Vers la simulation numérique pétaflopique sur architectures parallèles hybrides

6 au 10 juin 2011
INRIA
Sophia Antipolis, France

Slides - Présentations

Emmanuel Agullo- Julien Langou
INRIA Bordeaux – Sud-Ouest

Title:Designing a QR factorization for Multicore and multi-GPU architectures using runtime systems

François Bodin
CAPS entreprise

Title:Heterogeneous Architecture Programming

Denis Caromel
INRIA - ActiveEon


Title: ProActive Hybrid Workflows with CPUs and GPUs

Jack Dongarra
University of Tennessee


Title: The Past, Present and Future of HPC

Florent Duchaine
CERFACS


Title: Large Eddy Simulation and Muti-physics for Engine computations on Massively Parallel Machines

Luigi Genovese
CEA/INAC/SP2M
Laboratoire de Simulation Atomistique

Title:Wavelet-Based DFT calculations on Massively Parallel Hybrid Architectures

Judith Gimenez
Barcelona Supercomputing center

Title:Methods for performance evaluation and optimization on modern HPC systems

Dominik Goeddeke
Institute of Applied Mathematics, TU Dortmund, Germany.

Title:Finte element methods on GPU systems

Michael Heroux
Sandia National Labs.

Title:Toward Portable Programming of Numerical Linear Algebra on Manycore Nodes

Manfred Liebmann
Karl-Franzens-University Graz


Title:Algebraic Multigrid Methods on GPU-Accelerated Hybrid Architectures

Raymond Namyst
Equipe RUNTIME, INRIA Bordeaux - Sud–Ouest

Title:Programming heterogeneous, accelerator-based multicore machines: a runtime system's perspective

Enrique S. Quintana Ortí
Universidad Jaime I

Title:Easy programming of Linear Algebra Operations on Hybrid CPU-GPU Platforms

Robert Strzodka
Max Planck Institut Informatik et Stanford University

Title: Finte element methods on GPU systems

Marc Tajchman
CEA

Title:Programming paradigms using PGAS-based languages

Tim Warburton
Rice University

Title:GPU Accelerated Discontinuous Galerkin Methods

Felix Wolf
German Research School for Simulation Sciences

Title:Methods for performance evaluation and optimization on modern HPC systems