Accéder directement au contenu

Pierre Ramet

Pierre RAMET - Responsable du département SATANAS (Supports et Algorithms pour les Applications Numériques Hautes Performances)
116
Documents
Affiliations actuelles
  • 259761
  • 104751
  • 3102
  • 440172
  • 1124391
Identifiants chercheurs
Contact

Présentation

Ma problématique de recherche concerne les problèmes du calcul haute performance, en particulier l'algèbre linéaire creuse. Je développe la bibliothèque PaStiX ([https://solverstack.gitlabpages.inria.fr/pastix](https://solverstack.gitlabpages.inria.fr/pastix "PaStiX")) qui implémente un solveur direct creux haute performance. ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
My interests span high-performance computing, focusing on sparse linear algebra. I am the developer of PaStiX ([https://solverstack.gitlabpages.inria.fr/pastix](https://solverstack.gitlabpages.inria.fr/pastix "PaStiX")), a high-performance sparse direct solver. ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Domaines de recherche

Informatique [cs] Analyse numérique [math.NA]

Compétences

Sparse Linear Algebra Parallel Algorithms Scientific Computing

Publications

The JOREK non-linear extended MHD code and applications to large-scale instabilities and their control in magnetically confined fusion plasmas

Matthias Hoelzl , Guido Huijsmans , Stanislas Pamela , Marina Bécoulet , Eric Nardon
Nuclear Fusion, 2021, 61 (6), pp.065001. ⟨10.1088/1741-4326/abf99f⟩
Article dans une revue hal-03352509v1
Image document

Efficient Parallel Solution of the 3D Stationary Boltzmann Transport Equation for Diffusive Problems

Salli Moustafa , François Févotte , Mathieu Faverge , Laurent Plagne , Pierre Ramet
Journal of Computational Physics, 2019, ⟨10.1016/j.jcp.2019.03.019⟩
Article dans une revue hal-02080624v1
Image document

Sparse supernodal solver using block low-rank compression: Design, performance and analysis

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
International Journal of Computational Science and Engineering, 2018, 27, pp.255 - 270. ⟨10.1016/J.JOCS.2018.06.007⟩
Article dans une revue hal-01824275v1
Image document

Reordering Strategy for Blocking Optimization in Sparse Linear Solvers

Grégoire Pichon , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Journal on Matrix Analysis and Applications, 2017, SIAM Journal on Matrix Analysis and Applications, 38 (1), pp.226 - 248. ⟨10.1137/16M1062454⟩
Article dans une revue hal-01485507v2
Image document

Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver

Salli Moustafa , Ivan Dutka Malen , Laurent Plagne , Angélique Ponçot , Pierre Ramet
Annals of Nuclear Energy, 2014, Special Issue SNA+MC 2013, pp.1-10. ⟨10.1016/j.anucene.2014.08.034⟩
Article dans une revue hal-00986975v1
Image document

Efficient Parallel Resolution of The Simplified Transport Equations in Mixed-Dual Formulation

Maxime Barrault , Bruno Lathuilière , Pierre Ramet , Jean Roman
Journal of Computational Physics, 2011, 230 (5), pp.2004-2020. ⟨10.1016/j.jcp.2010.11.047⟩
Article dans une revue hal-00547406v1

Non-linear MHD simulations of edge localized modes (ELMs)

G. Huysmans , Stanislas Pamela , Emiel van Der Plas , Pierre Ramet
Plasma Physics, 2009, 51 (12), pp.124012
Article dans une revue hal-01251754v1
Image document

Numerical simulation of unsteady MHD flows and applications

Remi Abgrall , Pierre Ramet , Robin Huart
Magnetohydrodynamics c/c of Magnitnaia Gidrodinamika, 2009, 45 (2), pp.225-232
Article dans une revue hal-00547413v1

On finding approximate supernodes for an efficient ILU(k) factorization

Pascal Hénon , Pierre Ramet , Jean Roman
Parallel Computing, 2008, 34, pp.345--362
Article dans une revue inria-00346018v1

PaStiX: A High-Performance Parallel Direct Solver for Sparse Symmetric Definite Systems

Pascal Hénon , Pierre Ramet , Jean Roman
Parallel Computing, 2002, 28 (2), pp.301--321
Article dans une revue inria-00346017v1

Scilab to Scilab//, the OURAGAN Project

Eddy Caron , Serge Chaumette , Sylvain Contassot-Vivier , Frédéric Desprez , Eric Fleury
Parallel Computing, 2001, 27 (11), pp.1497-1519. ⟨10.1016/S0167-8191(01)00101-6⟩
Article dans une revue inria-00000277v1

Parallel Sparse Linear Algebra and Application to Structural Mechanics

David Goudin , Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman
Numerical Algorithms, 2000, 24, pp.371--391
Article dans une revue inria-00346016v1

Toward a Multigrid Method for the Indefinite Helmholtz Equation

Robert Falgout , Matthieu Lecouvez , Pierre Ramet , Clément Richefort
CSE 2023 - SIAM Conference on Computational Science and Engineering, Feb 2023, Amsterdam, Netherlands
Communication dans un congrès hal-04046630v1
Image document

Toward a multilevel method for the Helmholtz equation

Clément Richefort , Matthieu Lecouvez , Robert Falgout , Pierre Ramet
21st SIAM Copper Mountain Conference on Multigrid Method, Apr 2023, Copper Mountain, CO, United States
Communication dans un congrès hal-04046622v1
Image document

Deciding Non-Compressible Blocks in Sparse Direct Solvers using Incomplete Factorization

Esragul Korkmaz , Mathieu Faverge , Grégoire Pichon , Pierre Ramet
HiPC 2021 - 28th IEEE International Conference on High Performance Computing, Data, and Analytics, Dec 2021, Bangalore, India. pp.1-10, ⟨10.1109/HiPC53243.2021.00024⟩
Communication dans un congrès hal-03361299v1
Image document

Improving mapping for sparse direct solvers: A trade-off between data locality and load balancing

Changjiang Gou , Ali Al Zoobi , Anne Benoit , Mathieu Faverge , Loris Marchal
EuroPar 2020 - 26th International European Conference on Parallel and Distributed Computing, Aug 2020, Warsaw / Virtual, Poland. pp.1-16
Communication dans un congrès hal-02973315v1

Recent Developments Around the Block Low-Rank PaStiX Solver

Grégoire Pichon , Mathieu Faverge , Pierre Ramet
PP 2020 - SIAM Conference on Parallel Processing for Scientific Computing, Feb 2020, Seattle, United States
Communication dans un congrès hal-03140189v1

Exploiting Parameterized Task-graph in Sparse Direct Solvers

Mathieu Faverge , Grégoire Pichon , Pierre Ramet
SIAM Conference on Computational Science and Engineering (CSE19), Feb 2019, Spokane, United States
Communication dans un congrès hal-01956963v1
Image document

Block Low Rank Algebraic Clustering for Sparse Direct Solvers

Pierre Ramet
Journées Ondes Sud-Ouest (JOSO), Mar 2019, Le Barp, France
Communication dans un congrès hal-02139186v1

Rank Revealing QR Methods for Sparse Block Low Rank Solvers

Esragul Korkmaz , Mathieu Faverge , Grégoire Pichon , Pierre Ramet
COMPAS 2019 - Conférence d'informatique en Parallélisme, Architecture et Système, Jun 2019, Anglet, France
Communication dans un congrès hal-02326084v1

Rank Revealing QR Methods for Sparse Block Low Rank Solvers

Esragul Korkmaz , Mathieu Faverge , Grégoire Pichon , Pierre Ramet
Sparse Days 2019, Jul 2019, Toulouse, France
Communication dans un congrès hal-02326070v1

Block Low-rank Algebraic Clustering for Sparse Direct Solvers

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Conference on Computational Science and Engineering (CSE19), Feb 2019, Spokane, United States
Communication dans un congrès hal-01956962v1
Image document

Utilisation de la compression Block Low-Rank pour accélérer un solveur direct creux supernodal

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
COMPAS 2018 - Conférence d'informatique en Parallélisme, Architecture et Système, Jul 2018, Toulouse, France
Communication dans un congrès hal-01956959v1
Image document

Supernodes ordering to enhance Block Low-Rank compression in sparse direct solvers

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
PMAA 2018 - 10th International Workshop on Parallel Matrix Algorithms and Applications, Jun 2018, Zurich, Switzerland
Communication dans un congrès hal-01956960v1

Exploiting Modern Manycore Architecture in Sparse Direct Solver with Runtime Systems

Grégoire Pichon , Mathieu Faverge , Pierre Ramet
SIAM Conference on Computation Science and Engineering (CSE'17), Feb 2017, Atlanta, United States
Communication dans un congrès hal-01421383v1

Impact of Blocking Strategies for Sparse Direct Solvers on Top of Generic Runtimes

Grégoire Pichon , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Conference on Computation Science and Engineering (CSE'17), Feb 2017, Atlanta, United States
Communication dans un congrès hal-01421384v1
Image document

Sparse Supernodal Solver exploiting Low-Rankness Property

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
Sparse Days 2017, Sep 2017, Toulouse, France
Communication dans un congrès hal-01585622v1
Image document

Sparse Supernodal Solver Using Block Low-Rank Compression

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
18th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC 2017), Jun 2017, Orlando, United States
Communication dans un congrès hal-01502215v1

Sparse Supernodal Solver Using Hierarchical Compression over Runtime System

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Conference on Computation Science and Engineering (CSE'17), Feb 2017, Atlanta, United States
Communication dans un congrès hal-01421379v1

On the use of low rank approximations for sparse direct solvers

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Annual Meeting (AN'16), Jul 2016, Boston, United States
Communication dans un congrès hal-01421376v1

Exploiting Kepler architecture in sparse direct solver with runtime systems

Mathieu Faverge , Grégoire Pichon , Pierre Ramet
9th International Workshop on Parallel Matrix Algorithms and Applications (PMAA'2016), Jul 2016, Bordeaux, France
Communication dans un congrès hal-01421372v1

Exploiting H-Matrices in Sparse Direct Solvers

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2016), Apr 2016, Paris, France
Communication dans un congrès hal-01251812v1

Sparse Supernodal Solver Using Hierarchical Compression

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
Workshop on Fast Direct Solvers, Nov 2016, Purdue, United States
Communication dans un congrès hal-01421368v1

Impact of Blocking Strategies for Sparse Direct Solvers on Top of Generic Runtimes

Grégoire Pichon , Mathieu Faverge , Pierre Ramet , Jean Roman
SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2016), Apr 2016, Paris, France
Communication dans un congrès hal-01251808v1

On the design of parallel linear solvers for large scale problems

Xavier Lacoste , Mathieu Faverge , Pierre Ramet
Mini-Symposium on Recent advances in matrix computations for extreme-scale computers at ICIAM'15 conference, Aug 2015, Beijing, China
Communication dans un congrès hal-01100987v1

Towards a recursive graph bipartitioning algorithm for well balanced domain decomposition

Astrid Casadei , Pierre Ramet , Jean Roman
Mini-Symposium on "Combinatorial Issues in Sparse Matrix Computation" at ICIAM'15 conference, Aug 2015, Beijing, China
Communication dans un congrès hal-01100990v1

Blocking strategy optimizations for sparse direct linear solver on heterogeneous architectures

Mathieu Faverge , Grégoire Pichon , Pierre Ramet , Jean Roman
Sparse Days, Jun 2015, Saint Girons, France
Communication dans un congrès hal-01187881v1

On the use of H-Matrix Arithmetic in PaStiX: a Preliminary Study

Mathieu Faverge , Grégoire Pichon , Pierre Ramet , Jean Roman
Workshop on Fast Direct Solvers, Jun 2015, Toulouse, France
Communication dans un congrès hal-01187882v1

A task-based sparse direct solver suited for large scale hierarchical/heterogeneous architectures

Xavier Lacoste , Mathieu Faverge , Pierre Ramet
SIAM Conference on Computational Science and Engineering (SIAM CSE 2015), Mar 2015, Salt Lake City, United States
Communication dans un congrès hal-01100979v1
Image document

3D Cartesian Transport Sweep for Massively Parallel Architectures with PARSEC

Salli Moustafa , Mathieu Faverge , Laurent Plagne , Pierre Ramet
IEEE International Parallel & Distributed Processing Symposium (IPDPS 2015), May 2015, Hyderabad, India. pp.581-590, ⟨10.1109/IPDPS.2015.75⟩
Communication dans un congrès hal-01078362v1

Towards a recursive graph bipartitioning algorithm for well balanced domain decomposition

Astrid Casadei , Pierre Ramet , Jean Roman
SIAM Conference on Computational Science and Engineering (SIAM CSE 2015), Mar 2015, Salt Lake City, United States
Communication dans un congrès hal-01100985v1

Toward parallel scalable linear solvers suited for large scale hierarchical parallel platforms

Emmanuel Agullo , Mathieu Faverge , Luc Giraud , Abdou Guermouche , Pierre Ramet
World Congress on Computational Mechanics, Jul 2014, Barcelona, Spain
Communication dans un congrès hal-00987110v1
Image document

Parallel 3D Sweep Kernel with PARSEC

Salli Moustafa , Mathieu Faverge , Laurent Plagne , Pierre Ramet
HPCC Workshop on HPC-CFD in Energy/Transport Domains, Aug 2014, Paris, France
Communication dans un congrès hal-01078364v1
Image document

Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes

Xavier Lacoste , Mathieu Faverge , Pierre Ramet , Samuel Thibault , George Bosilca
HCW'2014 workshop of IPDPS, May 2014, Phoenix, United States. pp.29-38, ⟨10.1109/IPDPSW.2014.9⟩
Communication dans un congrès hal-00987094v1
Image document

An improved recursive graph bipartitioning algorithm for well balanced domain decomposition

Astrid Casadei , Pierre Ramet , Jean Roman
IEEE International Conference on High Performance Computing (HiPC 2014), Dec 2014, Goa, India. pp.1-10, ⟨10.1109/HiPC.2014.7116878⟩
Communication dans un congrès hal-01100962v1
Image document

Nested dissection with balanced halo

Astrid Casadei , Pierre Ramet , Jean Roman
Sixth SIAM Workshop on Combinatorial Scientific Computing, Jul 2014, Lyon, France
Communication dans un congrès hal-00987099v1
Image document

From hybrid architectures to hybrid solvers

Pierre Ramet
Workshop Celebrating 40 Years of Nested Dissection, Jul 2013, Waterloo, Canada
Communication dans un congrès hal-00924979v1
Image document

Shared Memory Parallelism for 3D Cartesian Discrete Ordinates Solver

Salli Moustafa , Ivan Dutka Malen , Laurent Plagne , Angélique Ponçot , Pierre Ramet
Joint International Conference on Supercomputing in Nuclear Applications and Monte Carlo 2013, Oct 2013, Paris, France
Communication dans un congrès hal-00924989v2
Image document

Towards Domain Decomposition with Balanced Halo

Astrid Casadei , Luc Giraud , Pierre Ramet , Jean Roman
Workshop Celebrating 40 Years of Nested Dissection, Jul 2013, Waterloo, Canada
Communication dans un congrès hal-00924977v1

Toward a supernodal sparse direct solver over DAG runtimes

George Bosilca , Mathieu Faverge , Xavier Lacoste , Ichitaro Yamazaki , Pierre Ramet
Parallel Matrix Algorithms and Applications, Jun 2012, Londres, United Kingdom
Communication dans un congrès hal-00769030v1

Memory Optimization to Build a Schur Complement

Astrid Casadei , Pierre Ramet
SIAM Conference on Applied Linear Algebra (SIAM LA 2012), Jun 2012, Valence, Spain
Communication dans un congrès hal-00769029v1

Sparse direct solver on top of large-scale multicore systems with GPU accelerators

Xavier Lacoste , Pierre Ramet
SIAM Conference on Applied Linear Algebra (SIAM LA 2012), Jun 2012, Valence, Spain
Communication dans un congrès hal-00769027v1

Fine Grain Scheduling for Sparse Solver on Manycore Architectures

Mathieu Faverge , Pierre Ramet
SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2012), Feb 2012, Savannah, United States
Communication dans un congrès hal-00769026v1
Image document

A NUMA Aware Scheduler for a Parallel Sparse Direct Solver

Mathieu Faverge , Pierre Ramet
Workshop on Massively Multiprocessor and Multicore Computers, INRIA, Feb 2009, Rocquencourt, France. 5p
Communication dans un congrès inria-00416502v1

Non-Linear MHD simulations of Edge Localised Modes

G. Huysmans , Stanislas Pamela , Emiel van Der Plas , Pierre Ramet
36th EPS Plasma Physics Conference, Jun 2009, Sofia, Bulgaria
Communication dans un congrès inria-00403797v1

A Non Overlapping Parallel Domain Decomposition Method Applied to The Simplified Transport Equations

Maxime Barrault , Bruno Lathuilière , Pierre Ramet , Jean Roman
International Conference on Mathematics, Computational Methods & Reactor Physics, 2009, New-York, United States
Communication dans un congrès inria-00346020v1

Tunable parallel experiments in a GridRPC framework: application to linear solvers

Yves Caniou , Jean-Sebastien Gay , Pierre Ramet
VECPAR'08, 2008, Toulouse, France. pp.46--52
Communication dans un congrès inria-00346611v1

A domain decomposition method applied to the simplified transport equations

Maxime Barrault , Bruno Lathuilière , Pierre Ramet , Jean Roman
IEEE 11th International Conference on Computational Science and Engineering, 2008, Sao Paulo, Brazil. pp.91--97
Communication dans un congrès inria-00346022v1

A domain decomposition method for the resolution of an eigenvalue problem in neutron physics

Maxime Barrault , Bruno Lathuilière , Pierre Ramet , Jean Roman
International Symposium on Iterative Methods in Scientific Computing (IMACS), 2008, Lille, France
Communication dans un congrès inria-00346021v1

A Domain Decomposition Method Applied to Large Eigenvalue Problems in Neutron Physics

Maxime Barrault , Bruno Lathuilière , Pierre Ramet , Jean Roman
PMAA'08, 2008, Neuchatel, Switzerland
Communication dans un congrès inria-00346025v1

Toward an international sparse linear algebra expert system by interconnecting the ITBL computational Grid with the Grid-TLSE platform

Noriyuki Kushida , Yoshio Suzuki , Naoya Teshima , Norihiro Nakajima , Yves Caniou
VECPAR 2008: 8th International Conference High Performance Computing for Computational Science, Jun 2008, Toulouse, France
Communication dans un congrès hal-00689964v1
Image document

Dynamic Scheduling for sparse direct Solver on NUMA architectures

Mathieu Faverge , Pierre Ramet
PARA'08, May 2008, Trondheim, Norway
Communication dans un congrès inria-00344026v1

A NUMA Aware Scheduler for a Parallel Sparse Direct Solver

Mathieu Faverge , Xavier Lacoste , Pierre Ramet
PMAA'08, 2008, Neuchâtel, Switzerland
Communication dans un congrès inria-00344709v1

Improvement of existing solvers for the simulation of MHD instabilities

Olivier Czarny , Pascal Hénon , Pierre Ramet , G. Huysmans
Numerical flow models for controlled fusion, 2007, Porquerolles, France
Communication dans un congrès inria-00346027v1

Partitioning and Blocking Issues for a Parallel Incomplete Factorization

Pascal Hénon , Pierre Ramet , Jean Roman
PARA'06, 2006, Umea, Sweden. pp.929--937
Communication dans un congrès inria-00346624v1

On finding approximate supernodes for an efficient ILU(k) factorization

Pascal Hénon , Pierre Ramet , Jean Roman
PMAA'06, 2006, Rennes, France
Communication dans un congrès inria-00346617v1

Efficient solution technique for low Mach number compressible multiphase problems

Benjamin Braconnier , Boniface Nkonga , Mickael Papin , Pierre Ramet , Mario Ricchiuto
PMAA'06, 2006, Rennes, France
Communication dans un congrès inria-00346608v1

On using an hybrid MPI-Thread programming for the implementation of a parallel sparse direct solver on a network of SMP nodes

Pascal Hénon , Pierre Ramet , Jean Roman
Sixth International Conference on Parallel Processing and Applied Mathematics, Workshop HPC Linear Algebra, 2005, Poznan, Poland. pp.1050--1057
Communication dans un congrès inria-00346610v1

Blocking Issues for an Efficient Parallel Block ILU Preconditioner

Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman
International SIAM Conference On Preconditioning Techniques For Large Sparse Matrix Problems In Scientific And Industrial Applications, 2005, Atlanta, United States
Communication dans un congrès inria-00346621v1

High Performance Complete and Incomplete Factorizations for Very Large Sparse Systems by using Scotch and PaStiX softwares

Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman , Yousef Saad
Eleventh SIAM Conference on Parallel Processing for Scientific Computing, 2004, San Francisco, United States
Communication dans un congrès inria-00346622v1

Using of the High Performance Sparse Solver PaStiX for the Complex Multiscale 3D Simulations performed by the FluidBox Fluid Mechanics Software

Pascal Hénon , Boniface Nkonga , Pierre Ramet , Jean Roman
PMAA'04, 2004, Marseille, France
Communication dans un congrès inria-00346607v1

A Blockwise Algorithm for Parallel Incomplete Cholesky Factorization

Pascal Hénon , Pierre Ramet , Jean Roman
PMAA'04, 2004, Marseille, France
Communication dans un congrès inria-00346616v1

Applying parallel direct solver skills to build robust and highly performant preconditioners

Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman , Yousef Saad
PARA'04, 2004, Copenhagen, Denmark. pp.601--619
Communication dans un congrès inria-00346623v1

Efficient algorithms for direct resolution of large sparse system on clusters of SMP nodes

Pascal Hénon , Pierre Ramet , Jean Roman
SIAM Conference on Applied Linear Algebra, 2003, Williamsburg, United States
Communication dans un congrès inria-00346609v1

Towards High Performance Hybrid Direct-Iterative Solvers for Large Sparse Systems

Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman
International SIAM Conference On Preconditioning Techniques For Large Sparse Matrix Problems In Scientific And Industrial Applications, 2003, Napa Valley, United States
Communication dans un congrès inria-00346620v1

Asymptotically optimal algorithm for Laplace task graphs on heterogeneous platforms

Olivier Beaumont , Pierre Ramet , Jean Roman
Fifth International Conference on Parallel Processing and Applied Mathematics, Workshop HeteroPar, 2003, Czestochowa, Poland. pp.880--887
Communication dans un congrès inria-00346587v1

Modélisation de pipelines hétérogènes

Olivier Beaumont , Vincent Boudet , Frédéric Desprez , Pierre Ramet , Jean Roman
GRID'2002, 2002, Aussois, France
Communication dans un congrès inria-00346586v1

Optimisation de l'occupation mémoire pour un solveur parallèle creux direct hautes performances de type supernodal

Pascal Hénon , Pierre Ramet
RenPar'2002, 2002, Hamamet, Tunisie
Communication dans un congrès inria-00346596v1

Parallel factorization of very large sparse SPD systems on a network of SMP nodes

Pascal Hénon , Pierre Ramet , Jean Roman
PMAA'02, 2002, Neuchatel, Switzerland
Communication dans un congrès inria-00346605v1

PaStiX: Un solveur parallèle direct pour des matrices creuses symétriques définies positives basé sur un ordonnancement statique performant et sur une gestion mémoire efficace

Pascal Hénon , Pierre Ramet
RenPar'2001, 2001, Paris, France
Communication dans un congrès inria-00346595v1

PaStiX: A Parallel Direct Solver for Sparse SPD Matrices based on Efficient Static Scheduling and Memory Managment

Pascal Hénon , Pierre Ramet , Jean Roman
Tenth SIAM Conference on Parallel Processing for Scientific Computing, 2001, Portsmouth, United States
Communication dans un congrès inria-00346598v1

PaStiX: A High-Performance Parallel Direct Solver for Sparse Symmetric Definite Systems

Pascal Hénon , Pierre Ramet , Jean Roman
PMAA'2K, 2000, Neuchatel, Switzerland
Communication dans un congrès inria-00346600v1

Description of the EMILIO Software Processing Chain and Application to Structural Mechanics

David Goudin , Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman
PMAA'2K, 2000, Neuchatel, Switzerland
Communication dans un congrès inria-00346601v1

PaStiX: A Parallel Sparse Direct Solver Based on a Static Scheduling for Mixed 1D/2D Block Distributions

Pascal Hénon , Pierre Ramet , Jean Roman
Irregular'2000 workshop of IPDPS, 2000, Cancun, Mexico. pp.519-525
Communication dans un congrès inria-00346594v1

Algèbre Linéaire Creuse Hautes Performances : Application à la Mécanique des Structures

David Goudin , Pascal Hénon , Francois Pellegrini , Pierre Ramet , Jean Roman
iHPerf'2000, 2000, Aussois, France
Communication dans un congrès inria-00346604v1

A Mapping and Scheduling Algorithm for Parallel Sparse Fan-In Numerical Factorization

Pascal Hénon , Pierre Ramet , Jean Roman
EuroPar'99, 1999, Toulouse, France. pp.1059-1067
Communication dans un congrès inria-00346593v1

Calcul de la suite optimale de taille de paquets pour la factorisation de Cholesky

Pierre Ramet
RenPar'9, 1997, Lausanne, Suisse. pp.111-114
Communication dans un congrès inria-00346581v1

Optimisation des Communications et Régulation de Charge pour la Résolution par Méthode Directe de Grands Systèmes Linéaires Creux

Patrick Amestoy , Frédéric Desprez , Pierre Ramet , Jean Roman
ICaRE'97, 1997, Aussois, France. pp.467-488
Communication dans un congrès inria-00346472v1

Calcul de la taille optimale des paquets pour les algorithmes macro-pipelines

Pierre Ramet
RenPar'8, 1996, Bordeaux, France. pp.21-24
Communication dans un congrès inria-00346477v1

Optimal Grain Size Computation for Pipelined Algorithms

Frédéric Desprez , Pierre Ramet , Jean Roman
Euro-Par'96, 1996, Lyon, France. pp.165-172
Communication dans un congrès inria-00346485v1
Image document

Sparse supernodal solver using block low-rank compression: Design, performance and analysis

Grégoire Pichon , Eric Darve , Mathieu Faverge , Esragul Korkmaz , Pierre Ramet
JOREK development meeting, Nov 2019, Cadarache, France
Document associé à des manifestations scientifiques hal-02326407v1
Image document

Utilisation de la compression low-rank pour réduire la complexité du solveur PaStiX

Grégoire Pichon , Mathieu Faverge , Pierre Ramet , Jean Roman
JCAD 2018 - Journées Calcul et Données, Oct 2018, Lyon, France
Document associé à des manifestations scientifiques hal-01956928v1
Image document

Sparse supernodal solver with low-rank compression for solving the frequency-domain Maxwell equations discretized by a high order HDG method

Grégoire Pichon , Eric Darve , Mathieu Faverge , Stéphane Lanteri , Pierre Ramet
Journées jeunes chercheur-e-s - Résolution de problèmes d’ondes harmoniques de grande taille, Nov 2017, PARIS, France. pp.1-55, 2017
Document associé à des manifestations scientifiques hal-01660653v1

Deflation and augmentation techniques in Krylov linear solvers

Olivier Coulaud , Luc Giraud , Pierre Ramet , Xavier Vasseur
Topping, B.H.V and Ivanyi, P. Developments in Parallel - Distributed - Grid and Cloud Computing for Engineering, Saxe-Coburg Publications, pp.249--275, 2013, 978-1-874672-62-3
Chapitre d'ouvrage hal-00860339v1
Image document

Reaching the Quality of SVD for Low-Rank Compression Through QR Variants

Esragul Korkmaz , Mathieu Faverge , Grégoire Pichon , Pierre Ramet
[Research Report] RR-9476, Inria Bordeaux - Sud Ouest. 2022, pp.43
Rapport hal-03718312v4
Image document

Deciding Non-Compressible Blocks in Sparse Direct Solvers using Incomplete Factorization

Esragul Korkmaz , Mathieu Faverge , Grégoire Pichon , Pierre Ramet
[Research Report] RR-9396, Inria Bordeaux - Sud Ouest. 2021, pp.16
Rapport hal-03152932v2
Image document

Improving mapping for sparse direct solvers: A trade-off between data locality and load balancing

Changjiang Gou , Ali Al Zoobi , Anne Benoit , Mathieu Faverge , Loris Marchal
[Research Report] RR-9328, Inria Rhône-Alpes. 2020, pp.21
Rapport hal-02491495v1
Image document

A hierarchical fast direct solver for distributed memory machines with manycore nodes

Cédric Augonnet , David Goudin , Matthieu Kuhn , Xavier Lacoste , Raymond Namyst
[Research Report] CEA/DAM; Total E&P; Université de Bordeaux. 2019
Rapport cea-02304706v1
Image document

Supernodes ordering to enhance Block Low-Rank compression in sparse direct solvers

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
[Research Report] RR-9238, Inria Bordeaux Sud-Ouest. 2018, pp.1-31
Rapport hal-01961675v1
Image document

Efficient Parallel Solution of the 3D Stationary Boltzmann Transport Equation for Diffusive Problems

Salli Moustafa , François Févotte , Mathieu Faverge , Laurent Plagne , Pierre Ramet
[Research Report] RR-9116, Inria; EDF Lab. 2017, pp.22
Rapport hal-01630208v2
Image document

Sparse Supernodal Solver Using Block Low-Rank Compression

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
[Research Report] RR-9022, Inria Bordeaux Sud-Ouest. 2017, pp.24
Rapport hal-01450732v3
Image document

Sparse Supernodal Solver Using Block Low-Rank Compression: design, performance and analysis

Grégoire Pichon , Eric Darve , Mathieu Faverge , Pierre Ramet , Jean Roman
[Research Report] RR-9130, Inria Bordeaux Sud-Ouest. 2017, pp.1-32
Rapport hal-01660665v1
Image document

Reordering strategy for blocking optimization in sparse linear solvers

Grégoire Pichon , Mathieu Faverge , Pierre Ramet , Jean Roman
[Research Report] RR-8860, Inria Bordeaux Sud-Ouest; LaBRI - Laboratoire Bordelais de Recherche en Informatique; Bordeaux INP; Université de Bordeaux. 2016, pp.26
Rapport hal-01276746v2
Image document

Simul'Elec and PASTIX interface specifications

Maher Alaya , Mathieu Faverge , Xavier Lacoste , Alexandre Péré-Laperne , Jacques Péré-Laperne
[Rapport Technique] RT-0458, INRIA Bordeaux; AlgoTech; INRIA. 2015
Rapport hal-01142204v1
Image document

An improved recursive graph bipartitioning algorithm for well balanced domain decomposition

Astrid Casadei , Pierre Ramet , Jean Roman
[Research Report] RR-8582, INRIA. 2014, pp.29
Rapport hal-01056749v1
Image document

Adaptive mesh refinement for numerical simulation of MHD instabilities in tokamaks: JOREK code

Hocine Sellama , Guido Huijsmans , Pierre Ramet
[Research Report] RR-8635, INRIA Bordeaux; INRIA. 2014, pp.18
Rapport hal-01088094v1
Image document

Taking advantage of hybrid systems for sparse direct solvers via task-based runtimes

Xavier Lacoste , Mathieu Faverge , Pierre Ramet , Samuel Thibault , George Bosilca
[Research Report] RR-8446, INRIA. 2014, pp.25
Rapport hal-00925017v2
Image document

Amélioration du comportement numérique des solveurs en prenant en compte les poids de la matrice lors de la décomposition de domaines

Sébastien Fourestier , François Pellegrini , Pierre Ramet
[Rapport Technique] RT-0445, INRIA. 2014, pp.58
Rapport hal-00967676v1
Image document

Deflation and augmentation techniques in Krylov linear solvers

Olivier Coulaud , Luc Giraud , Pierre Ramet , Xavier Vasseur
[Research Report] RR-8265, INRIA. 2013, 25 p
Rapport hal-00803225v1
Image document

Sparse direct solvers with accelerators over DAG runtimes

Xavier Lacoste , Pierre Ramet , Mathieu Faverge , Yamazaki Ichitaro , Jack Dongarra
[Research Report] RR-7972, INRIA. 2012, pp.11
Rapport hal-00700066v2
Image document

Memory Optimization to Build a Schur Complement in an Hybrid Solver

Astrid Casadei , Pierre Ramet
[Research Report] RR-7971, INRIA. 2012, pp.11
Rapport hal-00700053v2
Image document

Non regression testing for the JOREK code

Guillaume Latu , Marina Becoulet , Guilhem Dif-Pradalier , Virginie Grandgirard , Matthias Hoelzl
[Research Report] RR-8134, INRIA. 2012, pp.17
Rapport hal-00752270v1
Image document

A NUMA Aware Scheduler for a Parallel Sparse Direct Solver

Mathieu Faverge , Xavier Lacoste , Pierre Ramet
[Research Report] RR-7498, INRIA. 2010, pp.22
Rapport inria-00549827v1
Image document

SCILAB to SCILAB// - The Ouragan Project

Frédéric Desprez , Martin Quinson , Frédéric Suter , Eric Fleury , Emmanuel Jeannot
[Research Report] RR-4203, INRIA. 2001
Rapport inria-00072419v1

SCILAB to SCILAB// - The Ouragan Project

Eddy Caron , Serge Chaumette , Sylvain Contassot-Vivier , Frédéric Desprez , Eric Fleury
[Research Report] RR-2001-24, LIP - ENS Lyon. 2001
Rapport hal-01436419v1
Image document

Heterogeneous architectures, Hybrid methods, Hierarchical matrices for Sparse Linear Solvers

Pierre Ramet
Distributed, Parallel, and Cluster Computing [cs.DC]. Université de Bordeaux, 2017
HDR tel-01668740v2