International audienceHighly structured sparse matrices arise frequently from numerical discretizations of partial differential equations. Legolas++ is a C++ generic library designed for describing and manipulating such multi-level blocked matrices with the corresponding blocked vectors and algorithms. Legolas++ allows a very detailed description of the linear systems to be solved that can be used to generate efficient parallel implementations. We are working on enlarging the scope of Legolas++ from multi- core target to GPUs and cluster of GPUs
We address some key issues in designing dense linear algebra (DLA) algorithms that are common for bo...
Extended version of EuroGPU symposium article, in the International Conference on Parallel Computing...
Dense linear algebra(DLA) is one of the most seven important kernels in high performance computing. ...
International audienceHighly structured sparse matrices arise frequently from numerical discretizati...
The increasing complexity of new parallel architectures has widened the gap between adaptability and...
The original publication is available at www.springerlink.comInternational audienceA wide class of g...
International audienceThe increasing complexity of new parallel architectures has widened the gap be...
We describe the design of ScaLAPACK++, an object oriented C++ library for implementing linear algebr...
Parallel accelerators are playing an increasingly important role in scientific computing. However, i...
to appearInternational audienceA wide class of numerical methods needs to solve a linear system, whe...
Abstract—Krylov subspace solvers are often the method of choice when solving sparse linear systems i...
We describe the design of ScaLAPACK++, an object oriented C++ library for implementing linear algebr...
The aim of this course is to introduced the basic usages of the ScaLAPACK and MAGMA libraries ScaLA...
We present a new C++ library design for linear algebra computations on high performance architecture...
We propose two high-level application programming interfaces (APIs) to use a graphics processing uni...
We address some key issues in designing dense linear algebra (DLA) algorithms that are common for bo...
Extended version of EuroGPU symposium article, in the International Conference on Parallel Computing...
Dense linear algebra(DLA) is one of the most seven important kernels in high performance computing. ...
International audienceHighly structured sparse matrices arise frequently from numerical discretizati...
The increasing complexity of new parallel architectures has widened the gap between adaptability and...
The original publication is available at www.springerlink.comInternational audienceA wide class of g...
International audienceThe increasing complexity of new parallel architectures has widened the gap be...
We describe the design of ScaLAPACK++, an object oriented C++ library for implementing linear algebr...
Parallel accelerators are playing an increasingly important role in scientific computing. However, i...
to appearInternational audienceA wide class of numerical methods needs to solve a linear system, whe...
Abstract—Krylov subspace solvers are often the method of choice when solving sparse linear systems i...
We describe the design of ScaLAPACK++, an object oriented C++ library for implementing linear algebr...
The aim of this course is to introduced the basic usages of the ScaLAPACK and MAGMA libraries ScaLA...
We present a new C++ library design for linear algebra computations on high performance architecture...
We propose two high-level application programming interfaces (APIs) to use a graphics processing uni...
We address some key issues in designing dense linear algebra (DLA) algorithms that are common for bo...
Extended version of EuroGPU symposium article, in the International Conference on Parallel Computing...
Dense linear algebra(DLA) is one of the most seven important kernels in high performance computing. ...