Explore projects

The Massively Parallel Hybrid Solver (Maphys) aims at solving large sparse linear systems using hybrid direct/iterative methods.

Parallel Algebraic Domain Decomposition for Linear systEms (Paddle)

The C++ Patate Library provides tools to represent, characterize and analyze data commonly used in Computer Graphics through dedicated modules: geometry, light sources, materials.

Dense linear algebra subroutines for heterogeneous and distributed architectures

Perfect SImulator for Markov chains

isogeometric solver for PDE systems

Post-mortem analysis tool for StarPU scheduling studies

Dense linear algebra subroutines for heterogeneous and distributed architectures

Collection of CMake modules that can be shared among projects

Dinero IV, originally downloaded from ftp://ftp.cs.wisc.edu/markhill/DineroIV.

Collection of CMake modules that can be shared among projects

This project aims at providing a set of tools to generate efficient trees for the tile QR/LQ algorithms in order to reduce the volume of communications and increase the level of parallelism of those algorithm for Tall and skinny matrices.

Flexible and extensible framework that integrates state-of-the-art methods for graph partitioning and sparse matrix ordering.

Dense linear algebra subroutines for heterogeneous and distributed architectures