BACK TO INDEX

RUNTIME

Publications of Mathieu Faverge


Articles in journal or book chapters

  1. Mathieu Faverge and Pierre Ramet. A NUMA Aware Scheduler for a Parallel Sparse Direct Solver. Parallel Computing, 2009. Note: Submitted. Keyword(s): NUMA.
    @Article{FavRam09ParCo,
    author = {Mathieu Faverge and Pierre Ramet},
    title = {A {NUMA} Aware Scheduler for a Parallel Sparse Direct Solver},
    journal = {{P}arallel {C}omputing},
    year = {2009},
    note = {Submitted},
    keywords = {NUMA} 
    }
    


Conference articles

  1. 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 workshop of IPDPS, Phoenix, États-Unis, May 2014. IEEE. Note: RR-8446 RR-8446. [WWW] [PDF] Keyword(s): StarPU.
    @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},
    keywords = {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},
    booktitle = {{HCW'2014 workshop of IPDPS}},
    publisher = {IEEE},
    address = {Phoenix, {\'E}tats-Unis},
    note = {RR-8446 RR-8446 },
    audience = {internationale },
    year = {2014},
    month = May,
    pdf = {http://hal.inria.fr/hal-00987094/PDF/sparsegpus.pdf},
    
    }
    


  2. 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] Keyword(s): StarPU.
    @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},
    keywords = {StarPU} 
    }
    


  3. 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] [doi:10.1109/IPDPS.2011.90] Keyword(s): StarPU.
    @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 },
    DAYS=16,
    MONTH=MAY,
    YEAR=2011,
    keywords = {StarPU},
    doi = {10.1109/IPDPS.2011.90},
    URL = {http://hal.inria.fr/inria-00547614} 
    }
    


  4. Mathieu Faverge. A NUMA Aware Scheduler for a Parallel Sparse Direct Solver. In Journées Informatique Massivement Multiprocesseur et Multicoeur, Rocquencourt, France, February 2009. [WWW] Keyword(s): NUMA.
    @InProceedings{Fav09I3M,
    author = {Mathieu Faverge},
    title = {A NUMA Aware Scheduler for a Parallel Sparse Direct Solver},
    booktitle = "Journ\'ees Informatique Massivement Multiprocesseur et Multicoeur",
    year = {2009},
    address = {Rocquencourt, France},
    month = feb,
    url = {http://www.labri.fr/~ramet/restricted/i3m.pdf.gz},
    keywords = {NUMA} 
    }
    


  5. Mathieu Faverge. Vers un solveur de systèmes linéaires creux adapté aux machines NUMA. In 19èmes Rencontres Francophones du Parallélisme, Toulouse / France, September 2009. [WWW] Keyword(s): NUMA.
    @InProceedings{Fav09Renpar19,
    author = {Mathieu Faverge},
    title = {Vers un solveur de syst{\`e}mes lin{\'e}aires creux adapt{\'e} aux machines {NUMA}},
    booktitle = {19{\`e}mes Rencontres Francophones du Parall{\'e}lisme},
    year = 2009,
    month = SEP,
    address = {Toulouse / France},
    keywords = {NUMA},
    url = {http://hal.inria.fr/inria-00416496} 
    }
    


  6. Mathieu Faverge, Xavier Lacoste, and Pierre Ramet. A NUMA Aware Scheduler for a Parallel Sparse Direct Solver. In Proceedings of PMAA'2008, Neuchâtel, Suisse, 2008. [WWW] Keyword(s): NUMA.
    @InProceedings{FavLacRam08PMAA,
    author = "Mathieu Faverge and Xavier Lacoste and Pierre Ramet",
    title = {{A NUMA Aware Scheduler for a Parallel Sparse Direct Solver}},
    booktitle = "Proceedings of {PMAA}'2008, Neuch\^atel, Suisse",
    year = "2008",
    url = {http://hal.inria.fr/inria-00344709},
    keywords = {NUMA},
    abstract = {Over the past few years, parallel sparse direct solvers made significant progress and are now able to solve efficiently industrial three-dimensional problems with several millions of unknowns. An hybrid MPI-thread implementation of our direct solver PaStiX is already well suited for SMP nodes or new multi-core architectures and drastically reduced the memory overhead and improved scalability. In the context of distributed NUMA architectures, a dynamic scheduler based on a work-stealing algorithm has been developed to fill in communication idle times. On these architectures, it is important to take care of NUMA effects and to preserve memory affinity during the work-stealing. The scheduling of communications also needs to be adapted, especially to ensure the overlap by computations. Experiments on numerical test cases will be presented to prove the efficiency of the approach on NUMA architectures. If memory is not large enough to treat a given problem, disks must be used to store data that cannot fit in memory (out-of-core storage). The idle-times due to disk access have to be managed by our dynamic scheduler to prefetch and save datasets. Thus, we design and study specific scheduling algorithms in this particular context.} 
    }
    


  7. Mathieu Faverge and Pierre Ramet. Dynamic Scheduling for sparse direct Solver on NUMA architectures. In Proceedings of PARA'2008, Trondheim, Norway, 2008. [WWW] Keyword(s): NUMA.
    @InProceedings{FavRam08PARA,
    author = {Mathieu Faverge and Pierre Ramet},
    title = {{Dynamic Scheduling for sparse direct Solver on NUMA architectures}},
    booktitle = {Proceedings of PARA'2008, Trondheim, Norway},
    year = {2008},
    url = {http://hal.inria.fr/inria-00344026},
    OPTurl = {http://www.labri.fr/~ramet/restricted/para08.pdf.gz},
    keywords = {NUMA},
    abstract = {Over the past few years, parallel sparse direct solvers made significant progress and are now able to efficiently work on problems with several millions of equations. This paper presents some improvements on our sparse direct solver PaStiX1 for distributed Non-Uniform Memory Access architectures. We show results on two preliminary works: a memory allocation scheme more adapted to these architectures and a better overlap of communication by computation. We also present a dynamic scheduler that takes care of memory affinity and data locality.} 
    }
    


Internal reports

  1. 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. Research Report RR-8927, Inria Bordeaux Sud-Ouest ; Bordeaux INP ; CNRS ; Université de Bordeaux ; CEA, June 2016. [WWW] [PDF] Keyword(s): StarPU, runtime system, sequential task flow, OpenMP depend clause, heterogeneous computing, distributed computing, multicore, Cholesky factorization, support d’exécution, flot de tâches séquentiel, clause OpenMP depend, calcul hétérogène, calcul distribué, multi-coeur, GPU, factorisation de Cholesky.
    @techreport{agullo:hal-01332774,
    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-01332774},
    TYPE = {Research Report},
    NUMBER = {RR-8927},
    PAGES = {27},
    INSTITUTION = {{Inria Bordeaux Sud-Ouest ; Bordeaux INP ; CNRS ; Universit{\'e} de Bordeaux ; CEA}},
    YEAR = {2016},
    MONTH = Jun,
    KEYWORDS = {StarPU ; runtime system ; sequential task flow ; OpenMP depend clause ; heterogeneous computing ; distributed computing ; multicore ; Cholesky factorization ; support d’ex{\'e}cution ; flot de t{\^a}ches s{\'e}quentiel ; clause OpenMP depend ; calcul h{\'e}t{\'e}rog{\`e}ne ; calcul distribu{\'e} ; multi-c{\oe}ur ; GPU ; factorisation de Cholesky},
    PDF = {https://hal.inria.fr/hal-01332774/file/RR-8927.pdf},
    HAL_ID = {hal-01332774},
    HAL_VERSION = {v1},
    
    }
    


  2. Xavier Lacoste, Mathieu Faverge, Pierre Ramet, Samuel Thibault, and George Bosilca. Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes. Rapport de recherche RR-8446, INRIA, January 2014. [WWW] [PDF] Keyword(s): StarPU.
    @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 = {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 = {Rapport de recherche},
    institution = {INRIA},
    number = {RR-8446},
    year = {2014},
    month = Jan,
    pdf = {http://hal.inria.fr/hal-00925017/PDF/RR-8446.pdf} 
    }
    


Miscellaneous

  1. 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): StarPU.
    @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, {\'E}tats-Unis},
    audience = {internationale },
    year = {2014},
    month = Feb,
    pdf = {http://hal.inria.fr/hal-00978602/PDF/siampp14.pdf},
    keywords = {StarPU} 
    }
    



BACK TO INDEX




Disclaimer:

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Les documents contenus dans ces répertoires sont rendus disponibles par les auteurs qui y ont contribué en vue d'assurer la diffusion à temps de travaux savants et techniques sur une base non-commerciale. Les droits de copie et autres droits sont gardés par les auteurs et par les détenteurs du copyright, en dépit du fait qu'ils présentent ici leurs travaux sous forme électronique. Les personnes copiant ces informations doivent adhérer aux termes et contraintes couverts par le copyright de chaque auteur. Ces travaux ne peuvent pas être rendus disponibles ailleurs sans la permission explicite du détenteur du copyright.




Last modified: Wed Dec 7 18:46:41 2016
Author: sthibault.


This document was translated from BibTEX by bibtex2html