Cédric Augonnet

Cette page est également disponible en français ici.

Welcome on my former website. I have now moved to NVIDIA where in the CUDA team. I am a PhD student working with Raymond Namyst and Samuel Thibault in the Runtime team at the INRIA Bordeaux since September 2008. My research activities mainly focus on high performance computing on heterogeneous multicore architectures (GPGPU, Cell, ...). I have therefore started the development of the StarPU runtime system in order to harness the power of those architectures.

Contact

CV

Main interests

• MultiCore Architectures
• GPGPU, Cell ...
• High Performance Computing
• Operating Systems
• High Speed Networking

Publications

• Détection optimale des coins et contours dans des bases d'images volumineuses sur architectures multicoeurs hétérogènes
  Sidi Ahmed Mahmoudi, Pierre Manneback, Cédric Augonnet, and Samuel Thibault.
  In 20èmes Rencontres Francophones du Parallélisme, Saint-Malo / France, May 2011. Bibtex
  @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 = {20{\`e}mes Rencontres Francophones du Parall{\'e}lisme},
    YEAR = 2011,
    MONTH = MAY,
    ADDRESS = {Saint-Malo / France},
  }
  

• A Hybridization Methodology for High-Performance Linear Algebra Software for GPUs
  Emmanuel Agullo, Cédric Augonnet, Jack Dongarra, Hatem Ltaief, Raymond Namyst, Samuel Thibault, and Stanimire Tomov.
  In Wen-mei W. Hwu, editor, GPU Computing Gems, volume 2. Morgan Kaufmann, 09 2010. Bibtex
  @incollection{AguAugDonLtaNamThiTomGPUgems,
  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},
  BOOKTITLE = {{GPU} {C}omputing {G}ems},
  PUBLISHER = {{M}organ {K}aufmann},
  VOLUME = {2},
  EDITOR = {{W}en-mei {W}. {H}wu},
  MONTH = SEP,
  YEAR = {2010},
  URL = {http://hal.inria.fr/inria-00547847},
  }
  

• QR Factorization on a Multicore Node Enhanced with Multiple GPU Accelerators
  Emmanuel Agullo, Cédric Augonnet, Jack Dongarra, Mathieu Faverge, Hatem Ltaief, Samuel Thibault and Stanimire Tomov.
  In 25th IEEE International Parallel and Distributed Processing Symposium (IEEE IPDPS 2011), Anchorage, Alaska, USA, May 2011. Bibtex
  @InProceedings{AguAugDonFavLtaThiTom11IPDPS,
    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},
    DAYS=16,
    MONTH=MAY,
    YEAR=2011
  }
  

• Data-Aware Task Scheduling on Multi-Accelerator based Platforms
  Cédric Augonnet, Jérôme Clet-Ortega, Samuel Thibault, and Raymond Namyst.
  In The 16th International Conference on Parallel and Distributed Systems (ICPADS), Shangai, China, December 2010. Bibtex
  @Article{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)},
    address = {Shangai, China},
    month = DEC,
    year = 2010,
    notes = {to appear},
    url = {http://hal.archives-ouvertes.fr/inria-00523937/}
    keywords = {StarPU}
  }
  

• StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures. (extended version)
  Cédric Augonnet, Samuel Thibault, Raymond Namyst, and Pierre-André Wacrenier.
  In Concurrency and Computation: Practice and Experience, Euro-Par 2009 best papers issue. Bibtex
  @Article{AugThiNamWac10CCPE,
    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 = {Concurrency and Computation: Practice and Experience, Euro-Par 2009 best papers issue},
    year = 2010,
    publisher = {Wiley},
    notes = {Accepted for publication, to appear},
    keywords = {StarPU}
  }
  

• Automatic Calibration of Performance Models on Heterogeneous Multicore Architectures.
  Cédric Augonnet, Samuel Thibault and Raymond Namyst.
  In Highly Parallel Processing on a Chip (HPPC 2009), workshop help in conjunction with Europar 2009, Delft, The Netherlands, August 2009. (slides) Bibtex
  @Inproceedings{AugThiNam09HPPC,
    author = {C{\'e}dric Augonnet and Samuel Thibault and Raymond Namyst},
    title = {{Automatic Calibration of Performance Models on Heterogeneous Multicore Architectures}},
    booktitle = {Proceedings of the International Euro-Par Workshops 2009, HPPC'09},
    address = {Delft, The Netherlands},
    month = AUG,
    year = 2009,
    keywords = {StarPU},
    publisher = {Springer},
    series = {Lecture Notes in Computer Science},
    url = {http://hal.inria.fr/inria-00421333},
    keywords = {StarPU}
  }
  

• StarPU : un support exécutif unifié pour les architectures multicoeurs hétérogènes.
  Cédric Augonnet.
  In 19ème Rencontres Francophones du Parallélisme, Toulouse / France, September 2009. Best Paper award. (slides) Bibtex
  @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}me Rencontres Francophones du Parall{\'e}lisme},
    year = 2009,
    month = SEP,
    address = {Toulouse / France},
    notes = {Best Paper Award},
    url = {http://hal.inria.fr/inria-00411581},
    keywords = {StarPU}
  }
  

• StarPU: A Unified Platform for Task Scheduling on Heterogeneous Multicore Architectures.
  Cédric Augonnet, Samuel Thibault, Raymond Namyst and Pierre-André Wacrenier.
  In Proceedings of the 15th International Euro-Par Conference, Lecture Notes in Computer Science, Delft, The Netherlands, August 2009. (slides) Bibtex
  @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 = {Proceedings of the 15th International Euro-Par Conference, Lecture Notes in Computer Science},
    year = 2009,
    publisher = {Springer},
    series = {Lecture Notes in Computer Science},
    volume = 5704,
    pages = {863--874},
    address = {Delft, The Netherlands},
    month = AUG,
    keywords = {StarPU},
    doi = {10.1007/978-3-642-03869-3_80},
    url = {http://hal.inria.fr/inria-00384363}
  }
  

• Exploiting the Cell/BE architecture with the StarPU unified runtime system.
  Cédric Augonnet, Samuel Thibault, Raymond Namyst and Maik Nijhuis.
  In International Workshop on Systems, Architectures, Modeling, and Simulation (SAMOS workshop 2009), Samos, Greece, July 2009. (slides) Bibtex
  @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,
    series = {Lecture Notes in Computer Science},
    address = {Samos, Greece},
    keywords = {StarPU},
    doi = {10.1007/978-3-642-03138-0_36},
    url = {http://hal.inria.fr/inria-00378705}
  }
  

• Mapping and synchronizing streaming applications on Cell processors.
  Maik Nijhuis, Herbert Bos, Henri Bal and Cédric Augonnet.
  In International Conference on High Performance Embedded Architectures and Compilers (HiPEAC 2009), Paphos, Cyprus, January 2009. Bibtex
  @InProceedings{NijBosBalAug09HiPEAC,
    author= {Maik Nijhuis and Herbert Bos and Henri Bal and C\'edric Augonnet},
    title = {{Mapping and Synchronizing Streaming Applications on Cell Processors}},
    address = {Paphos, Cyprus},
    month = JAN,
    year = {2009},
    booktitle = {International Conference on High Performance Embedded Architectures & Compilers},
    doi = {10.1007/978-3-540-92990-1_17},
    url = {http://runtime.bordeaux.inria.fr/augonnet/papers/NijBosBalAug09HiPEAC.pdf}
  }
  

• A unified runtime system for heterogeneous multicore architectures.
  Cédric Augonnet and Raymond Namyst.
  In Highly Parallel Processing on a Chip (HPPC 2008), workshop help in conjunction with Europar 2008, Las Palmas de Gran Canaria, Spain, August 2008. (slides) Bibtex
  @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 = {Lecture Notes in Computer Science},
    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},
    keywords = {StarPU}
  }
  

Master Thesis

• 2008: Vers des supports d'exécution capables d'exploiter les machines multicœurs hétérogènes (in french)

Internship reports

• 2007: Interval-based registration cache for zero-copy protocols (in english)

• 2006: Optimisation des communications sur réseaux rapides par utilisation de RDMA (in french)

Various reports

• 2008: Literature Study : The Implementation of the Cilk-5 Multithreaded Language (slides in french)
• 2007: An introduction to the Cell processor
• 2007: Literature Study : NUMA-Aware Thread Scheduling On Hierarchical Multiprocessor Machines (in english)