Team:POSTALE

Team Postale

Members

Overall Objectives

Research Program

Architectures and program optimization
High-level HPC libraries and applications

Highlights of the Year

New Software and Platforms

Boost.SIMD
CovTrack
Dohko
Molly
MyNRC
NT2

New Results

Parallel light speed labeling: the world’s fastest connected component labeling for multicore processors
Opening Polyhedral Compiler's Black Box
Automating Resource Selection and Configuration in Inter-clouds through a Software Product Line Method
A Randomized LU-based Solver Using GPU and Intel Xeon Phi Accelerators
Metaprogramming dense linear algebra solvers. Applications to multi and many-core architectures
Using Random Butterfly Transformations in Parallel Schur Complement-Based Preconditioning
LU Preconditioning for Overdetermined Sparse Least Squares Problems
Dense Symmetric Indefinite Factorization on GPU Accelerated Architectures
Computing least squares condition numbers on hybrid multicore/GPU systems
Towards a High-Performance Tensor Algebra Package for Accelerators

Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry

Partnerships and Cooperations

National Initiatives
International Initiatives
International Research Visitors

Dissemination

Promoting Scientific Activities
Teaching - Supervision - Juries
Popularization

Bibliography

Major publications
Publications of the year
References in notes

Inria | Raweb 2015 | Presentation of the Team POSTALE


	PDF	e-Pub

Previous |

Home | Next next

Section: Highlights of the Year

Highlights of the Year

Marc Baboulin was invited plenary speaker at the HPCSE conference, Solan, Czech Republic, May 25-28, 2015.

The Random Butterfly Transformations developed by Postale are now available in the MAGMA library for GPU (release 1.6) and Intel Xeon Phi (release 1.3).

Marc Baboulin is general vice-chair of the HPC Symposium to be held in April 2016, Pasadena, CA.

Previous |

Home | Next next