1 align=center width=80%> We present Task Bench, a parameterized benchmark designed to explore the performance of distributed programming systems under a variety of application scenarios. Task Bench dramatically lowers the barrier to benchmarking and comparing multiple programming systems by making the implementation for a given system orthogonal to the benchmarks themselves: every benchmark constructed with Task Bench runs on every Task Bench implementation. Furthermore, Task Bench's parameterization enables a wide variety of benchmark scenarios that distill the key characteristics of larger applications.To assess the effectiveness and overheads of the tested systems, we introduce a novel metric, minimum effective task granularity (METG). We conduct a comprehensive study with 15 programming systems on up to 256 Haswell nodes of the Cori supercomputer. Running at scale, 100μs-long tasks are the finest granularity that any system runs efficiently with current technologies. We also study each system's scalability, ability to hide communication and mitigate load imbalance.</td>

Abstract: || [bibtex-key = 10.5555/3433701.3433783]

@inproceedings{10.5555/3433701.3433783,
author = {Slaughter, Elliott and Wu, Wei and Fu, Yuankun and Brandenburg, Legend and Garcia, Nicolai and Kautz, Wilhem and Marx, Emily and Morris, Kaleb S. and Cao, Qinglei and Bosilca, George and Mirchandaney, Seema and Lee, Wonchan and Treichler, Sean and McCormick, Patrick and Aiken, Alex},
title = {Task Bench: A Parameterized Benchmark for Evaluating Parallel Runtime Performance},
year = {2020},
isbn = {9781728199986},
publisher = {IEEE Press},
abstract = {We present Task Bench, a parameterized benchmark designed to explore the performance of distributed programming systems under a variety of application scenarios. Task Bench dramatically lowers the barrier to benchmarking and comparing multiple programming systems by making the implementation for a given system orthogonal to the benchmarks themselves: every benchmark constructed with Task Bench runs on every Task Bench implementation. Furthermore, Task Bench's parameterization enables a wide variety of benchmark scenarios that distill the key characteristics of larger applications.To assess the effectiveness and overheads of the tested systems, we introduce a novel metric, minimum effective task granularity (METG). We conduct a comprehensive study with 15 programming systems on up to 256 Haswell nodes of the Cori supercomputer. Running at scale, 100μs-long tasks are the finest granularity that any system runs efficiently with current technologies. We also study each system's scalability, ability to hide communication and mitigate load imbalance.},
booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
articleno = {62},
numpages = {15},
location = {Atlanta, Georgia},
series = {SC '20},
doi = {10.5555/3433701.3433783},
url = {https://dl.acm.org/doi/10.5555/3433701.3433783},
pdf = {https://dl.acm.org/doi/pdf/10.5555/3433701.3433783},
keywords = {Papers related to StarPU} 
}
  1. Samuel Thibault, Luka Stanisic, and Arnaud Legrand
    Faithful Performance Prediction of a Dynamic Task-based Runtime System, an Opportunity for Task Graph Scheduling
    In SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2020), Seattle, USA, February 2020
    [WWW] [PDF] Keyword(s): On The Simulation Support through SimGrid
    [bibtex-key = thibault:hal-02943753]

    @inproceedings{thibault:hal-02943753,
    TITLE = {{Faithful Performance Prediction of a Dynamic Task-based Runtime System, an Opportunity for Task Graph Scheduling}},
    AUTHOR = {Thibault, Samuel and Stanisic, Luka and Legrand, Arnaud},
    URL = {https://hal.inria.fr/hal-02943753},
    BOOKTITLE = {{SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2020)}},
    ADDRESS = {Seattle, USA},
    YEAR = {2020},
    MONTH = Feb,
    KEYWORDS = {On The Simulation Support through SimGrid},
    PDF = {https://hal.inria.fr/hal-02943753/file/20-02-15-siampp-seattle.pdf},
    HAL_ID = {hal-02943753},
    HAL_VERSION = {v1},
    
    }
    
  2. Georgios Tzanos, Vineet Soni, Charles Prouveur, Matthieu Haefele, Stavroula Zouzoula, Lazaros Papadopoulos, Samuel Thibault, Nicolas Vandenbergen, Dirk Pleiter, and Dimitrios Soudris
    Applying StarPU runtime system to scientific applications: Experiences and lessons learned
    In Parallel Optimization using/for Multi and Many-core High Performance Computing (POMCO), Barcelona, Spain, December 2020
    [WWW] [PDF] Keyword(s): On Applications, StarPU, task-based programming models, HPC
    [bibtex-key = soni:hal-02985721]

    @inproceedings{soni:hal-02985721,
    TITLE = {{Applying StarPU runtime system to scientific applications: Experiences and lessons learned}},
    AUTHOR = {Tzanos, Georgios and Soni, Vineet and Prouveur, Charles and Haefele, Matthieu and Zouzoula, Stavroula and Papadopoulos, Lazaros and Thibault, Samuel and Vandenbergen, Nicolas and Pleiter, Dirk and Soudris, Dimitrios},
    URL = {https://hal.inria.fr/hal-02985721},
    BOOKTITLE = {{Parallel Optimization using/for Multi and Many-core High Performance Computing (POMCO)}},
    ADDRESS = {Barcelona, Spain},
    YEAR = {2020},
    MONTH = Dec,
    HAL_ID = {hal-02985721},
    HAL_VERSION = {v1},
    KEYWORDS = {On Applications; StarPU ; task-based programming models ; HPC},
    PDF = {https://hal.inria.fr/hal-02985721/file/POMCO2020-camera-ready.pdf},
    
    }
    

2019

  1. Bérenger Bramas
    Impact study of data locality on task-based applications through the Heteroprio scheduler
    PeerJ Computer Science, May 2019
    [WWW] [PDF] [doi:10.7717/peerj-cs.190] Keyword(s): On Scheduling, Task-based, Starpu, HPC, Data locality
    [bibtex-key = bramas:hal-02120736]

    @article{bramas:hal-02120736,
    TITLE = {{Impact study of data locality on task-based applications through the Heteroprio scheduler}},
    AUTHOR = {Bramas, B{\'e}renger},
    URL = {https://hal.inria.fr/hal-02120736},
    JOURNAL = {{PeerJ Computer Science}},
    PUBLISHER = {{PeerJ}},
    YEAR = {2019},
    MONTH = May,
    DOI = {10.7717/peerj-cs.190},
    KEYWORDS = {On Scheduling ; Task-based ; Starpu ; HPC ; Data locality},
    PDF = {https://hal.inria.fr/hal-02120736/file/peerj-cs-190.pdf},
    HAL_ID = {hal-02120736},
    HAL_VERSION = {v1},
    
    }
    
  2. A. AlOnazi, H. Ltaief, D. Keyes, I. Said, and Samuel Thibault
    Asynchronous Task-Based Execution of the Reverse Time Migration for the Oil and Gas Industry
    In 2019 IEEE International Conference on Cluster Computing (CLUSTER), Albuquerque, USA, pages 1-11, September 2019
    IEEE
    [WWW] [PDF] [doi:10.1109/CLUSTER.2019.8891054] Keyword(s): On Applications, Index Terms-Reverse Time Migration, Task-Based Program- ming Model, Out-Of-Core Algorithms, Asynchronous Executions, Overlapping I/O with Computation, STARPU OOC
    [bibtex-key = alonazi:hal-02403109]

    @inproceedings{alonazi:hal-02403109,
    TITLE = {{Asynchronous Task-Based Execution of the Reverse Time Migration for the Oil and Gas Industry}},
    AUTHOR = {AlOnazi, A. and Ltaief, H. and Keyes, D. and Said, I. and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-02403109},
    BOOKTITLE = {{2019 IEEE International Conference on Cluster Computing (CLUSTER)}},
    ADDRESS = {Albuquerque, USA},
    PUBLISHER = {{IEEE}},
    PAGES = {1-11},
    YEAR = {2019},
    MONTH = Sep,
    DOI = {10.1109/CLUSTER.2019.8891054},
    KEYWORDS = {On Applications; Index Terms-Reverse Time Migration ; Task-Based Program- ming Model ; Out-Of-Core Algorithms ; Asynchronous Executions ; Overlapping I/O with Computation ; STARPU OOC},
    PDF = {https://hal.inria.fr/hal-02403109/file/2019_tbrtm_cluster.pdf},
    HAL_ID = {hal-02403109},
    HAL_VERSION = {v1},
    
    }
    
  3. Lucas Leandro Nesi, Samuel Thibault, Luka Stanisic, and Lucas Mello Schnorr
    Visual Performance Analysis of Memory Behavior in a Task-Based Runtime on Hybrid Platforms
    In 2019 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), Larnaca, Cyprus, pages 142-151, May 2019
    IEEE
    [WWW] [PDF] [doi:10.1109/CCGRID.2019.00025] Keyword(s): On Scheduling
    [bibtex-key = leandronesi:hal-02275363]

    @inproceedings{leandronesi:hal-02275363,
    TITLE = {{Visual Performance Analysis of Memory Behavior in a Task-Based Runtime on Hybrid Platforms}},
    AUTHOR = {Leandro Nesi, Lucas and Thibault, Samuel and Stanisic, Luka and Mello Schnorr, Lucas},
    URL = {https://hal.inria.fr/hal-02275363},
    BOOKTITLE = {{2019 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)}},
    ADDRESS = {Larnaca, Cyprus},
    PUBLISHER = {{IEEE}},
    PAGES = {142-151},
    YEAR = {2019},
    MONTH = May,
    DOI = {10.1109/CCGRID.2019.00025},
    KEYWORDS = {On Scheduling},
    PDF = {https://hal.inria.fr/hal-02275363/file/CCGRID_camera_ready.pdf},
    HAL_ID = {hal-02275363},
    HAL_VERSION = {v1},
    
    }
    
  4. Romain Lion
    Tolérance aux pannes dans l'exécution distribuée de graphes de tâches
    In Conférence d'informatique en Parallélisme, Architecture et Système, Anglet, France, June 2019
    [WWW] [PDF] Keyword(s): On MPI Support, Task-based, Starpu, HPC, Data locality
    [bibtex-key = lion:hal-02296118]

    @inproceedings{lion:hal-02296118,
    TITLE = {{Tol{\'e}rance aux pannes dans l'ex{\'e}cution distribu{\'e}e de graphes de t{\^a}ches}},
    AUTHOR = {Lion, Romain},
    URL = {https://hal.inria.fr/hal-02296118},
    BOOKTITLE = {{Conf{\'e}rence d'informatique en Parall{\'e}lisme, Architecture et Syst{\`e}me}},
    ADDRESS = {Anglet, France},
    YEAR = {2019},
    MONTH = Jun,
    KEYWORDS = {On MPI Support ; Task-based ; Starpu ; HPC ; Data locality},
    PDF = {https://hal.inria.fr/hal-02296118/file/Compas_Romain_LION_submitted_final.pdf},
    HAL_ID = {hal-02296118},
    HAL_VERSION = {v1},
    
    }
    
  5. Christophe Alias, Samuel Thibault, and Laure Gonnord
    A Compiler Algorithm to Guide Runtime Scheduling
    Research Report RR-9315, INRIA Grenoble ; INRIA Bordeaux, December 2019
    [WWW] [PDF] Keyword(s): On Scheduling, Compilation, automatic parallelization, polyhedral model, runtime scheduling
    [bibtex-key = alias:hal-02421327]

    @techreport{alias:hal-02421327,
    TITLE = {{A Compiler Algorithm to Guide Runtime Scheduling}},
    AUTHOR = {Alias, Christophe and Thibault, Samuel and Gonnord, Laure},
    URL = {https://hal.inria.fr/hal-02421327},
    TYPE = {Research Report},
    NUMBER = {RR-9315},
    INSTITUTION = {{INRIA Grenoble ; INRIA Bordeaux}},
    YEAR = {2019},
    MONTH = Dec,
    PDF = {https://hal.inria.fr/hal-02421327/file/RR-9315.pdf},
    HAL_ID = {hal-02421327},
    HAL_VERSION = {v1},
    KEYWORDS = { On Scheduling, Compilation, automatic parallelization, polyhedral model, runtime scheduling },
    
    }
    

2018

  1. Terry Cojean
    Programmation of heterogeneous architectures using moldable tasks
    Ph.D Thesis, Université de Bordeaux, March 2018
    [WWW] [PDF] Keyword(s): On Parallel Tasks, High Performance Computing, Runtime systems, Parallel tasks programming, Applied linear algebra, Calcul Haute Performance, Supports d'exécution, Programmation à l'aide de tâches parallèles, Algèbre linéaire appliquée
    [bibtex-key = cojean:tel-01816341]

    @phdthesis{cojean:tel-01816341,
    TITLE = {{Programmation of heterogeneous architectures using moldable tasks}},
    AUTHOR = {Cojean, Terry},
    URL = {https://tel.archives-ouvertes.fr/tel-01816341},
    NUMBER = {2018BORD0041},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2018},
    MONTH = Mar,
    KEYWORDS = {On Parallel Tasks; High Performance Computing ; Runtime systems ; Parallel tasks programming ; Applied linear algebra ; Calcul Haute Performance ; Supports d'ex{\'e}cution ; Programmation {\`a} l'aide de t{\^a}ches parall{\`e}les ; Alg{\`e}bre lin{\'e}aire appliqu{\'e}e},
    TYPE = {Ph.D Thesis},
    PDF = {https://tel.archives-ouvertes.fr/tel-01816341/file/COJEAN_TERRY_2018.pdf},
    HAL_ID = {tel-01816341},
    HAL_VERSION = {v1},
    
    }
    
  2. Samuel Thibault
    On Runtime Systems for Task-based Programming on Heterogeneous Platforms
    Habilitation à diriger des recherches, Université de Bordeaux, December 2018
    [WWW] [PDF] Keyword(s): Runtime Systems, Task graphs, Task graph scheduling, Distributed Computing, Support Exécutif, Graphe de tâches, Ordonnancement de graphe de tâches, Calcul Distribué, General Presentations, StarPU
    [bibtex-key = thibault:tel-01959127]

    @phdthesis{thibault:tel-01959127,
    TITLE = {{On Runtime Systems for Task-based Programming on Heterogeneous Platforms}},
    AUTHOR = {Thibault, Samuel},
    URL = {https://hal.inria.fr/tel-01959127},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2018},
    MONTH = Dec,
    KEYWORDS = {Runtime Systems ; Task graphs ; Task graph scheduling ; Distributed Computing ; Support Ex{\'e}cutif ; Graphe de t{\^a}ches ; Ordonnancement de graphe de t{\^a}ches ; Calcul Distribu{\'e}},
    TYPE = {Habilitation {\`a} diriger des recherches},
    PDF = {https://hal.inria.fr/tel-01959127/file/hdr.pdf},
    HAL_ID = {tel-01959127},
    HAL_VERSION = {v1},
    KEYWORDS = {General Presentations;StarPU} 
    }
    
  3. Essadki, Mohamed, Jung, Jonathan, Larat, Adam, Pelletier, Milan, and Perrier, Vincent
    A Task-Driven Implementation of a Simple Numerical Solver for Hyperbolic Conservation Laws
    ESAIM: ProcS, 63:228-247, 2018
    [WWW] [PDF] [doi:10.1051/proc/201863228] Keyword(s): On Applications
    [bibtex-key = refId0]

    @article{ refId0,
    author = {{Essadki, Mohamed} and {Jung, Jonathan} and {Larat, Adam} and {Pelletier, Milan} and {Perrier, Vincent}},
    title = {A Task-Driven Implementation of a Simple Numerical Solver for Hyperbolic Conservation Laws},
    DOI= "10.1051/proc/201863228",
    url= "https://doi.org/10.1051/proc/201863228",
    PDF={https://www.esaim-proc.org/articles/proc/pdf/2018/03/proc_esaim2018_228.pdf},
    journal = {ESAIM: ProcS},
    year = 2018,
    volume = 63,
    pages = "228-247",
    KEYWORDS = {On Applications},
    
    }
    
  4. Vinicius Garcia Pinto, Lucas Mello Schnorr, Luka Stanisic, Arnaud Legrand, Samuel Thibault, and Vincent Danjean
    A Visual Performance Analysis Framework for Task-based Parallel Applications running on Hybrid Clusters
    CCPE - Concurrency and Computation: Practice and Experience, 30, April 2018
    [WWW] [PDF] [doi:10.1002/cpe.4472] Keyword(s): On Scheduling, Heterogeneous platforms, Cholesky, High-Performance Computing, Trace Visualization, Task-based applications
    [bibtex-key = garciapinto:hal-01616632]

    @article{garciapinto:hal-01616632,
    TITLE = {{A Visual Performance Analysis Framework for Task-based Parallel Applications running on Hybrid Clusters}},
    AUTHOR = {Garcia Pinto, Vinicius and Schnorr, Lucas Mello and Stanisic, Luka and Legrand, Arnaud and Thibault, Samuel and Danjean, Vincent},
    URL = {https://hal.inria.fr/hal-01616632},
    JOURNAL = {{CCPE - Concurrency and Computation: Practice and Experience}},
    PUBLISHER = {{Wiley}},
    YEAR = {2018},
    MONTH = Apr,
    VOLUME = 30,
    ISSUE = 18,
    DOI = {10.1002/cpe.4472},
    KEYWORDS = {On Scheduling; Heterogeneous platforms ; Cholesky ; High-Performance Computing ; Trace Visualization ; Task-based applications},
    PDF = {https://hal.inria.fr/hal-01616632/file/CCPE_article_submitted_2018_02_06.pdf},
    HAL_ID = {hal-01616632},
    HAL_VERSION = {v2},
    
    }
    
  5. Peter Thoman, Kiril Dichev, Thomas Heller, Roman Iakymchuk, Xavier Aguilar, Khalid Hasanov, Philipp Gschwandtner, Pierre Lemarinier, Stefano Markidis, Herbert Jordan, and others
    A taxonomy of task-based parallel programming technologies for high-performance computing
    The Journal of Supercomputing, 74(4):1422-1434, 2018
    [WWW] [PDF] [doi:10.1007/s11227-018-2238-4] Keyword(s): Papers related to StarPU
    [bibtex-key = thoman2018taxonomy]

    @article{thoman2018taxonomy,
    title={A taxonomy of task-based parallel programming technologies for high-performance computing},
    author={Thoman, Peter and Dichev, Kiril and Heller, Thomas and Iakymchuk, Roman and Aguilar, Xavier and Hasanov, Khalid and Gschwandtner, Philipp and Lemarinier, Pierre and Markidis, Stefano and Jordan, Herbert and others},
    journal={The Journal of Supercomputing},
    volume={74},
    number={4},
    pages={1422--1434},
    year={2018},
    publisher={Springer} doi={10.1007/s11227-018-2238-4} url = {https://link.springer.com/article/10.1007%2Fs11227-018-2238-4},
    pdf = {https://link.springer.com/content/pdf/10.1007/s11227-018-2238-4.pdf},
    keywords = {Papers related to StarPU} 
    }
    
  6. Vinicius Garcia Pinto, Lucas Mello Schnorr, Arnaud Legrand, Samuel Thibault, Luka Stanisic, and Vincent Danjean
    Detecção de Anomalias de Desempenho em Aplicações de Alto Desempenho baseadas em Tarefas em Clusters Hìbridos
    In WPerformance - 17o Workshop em Desempenho de Sistemas Computacionais e de Comunicação, Natal, Brazil, July 2018
    [WWW] [PDF] Keyword(s): On Scheduling
    [bibtex-key = pinto:hal-01842038]

    @inproceedings{pinto:hal-01842038,
    TITLE = {{Detec{\c c}{\~a}o de Anomalias de Desempenho em Aplica{\c c}{\~o}es de Alto Desempenho baseadas em Tarefas em Clusters H{\'i}bridos}},
    AUTHOR = {Pinto, Vinicius Garcia and Mello Schnorr, Lucas and Legrand, Arnaud and Thibault, Samuel and Stanisic, Luka and Danjean, Vincent},
    URL = {https://hal.inria.fr/hal-01842038},
    BOOKTITLE = {{WPerformance - 17o Workshop em Desempenho de Sistemas Computacionais e de Comunica{\c c}{\~a}o}},
    ADDRESS = {Natal, Brazil},
    YEAR = {2018},
    MONTH = Jul,
    KEYWORDS = {On Scheduling},
    PDF = {https://hal.inria.fr/hal-01842038/file/181587_1.pdf},
    HAL_ID = {hal-01842038},
    HAL_VERSION = {v1},
    
    }
    
  7. Dimitrios Soudris, Lazaros Papadopoulos, Christoph W Kessler, Dionysios D Kehagias, Athanasios Papadopoulos, Panos Seferlis, Alexander Chatzigeorgiou, Apostolos Ampatzoglou, Samuel Thibault, Raymond Namyst, Dirk Pleiter, Georgi Gaydadjiev, Tobias Becker, and Matthieu Haefele
    EXA2PRO programming environment
    In SAMOS XVIII: Architectures, Modeling, and Simulation, Pythagorion, Greece, pages 202-209, July 2018
    ACM
    [WWW] [PDF] [doi:10.1145/3229631.3239369] Keyword(s): On Applications, StarPU
    [bibtex-key = soudris:hal-03273509]

    @inproceedings{soudris:hal-03273509,
    TITLE = {{EXA2PRO programming environment}},
    AUTHOR = {Soudris, Dimitrios and Papadopoulos, Lazaros and Kessler, Christoph W and Kehagias, Dionysios D and Papadopoulos, Athanasios and Seferlis, Panos and Chatzigeorgiou, Alexander and Ampatzoglou, Apostolos and Thibault, Samuel and Namyst, Raymond and Pleiter, Dirk and Gaydadjiev, Georgi and Becker, Tobias and Haefele, Matthieu},
    URL = {https://hal.inria.fr/hal-03273509},
    BOOKTITLE = {{SAMOS XVIII: Architectures, Modeling, and Simulation}},
    ADDRESS = {Pythagorion, Greece},
    PUBLISHER = {{ACM}},
    PAGES = {202-209},
    YEAR = {2018},
    MONTH = Jul,
    DOI = {10.1145/3229631.3239369},
    PDF = {https://hal.inria.fr/hal-03273509/file/3229631.3239369.pdf},
    HAL_ID = {hal-03273509},
    HAL_VERSION = {v1},
    KEYWORDS = {On Applications;StarPU} 
    }
    

2017

  1. Arthur Chevalier
    Critical resources management and scheduling under StarPU
    Master Thesis, Université de Bordeaux, September 2017
    [WWW] [PDF] Keyword(s): On Memory Control, On Hierarchical Tasks
    [bibtex-key = chevalier:hal-01718280]

    @phdthesis{chevalier:hal-01718280,
    TITLE = {{Critical resources management and scheduling under StarPU}},
    AUTHOR = {Chevalier, Arthur},
    URL = {https://hal.inria.fr/hal-01718280},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2017},
    MONTH = Sep,
    KEYWORDS = {On Memory Control; On Hierarchical Tasks},
    PDF = {https://hal.inria.fr/hal-01718280/file/Memoire.pdf},
    TYPE = {Master Thesis},
    HAL_ID = {hal-01718280},
    HAL_VERSION = {v1},
    
    }
    
  2. Suraj Kumar
    Scheduling of Dense Linear Algebra Kernels on Heterogeneous Resources
    PhD thesis, Université de Bordeaux, April 2017
    [WWW] [PDF] Keyword(s): On Scheduling, STARPU, Runtime Systems, Heterogeneous Platforms, Task-based Scheduling, Dynamic Schedulers, Dense Linear Algebra, Systèmes d'ordonnancement dynamiques, Plates-formes hétérogènes, Algèbre linéaire dense, Ordonnancement dynamique, Ordonnancement à base de graphe de tâches
    [bibtex-key = kumar:tel-01538516]

    @phdthesis{kumar:tel-01538516,
    TITLE = {{Scheduling of Dense Linear Algebra Kernels on Heterogeneous Resources}},
    AUTHOR = {Kumar, Suraj},
    URL = {https://tel.archives-ouvertes.fr/tel-01538516},
    NUMBER = {2017BORD0572},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2017},
    MONTH = Apr,
    KEYWORDS = {On Scheduling; STARPU ; Runtime Systems ; Heterogeneous Platforms ; Task-based Scheduling ; Dynamic Schedulers ; Dense Linear Algebra ; Syst{\`e}mes d'ordonnancement dynamiques ; Plates-formes h{\'e}t{\'e}rog{\`e}nes ; Alg{\`e}bre lin{\'e}aire dense ; Ordonnancement dynamique ; Ordonnancement {\`a} base de graphe de t{\^a}ches},
    PDF = {https://tel.archives-ouvertes.fr/tel-01538516/file/KUMAR_SURAL_2017.pdf},
    HAL_ID = {tel-01538516},
    HAL_VERSION = {v1},
    
    }
    
  3. Emmanuel Agullo, Olivier Aumage, Berenger Bramas, Olivier Coulaud, and Samuel Pitoiset
    Bridging the gap between OpenMP and task-based runtime systems for the fast multipole method
    IEEE Transactions on Parallel and Distributed Systems, April 2017
    [WWW] [PDF] [doi:10.1109/TPDS.2017.2697857] Keyword(s): On OpenMP Support on top of StarPU, STARPU, multicore architecture, commutativity, priority, high performance computing, fast multipole method, runtime system, OpenMP, compiler, parallel programming model, StarPU, KStar, ScalFMM
    [bibtex-key = agullo:hal-01517153]

    @article{agullo:hal-01517153,
    TITLE = {{Bridging the gap between OpenMP and task-based runtime systems for the fast multipole method}},
    AUTHOR = {Agullo, Emmanuel and Aumage, Olivier and Bramas, Berenger and Coulaud, Olivier and Pitoiset, Samuel},
    URL = {https://hal.inria.fr/hal-01517153},
    JOURNAL = {{IEEE Transactions on Parallel and Distributed Systems}},
    YEAR = {2017},
    MONTH = Apr,
    DOI = {10.1109/TPDS.2017.2697857},
    KEYWORDS = {On OpenMP Support on top of StarPU; STARPU ; multicore architecture ; commutativity ; priority ; high performance computing ; fast multipole method ; runtime system ; OpenMP ; compiler ; parallel programming model ; StarPU ; KStar ; ScalFMM},
    PDF = {https://hal.inria.fr/hal-01517153/file/tpds_kstar_scalfmm_print.pdf},
    HAL_ID = {hal-01517153},
    HAL_VERSION = {v1},
    
    }
    
  4. Emmanuel Agullo, Olivier Aumage, Mathieu Faverge, Nathalie Furmento, Florent Pruvost, Marc Sergent, and Samuel Thibault
    Achieving High Performance on Supercomputers with a Sequential Task-based Programming Model
    TPDS - IEEE Transactions on Parallel and Distributed Systems, December 2017
    [WWW] [PDF] [doi:10.1109/TPDS.2017.2766064] Keyword(s): On MPI Support, runtime system, sequential task flow, task-based programming, heterogeneous computing, distributed computing, multicore, GPU, Cholesky factorization
    [bibtex-key = agullo:hal-01618526]

    @article{agullo:hal-01618526,
    TITLE = {{Achieving High Performance on Supercomputers with a Sequential Task-based Programming Model}},
    AUTHOR = {Agullo, Emmanuel and Aumage, Olivier and Faverge, Mathieu and Furmento, Nathalie and Pruvost, Florent and Sergent, Marc and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-01618526},
    JOURNAL = {{TPDS - IEEE Transactions on Parallel and Distributed Systems}},
    PUBLISHER = {{Institute of Electrical and Electronics Engineers}},
    MONTH = DEC,
    YEAR = {2017},
    KEYWORDS = {On MPI Support ; runtime system ; sequential task flow ; task-based programming ; heterogeneous computing ; distributed computing ; multicore ; GPU ; Cholesky factorization},
    PDF = {https://hal.inria.fr/hal-01618526/file/tpds14.pdf},
    HAL_ID = {hal-01618526},
    HAL_VERSION = {v1},
    doi = {10.1109/TPDS.2017.2766064},
    
    }
    
  5. Jean Marie Couteyen Carpaye, Jean Roman, and Pierre Brenner
    Design and Analysis of a Task-based Parallelization over a Runtime System of an Explicit Finite-Volume CFD Code with Adaptive Time Stepping
    International Journal of Computational Science and Engineering, pp 1 - 22, 2017
    [WWW] [PDF] [doi:10.1016/j.jocs.2017.03.008] Keyword(s): On Applications, HPC, CFD, runtime, task-based
    [bibtex-key = couteyencarpaye:hal-01507613]

    @article{couteyencarpaye:hal-01507613,
    TITLE = {{Design and Analysis of a Task-based Parallelization over a Runtime System of an Explicit Finite-Volume CFD Code with Adaptive Time Stepping}},
    AUTHOR = {Couteyen Carpaye, Jean Marie and Roman, Jean and Brenner, Pierre},
    URL = {https://hal.inria.fr/hal-01507613},
    JOURNAL = {{International Journal of Computational Science and Engineering}},
    PUBLISHER = {{Inderscience}},
    PAGES = {1 - 22},
    YEAR = {2017},
    DOI = {10.1016/j.jocs.2017.03.008},
    KEYWORDS = {On Applications, HPC ; CFD ; runtime ; task-based},
    PDF = {https://hal.inria.fr/hal-01507613/file/flusepa-task-hal-inria-preprint.pdf},
    HAL_ID = {hal-01507613},
    HAL_VERSION = {v1},
    
    }
    
  6. O. Beaumont, L. Eyraud-Dubois, and S. Kumar
    Approximation Proofs of a Fast and Efficient List Scheduling Algorithm for Task-Based Runtime Systems on Multicores and GPUs
    In 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pages 768-777, May 2017
    [WWW] [PDF] [doi:10.1109/IPDPS.2017.71] Keyword(s): On Scheduling, STARPU, List scheduling, Approximation proofs, Runtime systems, Heterogeneous scheduling, Dense linear algebra
    [bibtex-key = beaumont:hal-01386174]

    @INPROCEEDINGS{beaumont:hal-01386174,
    author={O. Beaumont and L. Eyraud-Dubois and S. Kumar},
    booktitle={2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
    title={Approximation Proofs of a Fast and Efficient List Scheduling Algorithm for Task-Based Runtime Systems on Multicores and GPUs},
    year={2017},
    volume={},
    number={},
    pages={768-777},
    doi={10.1109/IPDPS.2017.71},
    URL = {https://hal.inria.fr/hal-01386174},
    PDF = {https://hal.inria.fr/hal-01386174/file/heteroPrioApproxProofsRR.pdf},
    ISSN={},
    month={May},
    KEYWORDS = {On Scheduling; STARPU ; List scheduling ; Approximation proofs ; Runtime systems ; Heterogeneous scheduling ; Dense linear algebra},
    HAL_ID = {hal-01386174},
    HAL_VERSION = {v1},
    
    }
    
  7. Emmanuel Agullo, Bérenger Bramas, Olivier Coulaud, Luka Stanisic, and Samuel Thibault
    Modeling Irregular Kernels of Task-based codes: Illustration with the Fast Multipole Method
    Research Report RR-9036, INRIA Bordeaux, February 2017
    [WWW] [PDF] Keyword(s): On Performance Model Tuning, Mathematical Software, Modeling and simulation, Parallel computing methodologies, fast multipole method, runtime system, task-based programming
    [bibtex-key = agullo:hal-01474556]

    @techreport{agullo:hal-01474556,
    TITLE = {{Modeling Irregular Kernels of Task-based codes: Illustration with the Fast Multipole Method}},
    AUTHOR = {Agullo, Emmanuel and Bramas, B{\'e}renger and Coulaud, Olivier and Stanisic, Luka and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-01474556},
    TYPE = {Research Report},
    NUMBER = {RR-9036},
    PAGES = {35},
    INSTITUTION = {{INRIA Bordeaux}},
    YEAR = {2017},
    MONTH = Feb,
    KEYWORDS = {On Performance Model Tuning; Mathematical Software ; Modeling and simulation ; Parallel computing methodologies ; fast multipole method ; runtime system ; task-based programming},
    PDF = {https://hal.inria.fr/hal-01474556/file/rapport.pdf},
    HAL_ID = {hal-01474556},
    HAL_VERSION = {v1},
    
    }
    
  8. Emmanuel Agullo, Alfredo Buttari, Mikko Byckling, Abdou Guermouche, and Ian Masliah
    Achieving high-performance with a sparse direct solver on Intel KNL
    Research Report RR-9035, Inria Bordeaux Sud-Ouest ; CNRS-IRIT ; Intel corporation ; Université Bordeaux, February 2017
    [WWW] [PDF] Keyword(s): On Applications, runtime system, sparse direct solver, energy efficiency, high-performance computing, portability, Intel KNL, manycore parallelism
    [bibtex-key = agullo:hal-01473475]

    @techreport{agullo:hal-01473475,
    TITLE = {{Achieving high-performance with a sparse direct solver on Intel KNL}},
    AUTHOR = {Agullo, Emmanuel and Buttari, Alfredo and Byckling, Mikko and Guermouche, Abdou and Masliah, Ian},
    URL = {https://hal.inria.fr/hal-01473475},
    TYPE = {Research Report},
    NUMBER = {RR-9035},
    PAGES = {15},
    INSTITUTION = {{Inria Bordeaux Sud-Ouest ; CNRS-IRIT ; Intel corporation ; Universit{\'e} Bordeaux}},
    YEAR = {2017},
    MONTH = Feb,
    KEYWORDS = {On Applications; runtime system ; sparse direct solver ; energy efficiency ; high-performance computing ; portability ; Intel KNL ; manycore parallelism},
    PDF = {https://hal.inria.fr/hal-01473475/file/RR-9035.pdf},
    HAL_ID = {hal-01473475},
    HAL_VERSION = {v1},
    
    }
    

2016

  1. Marc Sergent
    Scalability of a task-based runtime system for dense linear algebra applications
    PhD thesis, Université de Bordeaux, December 2016
    [WWW] [PDF] Keyword(s): On MPI Support, High performance computing, Run-time systems, Distributed computing, Task-based programming, Parallel programming models, Calcul haute performance, Supports d'exécution, Calcul distribué, Programmation par tâches, Modèles de programmation parallèle
    [bibtex-key = sergent:tel-01483666]

    @phdthesis{sergent:tel-01483666,
    TITLE = {{Scalability of a task-based runtime system for dense linear algebra applications}},
    AUTHOR = {Sergent, Marc},
    URL = {https://tel.archives-ouvertes.fr/tel-01483666},
    NUMBER = {2016BORD0372},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2016},
    MONTH = Dec,
    KEYWORDS = {On MPI Support ; High performance computing ; Run-time systems ; Distributed computing ; Task-based programming ; Parallel programming models ; Calcul haute performance ; Supports d'ex{\'e}cution ; Calcul distribu{\'e} ; Programmation par t{\^a}ches ; Mod{\`e}les de programmation parall{\`e}le},
    PDF = {https://tel.archives-ouvertes.fr/tel-01483666/file/SERGENT_MARC_2016.pdf},
    HAL_ID = {tel-01483666},
    HAL_VERSION = {v1},
    
    }
    
  2. Emmanuel Agullo, Olivier Beaumont, Lionel Eyraud-Dubois, and Suraj Kumar
    Are Static Schedules so Bad ? A Case Study on Cholesky Factorization
    In Proceedings of the 30th IEEE International Parallel & Distributed Processing Symposium, IPDPS'16, Chicago, IL, USA, May 2016
    IEEE
    [WWW] [PDF] Keyword(s): On Scheduling, Cholesky Factorization, Accelerators, Heterogeneous Systems, Runtime Systems, Scheduling, Unrelated Machines
    [bibtex-key = agullo:hal-01223573]

    @inproceedings{agullo:hal-01223573,
    TITLE = {{Are Static Schedules so Bad ? A Case Study on Cholesky Factorization}},
    AUTHOR = {Agullo, Emmanuel and Beaumont, Olivier and Eyraud-Dubois, Lionel and Kumar, Suraj},
    URL = {https://hal.inria.fr/hal-01223573},
    ADDRESS = {Chicago, IL, USA},
    PUBLISHER = {{IEEE}},
    BOOKTITLE = {Proceedings of the 30th IEEE International Parallel \& Distributed Processing Symposium, IPDPS'16},
    YEAR = {2016},
    MONTH = May,
    keywords = {On Scheduling; Cholesky Factorization ; Accelerators ; Heterogeneous Systems ; Runtime Systems; Scheduling ; Unrelated Machines},
    PDF = {https://hal.inria.fr/hal-01223573/file/heteroprioCameraReady-ieeeCompatiable.pdf},
    HAL_ID = {hal-01223573},
    HAL_VERSION = {v2},
    
    }
    
  3. Olivier Beaumont, Terry Cojean, Lionel Eyraud-Dubois, Abdou Guermouche, and Suraj Kumar
    Scheduling of Linear Algebra Kernels on Multiple Heterogeneous Resources
    In International Conference on High Performance Computing, Data, and Analytics (HiPC), Hyderabad, India, December 2016
    [WWW] [PDF] Keyword(s): On Parallel Tasks, STARPU, Scheduling, Linear Algebra, Heterogeneous Platforms, Task-based Scheduling, Cholesky Factorization, Simulation, Resource Aggregation
    [bibtex-key = beaumont:hal-01361992]

    @inproceedings{beaumont:hal-01361992,
    TITLE = {{Scheduling of Linear Algebra Kernels on Multiple Heterogeneous Resources}},
    AUTHOR = {Beaumont, Olivier and Cojean, Terry and Eyraud-Dubois, Lionel and Guermouche, Abdou and Kumar, Suraj},
    URL = {https://hal.inria.fr/hal-01361992},
    BOOKTITLE = {{International Conference on High Performance Computing, Data, and Analytics (HiPC)}},
    ADDRESS = {Hyderabad, India},
    YEAR = {2016},
    MONTH = Dec,
    KEYWORDS = {On Parallel Tasks; STARPU ; Scheduling ; Linear Algebra ; Heterogeneous Platforms ; Task-based Scheduling ; Cholesky Factorization ; Simulation ; Resource Aggregation},
    PDF = {https://hal.inria.fr/hal-01361992v2/document},
    HAL_ID = {hal-01361992},
    HAL_VERSION = {v1},
    
    }
    
  4. Terry Cojean, Abdou Guermouche, Andra Hugo, Raymond Namyst, and Pierre-André Wacrenier
    Resource aggregation for task-based Cholesky Factorization on top of heterogeneous machines
    In HeteroPar'2016 workshop of Euro-Par, Grenoble, France, August 2016
    [WWW] [PDF] Keyword(s): On Parallel Tasks, dense linear algebra, Cholesky, Multicore, accelerator, GPU, heterogeneous computing, task DAG, runtime system
    [bibtex-key = cojean:hal-01181135]

    @inproceedings{cojean:hal-01181135,
    TITLE = {{Resource aggregation for task-based Cholesky Factorization on top of heterogeneous machines}},
    AUTHOR = {Cojean, Terry and Guermouche, Abdou and Hugo, Andra and Namyst, Raymond and Wacrenier, Pierre-Andr{\'e}},
    URL = {https://hal.inria.fr/hal-01181135},
    BOOKTITLE = {{HeteroPar'2016 workshop of Euro-Par}},
    ADDRESS = {Grenoble, France},
    YEAR = {2016},
    MONTH = Aug,
    KEYWORDS = {On Parallel Tasks; dense linear algebra ; Cholesky ; Multicore ; accelerator ; GPU ; heterogeneous computing ; task DAG ; runtime system},
    PDF = {https://hal.inria.fr/hal-01181135/file/papier%20%281%29.pdf},
    HAL_ID = {hal-01181135},
    HAL_VERSION = {v3},
    
    }
    
  5. Vinicius Garcia Pinto, Luka Stanisic, Arnaud Legrand, Lucas Mello Schnorr, Samuel Thibault, and Vincent Danjean
    Analyzing Dynamic Task-Based Applications on Hybrid Platforms: An Agile Scripting Approach
    In VPA - 3rd Workshop on Visual Performance Analysis, Salt Lake City, USA, November 2016
    Note: Held in conjunction with SC16
    [WWW] [PDF] [doi:10.1109/VPA.2016.008] Keyword(s): On Scheduling, STARPU
    [bibtex-key = garciapinto:hal-01353962]

    @inproceedings{garciapinto:hal-01353962,
    TITLE = {{Analyzing Dynamic Task-Based Applications on Hybrid Platforms: An Agile Scripting Approach}},
    AUTHOR = {Garcia Pinto, Vinicius and Stanisic, Luka and Legrand, Arnaud and Mello Schnorr, Lucas and Thibault, Samuel and Danjean, Vincent},
    URL = {https://hal.inria.fr/hal-01353962},
    NOTE = {Held in conjunction with SC16},
    BOOKTITLE = {{VPA - 3rd Workshop on Visual Performance Analysis}},
    ADDRESS = {Salt Lake City, USA},
    YEAR = {2016},
    MONTH = Nov,
    KEYWORDS = {On Scheduling; STARPU},
    PDF = {https://hal.inria.fr/hal-01353962v2/document},
    HAL_ID = {hal-01353962},
    HAL_VERSION = {v1},
    doi = {10.1109/VPA.2016.008},
    
    }
    
  6. Johan Janzén, David Black-Schaffer, and Andra Hugo
    Partitioning GPUs for Improved Scalability
    In IEEE 28th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), October 2016
    [WWW] [doi:10.1109/SBAC-PAD.2016.14] Keyword(s): On Scheduling
    [bibtex-key = JaBlHU2016a]

    @InProceedings{JaBlHU2016a,
    author = {Johan Janz{\'e}n and David Black-Schaffer and Andra Hugo},
    title = {{Partitioning GPUs for Improved Scalability}},
    booktitle = {IEEE 28th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)},
    year = 2016,
    KEYWORDS = {On Scheduling},
    DOI = {10.1109/SBAC-PAD.2016.14},
    URL = {http://ieeexplore.ieee.org/abstract/document/7789322/},
    month = Oct
    }
    
  7. Marc Sergent, David Goudin, Samuel Thibault, and Olivier Aumage
    Controlling the Memory Subscription of Distributed Applications with a Task-Based Runtime System
    In HIPS - 21st International Workshop on High-Level Parallel Programming Models and Supportive Environments, Chicago, USA, May 2016
    [WWW] [PDF] [doi:10.1109/IPDPSW.2016.105] Keyword(s): On Memory Control, memory control, task-based run-time systems, compressed linear algebra, distributed computing
    [bibtex-key = sergent:hal-01284004]

    @inproceedings{sergent:hal-01284004,
    TITLE = {{Controlling the Memory Subscription of Distributed Applications with a Task-Based Runtime System}},
    AUTHOR = {Sergent, Marc and Goudin, David and Thibault, Samuel and Aumage, Olivier},
    URL = {https://hal.inria.fr/hal-01284004},
    BOOKTITLE = {{HIPS - 21st International Workshop on High-Level Parallel Programming Models and Supportive Environments}},
    ADDRESS = {Chicago, USA},
    YEAR = {2016},
    MONTH = May,
    keywords = {On Memory Control; memory control ; task-based run-time systems ; compressed linear algebra ; distributed computing},
    PDF = {https://hal.inria.fr/hal-01284004/file/PID4127657.pdf},
    HAL_ID = {hal-01284004},
    HAL_VERSION = {v1},
    doi = {10.1109/IPDPSW.2016.105},
    
    }
    
  8. Emmanuel Agullo, Olivier Aumage, Berenger Bramas, Olivier Coulaud, and Samuel Pitoiset
    Bridging the gap between OpenMP 4.0 and native runtime systems for the fast multipole method
    Research Report RR-8953, Inria, March 2016
    [WWW] [PDF] Keyword(s): On OpenMP Support on top of StarPU, STARPU, runtime system, parallel programming model, compiler, priority, commutativity, multicore architecture, moteur d'exécution, modèle de programmation parallèle, compilateur, OpenMP 4.0, OpenMP 4.X, priorité, commutativité, architecture multicore
    [bibtex-key = agullo:hal-01372022]

    @techreport{agullo:hal-01372022,
    TITLE = {{Bridging the gap between OpenMP 4.0 and native runtime systems for the fast multipole method}},
    AUTHOR = {Agullo, Emmanuel and Aumage, Olivier and Bramas, Berenger and Coulaud, Olivier and Pitoiset, Samuel},
    URL = {https://hal.inria.fr/hal-01372022},
    TYPE = {Research Report},
    NUMBER = {RR-8953},
    PAGES = {49},
    INSTITUTION = {{Inria}},
    YEAR = {2016},
    MONTH = Mar,
    KEYWORDS = {On OpenMP Support on top of StarPU; STARPU ; runtime system ; parallel programming model ; compiler ; priority ; commutativity ; multicore architecture ; moteur d'ex{\'e}cution ; mod{\`e}le de programmation parall{\`e}le ; compilateur ; OpenMP 4.0 ; OpenMP 4.X ; priorit{\'e} ; commutativit{\'e} ; architecture multicore},
    PDF = {https://hal.inria.fr/hal-01372022/file/RR-8953.pdf},
    HAL_ID = {hal-01372022},
    HAL_VERSION = {v1},
    
    }
    
  9. Emmanuel Agullo, Bérenger Bramas, Olivier Coulaud, Martin Khannouz, and Luka Stanisic
    Task-based fast multipole method for clusters of multicore processors
    Research Report RR-8970, Inria Bordeaux Sud-Ouest, October 2016
    [WWW] [PDF] Keyword(s): On Applications, STARPU, multicore processor, runtime system, FMM, cluster, high performance computing (HPC), fast multipole method, hybrid parallelization, task-based programming, MPI, OpenMP
    [bibtex-key = agullo:hal-01387482]

    @techreport{agullo:hal-01387482,
    TITLE = {{Task-based fast multipole method for clusters of multicore processors}},
    AUTHOR = {Agullo, Emmanuel and Bramas, B{\'e}renger and Coulaud, Olivier and Khannouz, Martin and Stanisic, Luka},
    URL = {https://hal.inria.fr/hal-01387482},
    TYPE = {Research Report},
    NUMBER = {RR-8970},
    PAGES = {15 },
    INSTITUTION = {{Inria Bordeaux Sud-Ouest}},
    YEAR = {2016},
    MONTH = Oct,
    KEYWORDS = {On Applications; STARPU ; multicore processor ; runtime system ; FMM ; cluster ; high performance computing (HPC) ; fast multipole method ; hybrid parallelization ; task-based programming ; MPI ; OpenMP},
    PDF = {https://hal.inria.fr/hal-01387482/file/report-8970.pdf},
    HAL_ID = {hal-01387482},
    HAL_VERSION = {v1},
    
    }
    
  10. E Agullo, L Giraud, A Guermouche, S Nakov, and Jean Roman
    Task-based Conjugate Gradient: from multi-GPU towards heterogeneous architectures
    Research Report 8912, Inria Bordeaux Sud-Ouest, May 2016
    [WWW] [PDF] Keyword(s): High Performance Computing (HPC), multi-GPUs, heterogeneous architectures, task-based model, runtime system, sparse linear systems, Conjugate Gradient., On Applications, StarPU, scheduling
    [bibtex-key = agullo:hal-01316982]

    @techreport{agullo:hal-01316982,
    TITLE = {{Task-based Conjugate Gradient: from multi-GPU towards heterogeneous architectures}},
    AUTHOR = {Agullo, E and Giraud, L and Guermouche, A and Nakov, S and Roman, Jean},
    URL = {https://hal.inria.fr/hal-01316982},
    TYPE = {Research Report},
    NUMBER = {8912},
    INSTITUTION = {{Inria Bordeaux Sud-Ouest}},
    YEAR = {2016},
    MONTH = May,
    KEYWORDS = {High Performance Computing (HPC) ; multi-GPUs ; heterogeneous architectures ; task-based model ; runtime system ; sparse linear systems ; Conjugate Gradient.},
    PDF = {https://hal.inria.fr/hal-01316982/file/RR-8912.pdf},
    HAL_ID = {hal-01316982},
    HAL_VERSION = {v1},
    KEYWORDS = {On Applications; StarPU, scheduling} 
    }
    
  11. Terry Cojean, Abdou Guermouche, Andra Hugo, Raymond Namyst, and Pierre-André Wacrenier
    Resource aggregation for task-based Cholesky Factorization on top of modern architectures
    Note: This paper is submitted for review to the Parallel Computing special issue for HCW and HeteroPar 16 workshops, November 2016
    [WWW] [PDF] Keyword(s): On Parallel Tasks, Intel Xeon-Phi KNL, heterogeneous computing, GPU, accelerator, Multicore, dense linear algebra, task DAG, Cholesky factorization, runtime system
    [bibtex-key = cojean:hal-01409965]

    @unpublished{cojean:hal-01409965,
    TITLE = {{Resource aggregation for task-based Cholesky Factorization on top of modern architectures}},
    AUTHOR = {Cojean, Terry and Guermouche, Abdou and Hugo, Andra and Namyst, Raymond and Wacrenier, Pierre-Andr{\'e}},
    URL = {https://hal.inria.fr/hal-01409965},
    NOTE = {This paper is submitted for review to the Parallel Computing special issue for HCW and HeteroPar 16 workshops},
    YEAR = {2016},
    MONTH = Nov,
    KEYWORDS = {On Parallel Tasks; Intel Xeon-Phi KNL ; heterogeneous computing ; GPU ; accelerator ; Multicore ; dense linear algebra ; task DAG ; Cholesky factorization ; runtime system},
    PDF = {https://hal.inria.fr/hal-01409965/file/submission.pdf},
    HAL_ID = {hal-01409965},
    HAL_VERSION = {v1},
    
    }
    

2015

  1. Corentin Rossignon
    A fine grain model programming for parallelization of sparse linear solver
    PhD thesis, Université de Bordeaux, July 2015
    [WWW] [PDF] Keyword(s): On Applications, Sparse linear algebra, Multicore, Runtime Systems, Task-based programming, Parallelism, Algèbre linéaire creuse, Multi-coeurs, NUMA, Parallélisme, Graphe de tâches, Supports d’exécution
    [bibtex-key = rossignon:tel-01230876]

    @phdthesis{rossignon:tel-01230876,
    TITLE = {{A fine grain model programming for parallelization of sparse linear solver}},
    AUTHOR = {Rossignon, Corentin},
    URL = {https://tel.archives-ouvertes.fr/tel-01230876},
    NUMBER = {2015BORD0094},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2015},
    MONTH = Jul,
    keywords = {On Applications; Sparse linear algebra ; Multicore ; Runtime Systems ; Task-based programming ; Parallelism ; Alg{\`e}bre lin{\'e}aire creuse ; Multi-coeurs ; NUMA ; Parall{\'e}lisme ; Graphe de t{\^a}ches ; Supports d’ex{\'e}cution},
    PDF = {https://tel.archives-ouvertes.fr/tel-01230876/file/ROSSIGNON_CORENTIN_2015.pdf},
    HAL_ID = {tel-01230876},
    HAL_VERSION = {v1},
    
    }
    
  2. Luka Stanisic, Samuel Thibault, Arnaud Legrand, Brice Videau, and Jean-François Méhaut
    Faithful Performance Prediction of a Dynamic Task-Based Runtime System for Heterogeneous Multi-Core Architectures
    CCPE - Concurrency and Computation: Practice and Experience, pp 16, May 2015
    [WWW] [PDF] [doi:10.1002/cpe.3555] Keyword(s): On The Simulation Support through SimGrid, runtime systems, simulation, simgrid, HPC, Starpu-simgrid
    [bibtex-key = stanisic:hal-01147997]

    @article{stanisic:hal-01147997,
    TITLE = {{Faithful Performance Prediction of a Dynamic Task-Based Runtime System for Heterogeneous Multi-Core Architectures}},
    AUTHOR = {Stanisic, Luka and Thibault, Samuel and Legrand, Arnaud and Videau, Brice and M{\'e}haut, Jean-Fran{\c c}ois},
    URL = {https://hal.inria.fr/hal-01147997},
    JOURNAL = {{CCPE - Concurrency and Computation: Practice and Experience}},
    PUBLISHER = {{John Wiley and Sons}},
    PAGES = {16},
    YEAR = {2015},
    MONTH = May,
    DOI = {10.1002/cpe.3555},
    PDF = {https://hal.inria.fr/hal-01147997/file/CCPE14_article.pdf},
    HAL_ID = {hal-01147997},
    HAL_VERSION = {v1},
    KEYWORDS = {On The Simulation Support through SimGrid; runtime systems ; simulation ; simgrid ; HPC ; Starpu-simgrid} 
    }
    
  3. Emmanuel Agullo, Olivier Beaumont, Lionel Eyraud-Dubois, Julien Herrmann, Suraj Kumar, Loris Marchal, and Samuel Thibault
    Bridging the Gap between Performance and Bounds of Cholesky Factorization on Heterogeneous Platforms
    In HCW'2015 - Heterogeneity in Computing Workshop of IPDPS, Hyderabad, India, May 2015
    [WWW] [PDF] [doi:10.1109/IPDPSW.2015.35] Keyword(s): On Scheduling, StarPU, Simgrid, Dynamic Schedulers, Resource Allocation, Scheduling, Heterogeneous Resources, Dense Linear Algebra, Simulation, Cholesky Factorization
    [bibtex-key = agullo:hal-01120507]

    @inproceedings{agullo:hal-01120507,
    TITLE = {{Bridging the Gap between Performance and Bounds of Cholesky Factorization on Heterogeneous Platforms}},
    AUTHOR = {Agullo, Emmanuel and Beaumont, Olivier and Eyraud-Dubois, Lionel and Herrmann, Julien and Kumar, Suraj and Marchal, Loris and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-01120507},
    PDF = {https://hal.inria.fr/hal-01120507/document},
    BOOKTITLE = {{HCW'2015 - Heterogeneity in Computing Workshop of IPDPS}},
    ADDRESS = {Hyderabad, India},
    YEAR = {2015},
    MONTH = May,
    HAL_ID = {hal-01120507},
    HAL_VERSION = {v1},
    KEYWORDS = {On Scheduling;StarPU; Simgrid; Dynamic Schedulers; Resource Allocation; Scheduling; Heterogeneous Resources; Dense Linear Algebra; Simulation; Cholesky Factorization},
    doi = {10.1109/IPDPSW.2015.35},
    
    }
    
  4. Vìctor Martìnez, David Michéa, Fabrice Dupros, Olivier Aumage, Samuel Thibault, Hideo Aochi, and Philippe Olivier Alexandre Navaux
    Towards seismic wave modeling on heterogeneous many-core architectures using task-based runtime system
    In SBAC-PAD - 27th International Symposium on Computer Architecture and High Performance Computing, Florianopolis, Brazil, October 2015
    [WWW] [PDF] [doi:10.1109/SBAC-PAD.2015.33] Keyword(s): On Applications, StarPU, scheduling
    [bibtex-key = MaMiDuAuThiAoNa15]

    @inproceedings{MaMiDuAuThiAoNa15,
    TITLE = {{Towards seismic wave modeling on heterogeneous many-core architectures using task-based runtime system}},
    AUTHOR = {Mart{\'i}nez, V{\'i}ctor and Mich{\'e}a, David and Dupros, Fabrice and Aumage, Olivier and Thibault, Samuel and Aochi, Hideo and Navaux, Philippe Olivier Alexandre},
    URL = {https://hal.inria.fr/hal-01182746},
    PDF = {https://hal.inria.fr/hal-01182746/file/sbac2015_soumission.pdf},
    BOOKTITLE = {{SBAC-PAD - 27th International Symposium on Computer Architecture and High Performance Computing}},
    ADDRESS = {Florianopolis, Brazil},
    YEAR = {2015},
    MONTH = Oct,
    HAL_ID = {hal-01182746},
    HAL_VERSION = {v1},
    KEYWORDS = {On Applications; StarPU; scheduling},
    doi = {10.1109/SBAC-PAD.2015.33},
    
    }
    
  5. Luka Stanisic, Emmanuel Agullo, Alfredo Buttari, Abdou Guermouche, Arnaud Legrand, Florent Lopez, and Brice Videau
    Fast and Accurate Simulation of Multithreaded Sparse Linear Algebra Solvers
    In The 21st IEEE International Conference on Parallel and Distributed Systems, Melbourne, Australia, December 2015
    [WWW] [PDF] [doi:10.1109/ICPADS.2015.67] Keyword(s): On The Simulation Support through SimGrid, Sparse Linear Algebra, Mumps, Starpu-simgrid, HPC, Simgrid, Runtime
    [bibtex-key = stanisic:hal-01180272]

    @inproceedings{stanisic:hal-01180272,
    TITLE = {{Fast and Accurate Simulation of Multithreaded Sparse Linear Algebra Solvers}},
    AUTHOR = {Stanisic, Luka and Agullo, Emmanuel and Buttari, Alfredo and Guermouche, Abdou and Legrand, Arnaud and Lopez, Florent and Videau, Brice},
    URL = {https://hal.inria.fr/hal-01180272},
    BOOKTITLE = {{The 21st IEEE International Conference on Parallel and Distributed Systems}},
    ADDRESS = {Melbourne, Australia},
    YEAR = {2015},
    MONTH = Dec,
    KEYWORDS = {On The Simulation Support through SimGrid; Sparse Linear Algebra ; Mumps ; Starpu-simgrid ; HPC ; Simgrid ; Runtime},
    PDF = {https://hal.inria.fr/hal-01180272/file/QRMSTARSG_article.pdf},
    HAL_ID = {hal-01180272},
    HAL_VERSION = {v2},
    DOI = {10.1109/ICPADS.2015.67},
    
    }
    

2014

  1. Andra-Ecaterina Hugo
    Composability of parallel codes on heterogeneous architectures
    Ph.D Thesis, Université de Bordeaux, December 2014
    [WWW] [PDF] Keyword(s): Runtime, Composability, Hypervisor, Support d'exécution, Composition, On Composability
    [bibtex-key = hugo:tel-01162975]

    @phdthesis{hugo:tel-01162975,
    TITLE = {{Composability of parallel codes on heterogeneous architectures}},
    AUTHOR = {Hugo, Andra-Ecaterina},
    URL = {https://tel.archives-ouvertes.fr/tel-01162975},
    NUMBER = {2014BORD0373},
    SCHOOL = {{Universit{\'e} de Bordeaux}},
    YEAR = {2014},
    MONTH = Dec,
    KEYWORDS = {Runtime ; Composability ; Hypervisor ; Support d'ex{\'e}cution ; Composition},
    TYPE = {Ph.D Thesis},
    PDF = {https://tel.archives-ouvertes.fr/tel-01162975/file/HUGO_ANDRA_2014.pdf},
    HAL_ID = {tel-01162975},
    HAL_VERSION = {v1},
    KEYWORDS = {On Composability},
    
    }
    
  2. Emmanuel Agullo, Bérenger Bramas, Olivier Coulaud, Eric Darve, Matthias Messner, and Toru Takahashi
    Task-Based FMM for Multicore Architectures
    SIAM Journal on Scientific Computing, 36(1):66-93, 2014
    [WWW] [PDF] [doi:10.1137/130915662] Keyword(s): On Applications, fast multipole method, multicore architectures, shared memory paradigm, runtime system, pipeline
    [bibtex-key = agullo:hal-00911856]

    @article{agullo:hal-00911856,
    TITLE = {{Task-Based FMM for Multicore Architectures}},
    AUTHOR = {Agullo, Emmanuel and Bramas, B{\'e}renger and Coulaud, Olivier and Darve, Eric and Messner, Matthias and Takahashi, Toru},
    URL = {https://hal.inria.fr/hal-00911856},
    JOURNAL = {{SIAM Journal on Scientific Computing}},
    PUBLISHER = {{Society for Industrial and Applied Mathematics}},
    VOLUME = {36},
    NUMBER = {1},
    PAGES = {66-93},
    YEAR = {2014},
    DOI = {10.1137/130915662},
    KEYWORDS = {On Applications; fast multipole method ; multicore architectures ; shared memory paradigm ; runtime system ; pipeline},
    PDF = {https://hal.inria.fr/hal-00911856/file/sisc-cpu.pdf},
    HAL_ID = {hal-00911856},
    HAL_VERSION = {v1},
    
    }
    
  3. Emmanuel Agullo, Olivier Aumage, Mathieu Faverge, Nathalie Furmento, Florent Pruvost, Marc Sergent, and Samuel Thibault
    Harnessing clusters of hybrid nodes with a sequential task-based programming model
    In 8th International Workshop on Parallel Matrix Algorithms and Applications, July 2014
    [WWW] [PDF] Keyword(s): On MPI Support
    [bibtex-key = agullo:hal-01283949]

    @inproceedings{agullo:hal-01283949,
    TITLE = {{Harnessing clusters of hybrid nodes with a sequential task-based programming model}},
    AUTHOR = {Agullo, Emmanuel and Aumage, Olivier and Faverge, Mathieu and Furmento, Nathalie and Pruvost, Florent and Sergent, Marc and Thibault, Samuel},
    URL = {https://hal.inria.fr/hal-01283949},
    BOOKTITLE = {{8th International Workshop on Parallel Matrix Algorithms and Applications}},
    YEAR = {2014},
    MONTH = Jul,
    PDF = {https://hal.inria.fr/hal-01283949/file/pmaa14.pdf},
    HAL_ID = {hal-01283949},
    HAL_VERSION = {v1},
    keywords = {On MPI Support} 
    }
    
  4. Sylvain Henry, Alexandre Denis, Denis Barthou, Marie-Christine Counilh, and Raymond Namyst
    Toward OpenCL Automatic Multi-Device Support
    In Fernando Silva, Ines Dutra, and Vitor Santos Costa, editors, Euro-Par 2014, Porto, Portugal, August 2014
    Springer
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = sylvain:hal-01005765]

    @inproceedings{sylvain:hal-01005765,
    hal_id = {hal-01005765},
    url = {http://hal.inria.fr/hal-01005765},
    title = {{Toward OpenCL Automatic Multi-Device Support}},
    author = {Henry, Sylvain and Denis, Alexandre and Barthou, Denis and Counilh, Marie-Christine and Namyst, Raymond},
    language = {Anglais},
    affiliation = {Exascale Computing Research Laboratory , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{Euro-Par 2014}},
    publisher = {Springer},
    address = {Porto, Portugal},
    editor = {Fernando Silva and Ines Dutra and Vitor Santos Costa },
    audience = {internationale },
    year = {2014},
    month = Aug,
    pdf = {http://hal.inria.fr/hal-01005765/PDF/final.pdf},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  5. Xavier Lacoste, Mathieu Faverge, Pierre Ramet, Samuel Thibault, and George Bosilca
    Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes
    In HCW'2014 - Heterogeneity in Computing Workshop of IPDPS, Phoenix, USA, May 2014
    IEEE
    Note: RR-8446
    [WWW] [PDF] [doi:10.1109/IPDPSW.2014.9] Keyword(s): On Applications, StarPU
    [bibtex-key = lacoste:hal-00987094]

    @inproceedings{lacoste:hal-00987094,
    hal_id = {hal-00987094},
    url = {http://hal.inria.fr/hal-00987094},
    title = {{Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes}},
    author = {Lacoste, Xavier and Faverge, Mathieu and Ramet, Pierre and Thibault, Samuel and Bosilca, George},
    language = {Anglais},
    affiliation = {HiePACS - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest , Innovative Computing Laboratory - ICL},
    booktitle = {{HCW'2014 - Heterogeneity in Computing Workshop of IPDPS}},
    publisher = {IEEE},
    address = {Phoenix, USA},
    note = {RR-8446},
    audience = {internationale },
    year = {2014},
    month = May,
    pdf = {http://hal.inria.fr/hal-00987094/PDF/sparsegpus.pdf},
    KEYWORDS = {On Applications;StarPU},
    doi = {10.1109/IPDPSW.2014.9},
    
    }
    
  6. I. D. Mironescu and L. Vintan
    Coloured Petri Net modelling of task scheduling on a heterogeneous computational node
    In 2014 IEEE 10th International Conference on Intelligent Computer Communication and Processing (ICCP), pages 323-330, 2014
    [WWW] [PDF] [doi:10.1109/ICCP.2014.6937016] Keyword(s): Papers related to StarPU
    [bibtex-key = 6937016]

    @INPROCEEDINGS{6937016,
    author={I. D. {Mironescu} and L. {Vin{\c t}an}},
    booktitle={2014 IEEE 10th International Conference on Intelligent Computer Communication and Processing (ICCP)},
    title={Coloured Petri Net modelling of task scheduling on a heterogeneous computational node},
    year={2014},
    volume={},
    number={},
    pages={323-330},
    doi={10.1109/ICCP.2014.6937016},
    url = {https://ieeexplore.ieee.org/document/6937016},
    pdf = {https://www.researchgate.net/profile/Lucian_Vintan/publication/264744234_Coloured_Petri_Net_Modelling_of_Task_Scheduling_on_a_Heterogeneous_Computational_Node/links/53edbae80cf26b9b7dc5f79e/Coloured-Petri-Net-Modelling-of-Task-Scheduling-on-a-Heterogeneous-Computational-Node.pdf},
    keywords = {Papers related to StarPU} 
    }
    
  7. Marc Sergent and Simon Archipoff
    Modulariser les ordonnanceurs de tâches : une approche structurelle
    In Compas'2014, Neuchâtel, Suisse, April 2014
    [WWW] [PDF] Keyword(s): On Scheduling, StarPU
    [bibtex-key = sergent:hal-00978364]

    @inproceedings{sergent:hal-00978364,
    hal_id = {hal-00978364},
    url = {http://hal.inria.fr/hal-00978364},
    title = {{Modulariser les ordonnanceurs de t{\^a}ches : une approche structurelle}},
    author = {Sergent, Marc and Archipoff, Simon},
    language = {Fran{\c c}ais},
    affiliation = {RUNTIME - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{Compas'2014}},
    address = {Neuch{\^a}tel, Suisse},
    audience = {nationale },
    year = {2014},
    month = Apr,
    pdf = {http://hal.inria.fr/hal-00978364/PDF/ordonnanceurs\_modulaires.pdf},
    KEYWORDS = {On Scheduling;StarPU} 
    }
    
  8. Luka Stanisic, Samuel Thibault, Arnaud Legrand, Brice Videau, and Jean-François Méhaut
    Modeling and Simulation of a Dynamic Task-Based Runtime System for Heterogeneous Multi-Core Architectures
    In Euro-Par - 20th International Conference on Parallel Processing, Porto, Portugal, August 2014
    Springer-Verlag
    [WWW] [PDF] [doi:10.1007/978-3-319-09873-9_5] Keyword(s): On The Simulation Support through SimGrid, StarPU
    [bibtex-key = stanisic:hal-01011633]

    @inproceedings{stanisic:hal-01011633,
    hal_id = {hal-01011633},
    url = {http://hal.inria.fr/hal-01011633},
    title = {{Modeling and Simulation of a Dynamic Task-Based Runtime System for Heterogeneous Multi-Core Architectures}},
    author = {Stanisic, Luka and Thibault, Samuel and Legrand, Arnaud and Videau, Brice and M{\'e}haut, Jean-Fran{\c c}ois},
    language = {Anglais},
    affiliation = {MESCAL - INRIA Grenoble Rh{\^o}ne-Alpes / LIG laboratoire d'Informatique de Grenoble , Laboratoire d'Informatique de Grenoble - LIG , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{Euro-Par - 20th International Conference on Parallel Processing}},
    publisher = {Springer-Verlag},
    address = {Porto, Portugal},
    audience = {internationale },
    year = {2014},
    month = Aug,
    pdf = {http://hal.inria.fr/hal-01011633/PDF/StarPUSG\_article.pdf},
    KEYWORDS = {On The Simulation Support through SimGrid;StarPU},
    doi = {10.1007/978-3-319-09873-9_5} 
    }
    
  9. Philippe Virouleau, Pierrick Brunet, François Broquedis, Nathalie Furmento, Samuel Thibault, Olivier Aumage, and Thierry Gautier
    Evaluation of OpenMP Dependent Tasks with the KASTORS Benchmark Suite
    In IWOMP2014 - 10th International Workshop on OpenMP, Salvador, Brazil, pages 16 - 29, September 2014
    Springer
    [WWW] [PDF] [doi:10.1007/978-3-319-11454-5_2] Keyword(s): On OpenMP Support on top of StarPU, OpenMP, task dependencies, benchmarks, runtime systems, KASTORS, StarPU
    [bibtex-key = virouleau:hal-01081974]

    @inproceedings{virouleau:hal-01081974,
    TITLE = {{Evaluation of OpenMP Dependent Tasks with the KASTORS Benchmark Suite}},
    AUTHOR = {Virouleau, Philippe and Brunet, Pierrick and Broquedis, Fran{\c c}ois and Furmento, Nathalie and Thibault, Samuel and Aumage, Olivier and Gautier, Thierry},
    URL = {https://hal.inria.fr/hal-01081974},
    PDF = {https://hal.inria.fr/hal-01081974/document},
    BOOKTITLE = {{IWOMP2014 - 10th International Workshop on OpenMP}},
    ADDRESS = {Salvador, Brazil},
    PUBLISHER = {{Springer}},
    PAGES = {16 - 29},
    YEAR = {2014},
    MONTH = Sep,
    DOI = {10.1007/978-3-319-11454-5\_2},
    HAL_ID = {hal-01081974},
    HAL_VERSION = {v1},
    KEYWORDS = {On OpenMP Support on top of StarPU;OpenMP; task dependencies; benchmarks; runtime systems; KASTORS; StarPU} 
    }
    
  10. Emmanuel Agullo, Berenger Bramas, Olivier Coulaud, Eric Darve, Matthias Messner, and Toru Takahashi
    Task-based FMM for heterogeneous architectures
    Research Report RR-8513, Inria Bordeaux - Sud-Ouest, April 2014
    [WWW] [PDF] Keyword(s): On Applications, pipeline., heterogeneous architectures, graphics processing unit, Fast multipole methods, pipeline, scheduling, runtime system
    [bibtex-key = agullo:hal-00974674]

    @techreport{agullo:hal-00974674,
    TITLE = {{Task-based FMM for heterogeneous architectures}},
    AUTHOR = {Agullo, Emmanuel and Bramas, Berenger and Coulaud, Olivier and Darve, Eric and Messner, Matthias and Takahashi, Toru},
    URL = {https://hal.inria.fr/hal-00974674},
    TYPE = {Research Report},
    NUMBER = {RR-8513},
    PAGES = {29},
    INSTITUTION = {{Inria Bordeaux - Sud-Ouest}},
    YEAR = {2014},
    MONTH = Apr,
    KEYWORDS = {On Applications; pipeline. ; heterogeneous architectures ; graphics processing unit ; Fast multipole methods ; pipeline ; scheduling ; runtime system},
    PDF = {https://hal.inria.fr/hal-00974674/file/RR-8513.pdf},
    HAL_ID = {hal-00974674},
    HAL_VERSION = {v1},
    
    }
    
  11. Cédric Augonnet, Olivier Aumage, Nathalie Furmento, Samuel Thibault, and Raymond Namyst
    StarPU-MPI: Task Programming over Clusters of Machines Enhanced with Accelerators
    Research Report RR-8538, INRIA, May 2014
    [WWW] [PDF] Keyword(s): On MPI Support, StarPU
    [bibtex-key = augonnet:hal-00992208]

    @techreport{augonnet:hal-00992208,
    hal_id = {hal-00992208},
    url = {http://hal.inria.fr/hal-00992208},
    title = {{StarPU-MPI: Task Programming over Clusters of Machines Enhanced with Accelerators}},
    author = {Augonnet, C{\'e}dric and Aumage, Olivier and Furmento, Nathalie and Thibault, Samuel and Namyst, Raymond},
    language = {Anglais},
    affiliation = {RUNTIME - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI},
    type = {Research Report},
    institution = {INRIA},
    number = {RR-8538},
    year = {2014},
    month = May,
    pdf = {http://hal.inria.fr/hal-00992208/PDF/RR-8538.pdf},
    KEYWORDS = {On MPI Support;StarPU} 
    }
    
  12. Xavier Lacoste, Mathieu Faverge, Pierre Ramet, Samuel Thibault, and George Bosilca
    Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes
    Research Report RR-8446, INRIA, January 2014
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = lacoste:hal-00925017]

    @techreport{lacoste:hal-00925017,
    hal_id = {hal-00925017},
    url = {http://hal.inria.fr/hal-00925017},
    title = {{Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes}},
    author = {Xavier Lacoste and Mathieu Faverge and Pierre Ramet and Samuel Thibault and George Bosilca},
    keywords = {On Applications; StarPU},
    language = {Anglais},
    affiliation = {HiePACS - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest , Innovative Computing Laboratory - ICL},
    pages = {25},
    type = {Research Report},
    institution = {INRIA},
    number = {RR-8446},
    year = {2014},
    month = Jan,
    pdf = {http://hal.inria.fr/hal-00925017/PDF/RR-8446.pdf} 
    }
    
  13. Emmanuel Agullo, Olivier Aumage, Mathieu Faverge, Nathalie Furmento, Florent Pruvost, Marc Sergent, and Samuel Thibault
    Overview of Distributed Linear Algebra on Hybrid Nodes over the StarPU Runtime
    SIAM Conference on Parallel Processing for Scientific Computing, February 2014
    [WWW] [PDF] Keyword(s): On Applications
    [bibtex-key = sergent:hal-00978602]

    @misc{sergent:hal-00978602,
    hal_id = {hal-00978602},
    url = {http://hal.inria.fr/hal-00978602},
    title = {{Overview of Distributed Linear Algebra on Hybrid Nodes over the StarPU Runtime}},
    author = {Agullo, Emmanuel and Aumage, Olivier and Faverge, Mathieu and Furmento, Nathalie and Pruvost, Florent and Sergent, Marc and Thibault, Samuel},
    language = {Anglais},
    affiliation = {RUNTIME - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI , HiePACS - INRIA Bordeaux - Sud-Ouest},
    howpublished = {{SIAM Conference on Parallel Processing for Scientific Computing}},
    address = {Portland, Oregon, USA},
    audience = {internationale },
    year = {2014},
    month = Feb,
    pdf = {http://hal.inria.fr/hal-00978602/PDF/siampp14.pdf},
    keywords = {On Applications} 
    }
    

2013

  1. Cyril Bordage
    Ordonnancement dynamique, adapté aux architectures hétérogènes, de la méthode multipôle pour les équations de Maxwell, en électromagnétisme
    PhD thesis, Université de Bordeaux, December 2013
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = Bor13Thesis]

    @PhDThesis{ Bor13Thesis,
    author = {Cyril Bordage},
    title = {{Ordonnancement dynamique, adapt{\'e} aux architectures h{\'e}t{\'e}rog{\`e}nes, de la m{\'e}thode multip{\^o}le pour les {\'e}quations de Maxwell, en {\'e}lectromagn{\'e}tisme}},
    school = {{Universit{\'e} de Bordeaux}},
    URL = {https://tel.archives-ouvertes.fr/tel-00958494},
    PDF = {https://tel.archives-ouvertes.fr/tel-00958494/document},
    year = 2013,
    month = DEC,
    KEYWORDS = {On Applications;StarPU} 
    }
    
  2. Sylvain Henry
    Modèles de programmation et supports exécutifs pour architectures hétérogènes
    PhD thesis, Université de Bordeaux, November 2013
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = Hen13Thesis]

    @PhDThesis{Hen13Thesis,
    author = {Sylvain Henry},
    title = {Mod{\`e}les de programmation et supports ex{\'e}cutifs pour architectures h{\'e}t{\'e}rog{\`e}nes},
    school = {{Universit{\'e} de Bordeaux}},
    year = 2013,
    month = NOV,
    URL = {http://tel.archives-ouvertes.fr/tel-00948309},
    PDF = {http://tel.archives-ouvertes.fr/tel-00948309/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  3. Sylvain Henry
    ViperVM: a Runtime System for Parallel Functional High-Performance Computing on Heterogeneous Architectures
    In 2nd Workshop on Functional High-Performance Computing (FHPC'13), Boston, USA, September 2013
    [WWW] [PDF] Keyword(s): On Applications, Parallel Functional Programming, High-Performance Computing, Heterogeneous Architectures
    [bibtex-key = hen13fhpc]

    @inproceedings{hen13fhpc,
    hal_id = {hal-00851122},
    url = {http://hal.inria.fr/hal-00851122},
    title = {{ViperVM: a Runtime System for Parallel Functional High-Performance Computing on Heterogeneous Architectures}},
    author = {Henry, Sylvain},
    keywords = {On Applications; Parallel Functional Programming; High-Performance Computing; Heterogeneous Architectures},
    language = {Anglais},
    affiliation = {Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{2nd Workshop on Functional High-Performance Computing (FHPC'13)}},
    address = {Boston, USA},
    audience = {internationale },
    year = {2013},
    month = Sep,
    pdf = {http://hal.inria.fr/hal-00851122/PDF/fhpc13.pdf},
    
    }
    
  4. Andra Hugo
    Le problème de la composition parallèle : une approche supervisée
    In 21èmes Rencontres Francophones du Parallélisme (RenPar'21), Grenoble, France, January 2013
    [WWW] [PDF] Keyword(s): On Composability, Composition, Hypervisor, StarPU
    [bibtex-key = AH13Renpar]

    @InProceedings{AH13Renpar,
    author = {Andra Hugo},
    title = {{Le probl{\`e}me de la composition parall{\`e}le : une approche supervis{\'e}e}},
    booktitle = {21{\`e}mes Rencontres Francophones du Parall{\'e}lisme (RenPar'21)},
    year = 2013,
    address = {Grenoble, France},
    month = JAN,
    url = {http://hal.inria.fr/hal-00773610},
    pdf = {http://hal.inria.fr/hal-00773610/document},
    KEYWORDS = {On Composability;Composition; Hypervisor; StarPU} 
    }
    
  5. Andra Hugo, Abdou Guermouche, Raymond Namyst, and Pierre-André Wacrenier
    Composing multiple StarPU applications over heterogeneous machines: a supervised approach
    In Third International Workshop on Accelerators and Hybrid Exascale Systems, Boston, USA, May 2013
    [WWW] [PDF] Keyword(s): On Composability
    [bibtex-key = hugo:hal-00824514]

    @inproceedings{hugo:hal-00824514,
    title = {{Composing multiple StarPU applications over heterogeneous machines: a supervised approach}},
    author = {Andra Hugo and Abdou Guermouche and Raymond Namyst and Pierre-Andr{\'e} Wacrenier},
    affiliation = {RUNTIME - INRIA Bordeaux - Sud-Ouest , Laboratoire Bordelais de Recherche en Informatique - LaBRI , HiePACS - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{Third International Workshop on Accelerators and Hybrid Exascale Systems}},
    address = {Boston, USA},
    year = {2013},
    month = May,
    url = {http://hal.inria.fr/hal-00824514},
    pdf = {http://hal.inria.fr/hal-00824514/document},
    KEYWORDS = {On Composability} 
    }
    
  6. Tetsuya Odajima, Taisuke Boku, Mitsuhisa Sato, Toshihiro Hanawa, Yuetsu Kodama, Raymond Namyst, Samuel Thibault, and Olivier Aumage
    Adaptive Task Size Control on High Level Programming for GPU/CPU Work Sharing
    In ICA3PP-2013 - The 13th International Conference on Algorithms and Architectures for Parallel Processing, Vietri sul Mare, Italy, December 2013
    [WWW] [PDF] [doi:10.1007/978-3-319-03889-6_7] Keyword(s): On Applications, StarPU
    [bibtex-key = odajima:hal-00920915]

    @inproceedings{odajima:hal-00920915,
    hal_id = {hal-00920915},
    url = {http://hal.inria.fr/hal-00920915},
    title = {{Adaptive Task Size Control on High Level Programming for GPU/CPU Work Sharing}},
    author = {Tetsuya Odajima and Taisuke Boku and Mitsuhisa Sato and Toshihiro Hanawa and Yuetsu Kodama and Raymond Namyst and Samuel Thibault and Olivier Aumage},
    language = {Anglais},
    affiliation = {Graduate School of Systems and Information Engineering [Tsukuba] , Center for Computational Sciences [Tsukuba] - CCS , Graduate School for Systems and Information Engineering [Tsukuba] , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{ICA3PP-2013 - The 13th International Conference on Algorithms and Architectures for Parallel Processing}},
    address = {Vietri sul Mare, Italy},
    audience = {internationale },
    year = {2013},
    month = Dec,
    pdf = {http://hal.inria.fr/hal-00920915/PDF/ADPC2013-117.pdf},
    KEYWORDS = {On Applications;StarPU},
    doi = {10.1007/978-3-319-03889-6_7},
    
    }
    
  7. Satoshi Ohshima, Satoshi Katagiri, Kengo Nakajima, Samuel Thibault, and Raymond Namyst
    Implementation of FEM Application on GPU with StarPU
    In SIAM CSE13 - SIAM Conference on Computational Science and Engineering 2013, Boston, USA, February 2013
    SIAM
    [WWW] Keyword(s): On Applications, StarPU
    [bibtex-key = ohshima:hal-00926144]

    @inproceedings{ohshima:hal-00926144,
    hal_id = {hal-00926144},
    url = {http://hal.inria.fr/hal-00926144},
    title = {{Implementation of FEM Application on GPU with StarPU}},
    author = {Satoshi Ohshima and Satoshi Katagiri and Kengo Nakajima and Samuel Thibault and Raymond Namyst},
    language = {Anglais},
    affiliation = {Computer Science Department - CST , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest},
    booktitle = {{SIAM CSE13 - SIAM Conference on Computational Science and Engineering 2013}},
    address = {Boston, USA},
    organization = {SIAM},
    audience = {internationale },
    year = {2013},
    month = Feb,
    KEYWORDS = {On Applications;StarPU} 
    }
    
  8. Corentin Rossignon
    Optimisation du produit matrice-vecteur creux sur architecture GPU pour un simulateur de reservoir
    In 21èmes Rencontres Francophones du Parallélisme (RenPar'21), Grenoble, France, January 2013
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = Ros13Renpar]

    @InProceedings{Ros13Renpar,
    author = {Corentin Rossignon},
    title = {{O}ptimisation du produit matrice-vecteur creux sur architecture GPU pour un simulateur de r{\'}eservoir},
    booktitle = {21{\`e}mes Rencontres Francophones du Parall{\'e}lisme (RenPar'21)},
    year = 2013,
    address = {Grenoble, France},
    month = JAN,
    url = {http://hal.inria.fr/hal-00773571},
    pdf = {http://hal.inria.fr/hal-00773571/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  9. Corentin Rossignon, Pascal Hénon, Olivier Aumage, and Samuel Thibault
    A NUMA-aware fine grain parallelization framework for multi-core architecture
    In PDSEC - 14th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing - 2013, Boston, USA, May 2013
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    <center> <table border=1 align=center width=80%> In this paper, we present some solutions to handle to problems commonly encountered when dealing with fine grain parallelization on multi-core architecture: expressing algorithm using a task grain size suitable for the hardware and minimizing the time penalty due to Non Uniform Memory Accesses. To evaluate the benefit of our work we present some experiments on the fine grain parallelization of an iterative solver for spare linear system with some comparisons with the Intel TBB approach.</td>

Abstract: || [bibtex-key = rossignon:hal-00858350]

@inproceedings{rossignon:hal-00858350,
hal_id = {hal-00858350},
url = {http://hal.inria.fr/hal-00858350},
title = {{A NUMA-aware fine grain parallelization framework for multi-core architecture}},
author = {Corentin Rossignon and Pascal H{\'e}non and Olivier Aumage and Samuel Thibault},
abstract = {{In this paper, we present some solutions to handle to problems commonly encountered when dealing with fine grain parallelization on multi-core architecture: expressing algorithm using a task grain size suitable for the hardware and minimizing the time penalty due to Non Uniform Memory Accesses. To evaluate the benefit of our work we present some experiments on the fine grain parallelization of an iterative solver for spare linear system with some comparisons with the Intel TBB approach.}},
language = {Anglais},
affiliation = {TOTAL-Scientific and Technical Center Jean F{\'e}ger - CSTJF , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest},
booktitle = {{PDSEC - 14th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing - 2013}},
address = {Boston, USA},
audience = {internationale },
year = {2013},
month = May,
pdf = {http://hal.inria.fr/hal-00858350/PDF/taggre\_pdsec\_2013.pdf},
KEYWORDS = {On Applications;StarPU} 
}
  1. Ludovic Courtès
    C Language Extensions for Hybrid CPU/GPU Programming with StarPU
    Research Report RR-8278, INRIA, April 2013
    [WWW] [PDF] Keyword(s): On The C Extensions, parallel programming, GPU, scheduling, programming language support, StarPU
    [bibtex-key = LC13Report]

    @techreport{LC13Report,
    hal_id = {hal-00807033},
    url = {http://hal.inria.fr/hal-00807033},
    title = {{C Language Extensions for Hybrid CPU/GPU Programming with StarPU}},
    author = {Court{\`e}s, Ludovic},
    pages = {25},
    type = {Research Report},
    institution = {INRIA},
    number = {RR-8278},
    year = {2013},
    month = Apr,
    pdf = {http://hal.inria.fr/hal-00807033/PDF/RR-8278.pdf},
    KEYWORDS = {On The C Extensions;parallel programming; GPU; scheduling; programming language support; StarPU} 
    }
    

2012

  1. Sylvain Henry, Alexandre Denis, and Denis Barthou
    Programmation unifiée multi-accélérateur OpenCL
    Techniques et Sciences Informatiques, (8-9-10):1233-1249, 2012
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = HenDenBar2012TSI]

    @article{HenDenBar2012TSI,
    title = {{Programmation unifi{\'e}e multi-acc{\'e}l{\'e}rateur OpenCL}},
    author = {Sylvain Henry and Alexandre Denis and Denis Barthou},
    publisher = {Lavoisier},
    pages = {1233-1249},
    journal = {Techniques et Sciences Informatiques},
    number = {8-9-10 },
    year = {2012},
    url = {http://hal.inria.fr/hal-00772742},
    pdf = {http://hal.inria.fr/hal-00772742/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  2. Sidi Ahmed Mahmoudi, Pierre Manneback, Cédric Augonnet, and Samuel Thibault
    Traitements d'Images sur Architectures Parallèles et Hétérogènes
    Technique et Science Informatiques, 31(8-10):1183-1203, 2012
    [WWW] [PDF] [doi:10.3166/tsi.31.1183-1203] Keyword(s): On Applications, StarPU
    [bibtex-key = MahManAugThi12TSI]

    @Article{MahManAugThi12TSI,
    author = {Sidi Ahmed Mahmoudi and Pierre Manneback and C\'edric Augonnet and Samuel Thibault},
    title = {Traitements d'Images sur Architectures Parall\`eles et H\'et\'erog\`enes },
    journal = {{Technique et Science Informatiques}},
    editor = {Lavoisier},
    year = 2012,
    volume = 31,
    number = {8-10},
    pages = {1183-1203},
    doi = {10.3166/tsi.31.1183-1203},
    url = {http://hal.inria.fr/hal-00714858/},
    pdf = {https://hal.inria.fr/hal-00714858/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  3. Cédric Augonnet, Olivier Aumage, Nathalie Furmento, Raymond Namyst, and Samuel Thibault
    StarPU-MPI: Task Programming over Clusters of Machines Enhanced with Accelerators
    In Siegfried Benkner Jesper Larsson Träff and Jack Dongarra, editors, EuroMPI 2012, volume 7490 of LNCS, September 2012
    Springer
    Note: Poster Session
    [WWW] [PDF] Keyword(s): On MPI Support, StarPU
    [bibtex-key = AugAumFurNamThi2012EuroMPI]

    @InProceedings{AugAumFurNamThi2012EuroMPI,
    author = {C\'edric Augonnet and Olivier Aumage and Nathalie Furmento and Raymond Namyst and Samuel Thibault},
    title = {{StarPU-MPI: Task Programming over Clusters of Machines Enhanced with Accelerators}},
    booktitle = {EuroMPI 2012},
    year = 2012,
    editor = {Jesper Larsson Tr{\"a}ff, Siegfried Benkner and Jack Dongarra},
    volume = {7490},
    series = {LNCS},
    month = SEP,
    note = {Poster Session},
    publisher = {Springer},
    url = {http://hal.inria.fr/hal-00725477},
    pdf = {http://hal.inria.fr/hal-00725477/document},
    KEYWORDS = {On MPI Support;StarPU} 
    }
    
  4. Siegfried Benkner, Enes Bajrovic, Erich Marth, Martin Sandrieser, Raymond Namyst, and Samuel Thibault
    High-Level Support for Pipeline Parallelism on Many-Core Architectures
    In Euro-Par - 18th International Conference on Parallel Processing, Rhodes Island, Greece, August 2012
    [WWW] [PDF] [doi:10.1007/978-3-642-32820-6_61] Keyword(s): On Applications, StarPU
    [bibtex-key = BenkBajMarSanNamThiEuroPar2012]

    @inproceedings{ BenkBajMarSanNamThiEuroPar2012,
    hal_id = {hal-00697020},
    url = {http://hal.inria.fr/hal-00697020},
    title = {{High-Level Support for Pipeline Parallelism on Many-Core Architectures}},
    author = {Benkner, Siegfried and Bajrovic, Enes and Marth, Erich and Sandrieser, Martin and Namyst, Raymond and Thibault, Samuel},
    booktitle = {{Euro-Par - 18th International Conference on Parallel Processing}},
    address = {Rhodes Island, Greece},
    audience = {internationale },
    year = {2012},
    month = AUG,
    pdf = {http://hal.inria.fr/hal-00697020/PDF/europar2012-submitted.pdf},
    keywords = {On Applications; StarPU},
    doi = {10.1007/978-3-642-32820-6_61},
    
    }
    
  5. Christoph Kessler, Usman Dastgeer, Samuel Thibault, Raymond Namyst, Andrew Richards, Uwe Dolinsky, Siegfried Benkner, Jesper Larsson Träff, and Sabri Pllana
    Programmability and Performance Portability Aspects of Heterogeneous Multi-/Manycore Systems
    In DATE - Design, Automation and Test in Europe, Dresden, Deutschland, March 2012
    ISBN: 978-3-9810801-8-6
    [WWW] [PDF] [doi:10.1109/DATE.2012.6176582] Keyword(s): On Applications, StarPU
    [bibtex-key = kessler:hal-00776610]

    @inproceedings{kessler:hal-00776610,
    hal_id = {hal-00776610},
    url = {http://hal.inria.fr/hal-00776610},
    title = {{Programmability and Performance Portability Aspects of Heterogeneous Multi-/Manycore Systems}},
    author = {Kessler, Christoph and Dastgeer, Usman and Thibault, Samuel and Namyst, Raymond and Richards, Andrew and Dolinsky, Uwe and Benkner, Siegfried and Larsson Tr{\"a}ff, Jesper and Pllana, Sabri},
    language = {Anglais},
    affiliation = {PELAB - PELAB , Laboratoire Bordelais de Recherche en Informatique - LaBRI , RUNTIME - INRIA Bordeaux - Sud-Ouest , Codeplay Software , University of Vienna , Technical University of Vienna - TU WIEN},
    booktitle = {{DATE - Design, Automation and Test in Europe}},
    address = {Dresden, Deutschland},
    audience = {internationale },
    year = {2012},
    month = Mar,
    doi = {10.1109/DATE.2012.6176582},
    pdf = {http://hal.inria.fr/hal-00776610/PDF/date12-paper.pdf},
    keywords = {On Applications; StarPU},
    isbn = {978-3-9810801-8-6},
    
    }
    

2011

  1. Cédric Augonnet
    Scheduling Tasks over Multicore machines enhanced with Accelerators: a Runtime System's Perspective
    PhD thesis, Université de Bordeaux, December 2011
    [WWW] [PDF] Keyword(s): General Presentations, StarPU
    [bibtex-key = Aug11Thesis]

    @PhDThesis{ Aug11Thesis,
    author = {C\'edric Augonnet},
    title = {{Scheduling Tasks over Multicore machines enhanced with Accelerators: a Runtime System's Perspective}},
    school = {{Universit{\'e} de Bordeaux}},
    year = 2011,
    month = DEC,
    url = {http://tel.archives-ouvertes.fr/tel-00777154},
    pdf = {http://tel.archives-ouvertes.fr/tel-00777154/document},
    KEYWORDS = {General Presentations;StarPU} 
    }
    
  2. Andra Hugo
    Composabilité de codes parallèles sur architectures hétérogènes
    Master Thesis, Université de Bordeaux, June 2011
    [WWW] [PDF] Keyword(s): On Composability, StarPU
    [bibtex-key = AH11Master]

    @PhDThesis{AH11Master,
    author = {Andra Hugo},
    title = {{Composabilit{\'e} de codes parall{\`e}les sur architectures h{\'e}t{\'e}rog{\`e}nes}},
    school = {Universit{\'e} de Bordeaux},
    year = {2011},
    type = {Master Thesis},
    month = JUN,
    url = {http://hal.inria.fr/inria-00619654/en/},
    pdf = {http://hal.inria.fr/inria-00619654/document},
    KEYWORDS = {On Composability;StarPU} 
    }
    
  3. Cédric Augonnet, Samuel Thibault, Raymond Namyst, and Pierre-André Wacrenier
    StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures
    CCPE - Concurrency and Computation: Practice and Experience, Special Issue: Euro-Par 2009, 23:187-198, February 2011
    [WWW] [PDF] [doi:10.1002/cpe.1631] Keyword(s): General Presentations, StarPU
    [bibtex-key = AugThiNamWac11CCPE]

    @Article{ AugThiNamWac11CCPE,
    author = {C{\'e}dric Augonnet and Samuel Thibault and Raymond Namyst and Pierre-Andr{\'e} Wacrenier},
    title = {{StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures}},
    journal = {CCPE - Concurrency and Computation: Practice and Experience, Special Issue: Euro-Par 2009},
    volume = 23,
    issue = 2,
    pages = {187--198},
    year = 2011,
    month = FEB,
    publisher = {John Wiley & Sons, Ltd.},
    doi = {10.1002/cpe.1631},
    url = {http://hal.inria.fr/inria-00550877},
    pdf = {http://hal.inria.fr/inria-00550877/document},
    KEYWORDS = {General Presentations;StarPU} 
    }
    
  4. Siegfried Benkner, Sabri Pllana, Jesper Larsson Träff, Philippas Tsigas, Uwe Dolinsky, Cédric Augonnet, Beverly Bachmayer, Christoph Kessler, David Moloney, and Vitaly Osipov
    PEPPHER: Efficient and Productive Usage of Hybrid Computing Systems
    IEEE Micro, 31(5):28-41, September 2011
    ISSN: 0272-1732
    [WWW] [PDF] [doi:10.1109/MM.2011.67] Keyword(s): On Applications, StarPU
    [bibtex-key = BenPllTraTsiDolAugBacKesMolOsi11IEEEMicro]

    @article{ BenPllTraTsiDolAugBacKesMolOsi11IEEEMicro,
    author = {Siegfried Benkner and Sabri Pllana and Jesper Larsson Tr{\"a}ff and Philippas Tsigas and Uwe Dolinsky and C\'edric Augonnet and Beverly Bachmayer and Christoph Kessler and David Moloney and Vitaly Osipov},
    title = {{PEPPHER: Efficient and Productive Usage of Hybrid Computing Systems}},
    journal ={IEEE Micro},
    volume = {31},
    number = {5},
    issn = {0272-1732},
    year = {2011},
    pages = {28-41},
    doi = {10.1109/MM.2011.67},
    publisher = {IEEE Computer Society},
    address = {Los Alamitos, CA, USA},
    month = SEP,
    url = {http://hal.inria.fr/hal-00648480},
    pdf = {http://hal.inria.fr/hal-00648480/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  5. Emmanuel Agullo, Cédric Augonnet, Jack Dongarra, Mathieu Faverge, Julien Langou, Hatem Ltaief, and Stanimire Tomov
    LU factorization for accelerator-based systems
    In 9th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 11), Sharm El-Sheikh, Egypt, June 2011
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = AguAugDonFavLanLtaTomAICCSA11]

    @InProceedings{AguAugDonFavLanLtaTomAICCSA11,
    author = {Emmanuel Agullo and C{\'e}dric Augonnet and Jack Dongarra and Mathieu Faverge and Julien Langou and Hatem Ltaief and Stanimire Tomov},
    title = {{LU} factorization for accelerator-based systems},
    booktitle = {9th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 11)},
    year = 2011,
    month = JUN,
    address = {Sharm El-Sheikh, Egypt},
    url = {http://hal.inria.fr/hal-00654193},
    pdf = {http://hal.inria.fr/hal-00654193/document},
    keywords = {On Applications; StarPU} 
    }
    
  6. Emmanuel Agullo, Cédric Augonnet, Jack Dongarra, Mathieu Faverge, Hatem Ltaief, Samuel Thibault, and Stanimire Tomov
    QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators
    In 25th IEEE International Parallel & Distributed Processing Symposium (IEEE IPDPS 2011), Anchorage, Alaska, USA, May 2011
    [WWW] [PDF] [doi:10.1109/IPDPS.2011.90] Keyword(s): On Applications, StarPU
    [bibtex-key = AguAugDonFavLtaThiTom11IPDPS]

    @InProceedings{AguAugDonFavLtaThiTom11IPDPS,
    HAL_ID = {inria-00547614},
    author={Emmanuel Agullo and C{\'{e}}dric Augonnet and Jack Dongarra and Mathieu Faverge and Hatem Ltaief and Samuel Thibault and Stanimire Tomov},
    title = {{QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators}},
    booktitle = {{25th IEEE International Parallel \& Distributed Processing Symposium (IEEE IPDPS 2011)}},
    ADDRESS={Anchorage, Alaska, USA},
    language = {{A}nglais},
    audience = {internationale },
    DAY=16,
    MONTH=MAY,
    YEAR=2011,
    doi = {10.1109/IPDPS.2011.90},
    URL = {http://hal.inria.fr/inria-00547614},
    pdf = {http://hal.inria.fr/inria-00547614/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  7. Usman Dastgeer, Christoph Kessler, and Samuel Thibault
    Flexible runtime support for efficient skeleton programming on hybrid systems
    In ParCo - Proceedings of the International Conference on Parallel Computing, volume 22 of Advances of Parallel Computing, Gent, Belgium, pages 159-166, August 2011
    [WWW] [PDF] [doi:10.3233/978-1-61499-041-3-159] Keyword(s): On Applications, StarPU
    [bibtex-key = DasKesThi11ParCo]

    @InProceedings{ DasKesThi11ParCo,
    author = { Usman Dastgeer and Christoph Kessler and Samuel Thibault },
    title = { Flexible runtime support for efficient skeleton programming on hybrid systems },
    booktitle = {ParCo - Proceedings of the International Conference on Parallel Computing},
    year = 2011,
    month = AUG,
    address = {Gent, Belgium},
    series = {Advances of Parallel Computing},
    pages = {159--166},
    volume = {22},
    url = {http://hal.inria.fr/inria-00606200/},
    pdf = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.699.6216&rep=rep1&type=pdf},
    doi = {10.3233/978-1-61499-041-3-159},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  8. Sylvain Henry
    Programmation multi-accélérateurs unifiée en OpenCL
    In 20èmes Rencontres Francophones du Parallélisme (RenPar'20), Saint Malo, France, May 2011
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = Hen11Renpar]

    @InProceedings{Hen11Renpar,
    author = {Sylvain Henry},
    title = {Programmation multi-acc{\'e}l{\'e}rateurs unifi{\'e}e en {OpenCL}},
    booktitle = {20{\`e}mes Rencontres Francophones du Parall{\'e}lisme (RenPar'20)},
    year = 2011,
    address = {Saint Malo, France},
    month = MAY,
    url = {http://hal.archives-ouvertes.fr/hal-00643257},
    pdf = {http://hal.archives-ouvertes.fr/hal-00643257/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    
  9. Sidi Ahmed Mahmoudi, Pierre Manneback, Cédric Augonnet, and Samuel Thibault
    Détection optimale des coins et contours dans des bases d'images volumineuses sur architectures multicoeurs hétérogènes
    In RenPar'20 - 20èmes Rencontres Francophones du Parallélisme, Saint-Malo, France, May 2011
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = MahManAugThi11Renpar20]

    @InProceedings{MahManAugThi11Renpar20,
    author = {Sidi Ahmed Mahmoudi and Pierre Manneback and C{\'e}dric Augonnet and Samuel Thibault},
    title = {D{\'e}tection optimale des coins et contours dans des bases d'images volumineuses sur architectures multicoeurs h{\'e}t{\'e}rog{\`e}nes},
    booktitle = {RenPar'20 - 20{\`e}mes Rencontres Francophones du Parall{\'e}lisme},
    year = 2011,
    month = MAY,
    address = {Saint-Malo, France},
    url = {http://hal.inria.fr/inria-00606195},
    pdf = {https://hal.inria.fr/inria-00606195/document},
    KEYWORDS = {On Applications;StarPU} 
    }
    

2010

  1. Emmanuel Agullo, Cédric Augonnet, Jack Dongarra, Hatem Ltaief, Raymond Namyst, Samuel Thibault, and Stanimire Tomov
    A Hybridization Methodology for High-Performance Linear Algebra Software for GPUs
    In Wen-mei W. Hwu, editor, GPU Computing Gems, volume 2
    Morgan Kaufmann, September 2010
    [WWW] [PDF] [doi:10.1016/B978-0-12-385963-1.00034-4] Keyword(s): On Applications, StarPU
    [bibtex-key = AguAugDonLtaNamThiTomGPUgems]

    @incollection{AguAugDonLtaNamThiTomGPUgems,
    HAL_ID = {inria-00547847},
    URL = {http://hal.inria.fr/inria-00547847/en/},
    title = { A {H}ybridization {M}ethodology for {H}igh-{P}erformance {L}inear {A}lgebra {S}oftware for {GPU}s},
    author = {{A}gullo, {E}mmanuel and {A}ugonnet, {C}{\'e}dric and {D}ongarra, {J}ack and {L}taief, {H}atem and {N}amyst, {R}aymond and {T}hibault, {S}amuel and {T}omov, {S}tanimire},
    language = {{A}nglais},
    booktitle = {{GPU} {C}omputing {G}ems },
    publisher = {{M}organ {K}aufmann },
    audience = {internationale },
    volume = {2 },
    editor = {{W}en-mei {W}. {H}wu },
    month = SEP,
    year = {2010},
    keywords = {On Applications; StarPU},
    URL = {http://hal.inria.fr/inria-00547847},
    pdf = {http://hal.inria.fr/inria-00547847/document},
    doi = {10.1016/B978-0-12-385963-1.00034-4},
    
    }
    
  2. Emmanuel Agullo, Cédric Augonnet, Jack Dongarra, Hatem Ltaief, Raymond Namyst, Jean Roman, Samuel Thibault, and Stanimire Tomov
    Dynamically scheduled Cholesky factorization on multicore architectures with GPU accelerators
    In SAAHPC - Symposium on Application Accelerators in High Performance Computing, Knoxville, USA, July 2010
    [WWW] [PDF] Keyword(s): On Applications, StarPU
    [bibtex-key = AguAugDonLtaNamRomThiTom10SAAHPC]

    @inproceedings{AguAugDonLtaNamRomThiTom10SAAHPC,
    HAL_ID = {inria-00547616},
    URL = {http://hal.inria.fr/inria-00547616/en/},
    title = { {D}ynamically scheduled {C}holesky factorization on multicore architectures with {GPU} accelerators},
    author = {{A}gullo, {E}mmanuel and {A}ugonnet, {C}{\'e}dric and {D}ongarra, {J}ack and {L}taief, {H}atem and {N}amyst, {R}aymond and {R}oman, {J}ean and {T}hibault, {S}amuel and {T}omov, {S}tanimire},
    language = {{A}nglais},
    booktitle = {SAAHPC - {S}ymposium on {A}pplication {A}ccelerators in {H}igh {P}erformance {C}omputing },
    address = {{K}noxville, USA},
    audience = {internationale },
    month = JUL,
    year = {2010},
    URL = {http://hal.inria.fr/inria-00547616},
    pdf = {http://hal.inria.fr/inria-00547616/document},
    keywords = {On Applications; StarPU},
    
    }
    
  3. Cédric Augonnet, Jérôme Clet-Ortega, Samuel Thibault, and Raymond Namyst
    Data-Aware Task Scheduling on Multi-Accelerator based Platforms
    In The 16th International Conference on Parallel and Distributed Systems (ICPADS), Shanghai, China, December 2010
    [WWW] [PDF] [doi:10.1109/ICPADS.2010.129] Keyword(s): On Scheduling, StarPU
    [bibtex-key = AugCleThiNam10ICPADS]

    @InProceedings{AugCleThiNam10ICPADS,
    author = {C\'edric Augonnet and J\'er\^ome Clet-Ortega and Samuel Thibault and Raymond Namyst},
    title = {{Data-Aware Task Scheduling on Multi-Accelerator based Platforms}},
    booktitle = {The 16th International Conference on Parallel and Distributed Systems (ICPADS)},
    year = {2010},
    address = {Shanghai, China},
    month = DEC,
    doi = {10.1109/ICPADS.2010.129},
    url = {http://hal.inria.fr/inria-00523937},
    pdf = {http://hal.inria.fr/inria-00523937/document},
    KEYWORDS = {On Scheduling;StarPU} 
    }
    
  4. Cédric Augonnet, Samuel Thibault, and Raymond Namyst
    StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines
    Research Report RR-7240, INRIA, March 2010
    [WWW] [PDF] Keyword(s): General Presentations, StarPU
    [bibtex-key = AugThiNamWac10RR7240]

    @TechReport{AugThiNamWac10RR7240,
    author = {C{\'e}dric Augonnet and Samuel Thibault and Raymond Namyst},
    title = {{StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines}},
    institution = {INRIA},
    year = 2010,
    type = {Research Report},
    number = {RR-7240},
    month = MAR,
    url = {http://hal.inria.fr/inria-00467677},
    pdf = {http://hal.inria.fr/inria-00467677/document},
    keywords = {General Presentations;StarPU} 
    }
    

2009

  1. Cédric Augonnet
    StarPU: un support exécutif unifié pour les architectures multicoeurs hétérogènes
    In 19èmes Rencontres Francophones du Parallélisme, Toulouse, France, September 2009
    Note: Best Paper Award
    [WWW] [PDF] Keyword(s): General Presentations, StarPU
    [bibtex-key = Aug09Renpar19]

    @InProceedings{Aug09Renpar19,
    author = {C{\'e}dric Augonnet},
    title = {{StarPU: un support ex{\'e}cutif unifi{\'e} pour les architectures multic\oe{}urs h{\'e}t{\'e}rog{\`e}nes}},
    booktitle = {19{\`e}mes Rencontres Francophones du Parall{\'e}lisme},
    year = 2009,
    month = SEP,
    address = {Toulouse, France},
    note = {Best Paper Award},
    url = {http://hal.inria.fr/inria-00411581},
    pdf = {http://hal.inria.fr/inria-00411581/document},
    KEYWORDS = {General Presentations;StarPU} 
    }
    
  2. Cédric Augonnet, Samuel Thibault, and Raymond Namyst
    Automatic Calibration of Performance Models on Heterogeneous Multicore Architectures
    In HPPC - Proceedings of the International Euro-Par Workshops, Highly Parallel Processing on a Chip, volume 6043 of LNCS, Delft, The Netherlands, pages 56-65, August 2009
    Springer
    [WWW] [PDF] [doi:10.1007/978-3-642-14122-5_9] Keyword(s): On Performance Model Tuning, StarPU
    [bibtex-key = AugThiNam09HPPC]

    @Inproceedings{AugThiNam09HPPC,
    author = {C{\'e}dric Augonnet and Samuel Thibault and Raymond Namyst},
    title = {{Automatic Calibration of Performance Models on Heterogeneous Multicore Architectures}},
    booktitle = {HPPC - Proceedings of the International Euro-Par Workshops, Highly Parallel Processing on a Chip},
    address = {Delft, The Netherlands},
    month = AUG,
    year = 2009,
    publisher = {Springer},
    series = {LNCS},
    volume = {6043},
    pages = {56--65},
    doi = {10.1007/978-3-642-14122-5_9},
    url = {http://hal.inria.fr/inria-00421333},
    pdf = {http://hal.inria.fr/inria-00421333/document},
    KEYWORDS = {On Performance Model Tuning;StarPU} 
    }
    
  3. Cédric Augonnet, Samuel Thibault, Raymond Namyst, and Maik Nijhuis
    Exploiting the Cell/BE architecture with the StarPU unified runtime system
    In SAMOS Workshop - International Workshop on Systems, Architectures, Modeling, and Simulation, volume 5657 of LNCS, Samos, Greece, July 2009
    [WWW] [PDF] [doi:10.1007/978-3-642-03138-0_36] Keyword(s): On The Cell Support, StarPU
    [bibtex-key = AugThiNamNij09Samos]

    @InProceedings{AugThiNamNij09Samos,
    author = {C{\'e}dric Augonnet and Samuel Thibault and Raymond Namyst and Maik Nijhuis},
    title = {Exploiting the {Cell/BE} architecture with the {StarPU} unified runtime system},
    booktitle = {SAMOS Workshop - International Workshop on {S}ystems, {A}rchitectures, {M}odeling, and {S}imulation},
    year = {2009},
    month = JUL,
    volume = {5657},
    series = {LNCS},
    address = {Samos, Greece},
    doi = {10.1007/978-3-642-03138-0_36},
    url = {http://hal.inria.fr/inria-00378705},
    pdf = {http://hal.inria.fr/inria-00378705/document},
    KEYWORDS = {On The Cell Support;StarPU} 
    }
    
  4. Cédric Augonnet, Samuel Thibault, Raymond Namyst, and Pierre-André Wacrenier
    StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures
    In Euro-Par - 15th International Conference on Parallel Processing, volume 5704 of LNCS, Delft, The Netherlands, pages 863-874, August 2009
    Springer
    [WWW] [PDF] [doi:10.1007/978-3-642-03869-3_80] Keyword(s): General Presentations, StarPU
    [bibtex-key = AugThiNamWac09Europar]

    @inproceedings{AugThiNamWac09Europar,
    author = {C{\'e}dric Augonnet and Samuel Thibault and Raymond Namyst and Pierre-Andr{\'e} Wacrenier},
    title = {{StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures}},
    booktitle = {Euro-Par - 15th International Conference on Parallel Processing},
    year = 2009,
    publisher = {Springer},
    series = {LNCS},
    volume = 5704,
    pages = {863--874},
    address = {Delft, The Netherlands},
    month = AUG,
    doi = {10.1007/978-3-642-03869-3_80},
    url = {http://hal.inria.fr/inria-00384363},
    pdf = {http://hal.inria.fr/inria-00384363/document},
    KEYWORDS = {General Presentations;StarPU} 
    }
    

2008

  1. Cédric Augonnet
    Vers des supports d'exécution capables d'exploiter les machines multicoeurs hétérogènes
    Master Thesis, Université de Bordeaux, June 2008
    [WWW] [PDF] Keyword(s): General Presentations, StarPU
    [bibtex-key = Aug08Master]

    @PhDThesis{Aug08Master,
    author = {C{\'e}dric Augonnet},
    title = {{Vers des supports d'ex{\'e}cution capables d'exploiter les machines multicoeurs h{\'e}t{\'e}rog{\`e}nes}},
    school = {Universit{\'e} de Bordeaux},
    year = {2008},
    type = {Master Thesis},
    month = JUN,
    url = {http://hal.inria.fr/inria-00289361},
    pdf = {http://hal.inria.fr/inria-00289361/document},
    keywords = {General Presentations; StarPU} 
    }
    
  2. Cédric Augonnet and Raymond Namyst
    A unified runtime system for heterogeneous multicore architectures
    In Proceedings of the International Euro-Par Workshops 2008, HPPC'08, volume 5415 of LNCS, Las Palmas de Gran Canaria, Spain, pages 174-183, August 2008
    Springer
    ISBN: 978-3-642-00954-9
    [WWW] [PDF] [doi:10.1007/978-3-642-00955-6_22] Keyword(s): General Presentations, StarPU
    [bibtex-key = AugNam08HPPC]

    @Inproceedings{AugNam08HPPC,
    author = {C{\'e}dric Augonnet and Raymond Namyst},
    title = {{A unified runtime system for heterogeneous multicore architectures}},
    booktitle = {Proceedings of the International Euro-Par Workshops 2008, HPPC'08},
    address = {Las Palmas de Gran Canaria, Spain},
    publisher = {Springer},
    series = {LNCS},
    volume = 5415,
    pages = {174--183},
    doi = {10.1007/978-3-642-00955-6_22},
    isbn = {978-3-642-00954-9},
    month = AUG,
    year = 2008,
    url = {http://hal.inria.fr/inria-00326917},
    pdf = {http://hal.inria.fr/inria-00326917/document},
    KEYWORDS = {General Presentations;StarPU} 
    }
    

Author: root

Created: 2022-05-18 Wed 08:25

Validate