P
Pierre Lemarinier
Researcher at University of Paris-Sud
Publications - 9
Citations - 278
Pierre Lemarinier is an academic researcher from University of Paris-Sud. The author has contributed to research in topics: Fault tolerance & Message passing. The author has an hindex of 6, co-authored 9 publications receiving 269 citations. Previous affiliations of Pierre Lemarinier include French Institute for Research in Computer Science and Automation & Centre national de la recherche scientifique.
Papers
More filters
Journal ArticleDOI
MPICH-V Project: A Multiprotocol Automatic Fault-Tolerant MPI
TL;DR: The MPICH-V project focuses on designing, implementing and comparing several automatic fault-tolerant protocols for MPI applications, covering a large spectrum of known approaches from coordinated checkpoint, to uncoordinated checkpoint associated with causal message logging.
Journal ArticleDOI
Blocking vs. non-blocking coordinated checkpointing for large-scale fault tolerant MPI Protocols
Darius Buntinas,Camille Coti,Thomas Herault,Thomas Herault,Pierre Lemarinier,Pierre Lemarinier,Laurence Pilard,Laurence Pilard,Ala Rezmerita,Ala Rezmerita,Eric Rodriguez,Eric Rodriguez,Franck Cappello,Franck Cappello +13 more
TL;DR: Two different concepts of coordinated checkpointing have been proposed: blocking and non-blocking and their respective scalabilities remain unknown and the first comparison between these two approaches is provided and a study of their scalabilities are studied.
Distibuted Dense Numerical Linear Algebra Algorithms on Massively Parallel Architectures: DPLASMA
George Bosilca,Aurelien Bouteiller,Anthony Danalis,Mathieu Faverge,Azzam Haidar,Thomas Herault,Jakub Kurzak,Julien Langou,Pierre Lemarinier,Hatem Ltaief,Piotr Luszczek,Asym Yarkhan,Jack Dongarra +12 more
TL;DR: It is demonstrated from the preliminary results that the DAG-based approach has the potential to bridge the gap between the peak and the achieved performance that is characteristic in the state-of-the-art distributed numerical softwares on current and emerging architectures.
Book ChapterDOI
Brief announcement: self-stabilizing spanning tree algorithm for large scale systems
TL;DR: A self-stabilizing algorithm that builds and maintains a spanning tree topology on any large scale system to cope with the large number of processes of a grid or a peer to peer system is introduced.
Proceedings ArticleDOI
Hybrid Preemptive Scheduling of MPI Applications on the Grids
TL;DR: A new hybrid sharing technique providing checkpoint based explicit memory management is introduced, which consists in co-scheduling parallel applications within a set, until the memory capacity of the node is reached, and using gang scheduling related techniques to switch from one set to another one.