In this paper, we deal with algorithmic issues on heterogeneous platforms. We concentrate on dense linear algebra kernels, such as matrix multiplication or LU decomposition. Block cyclic distribution techniques used in ScaLAPACK are no longer sufficient to balance the load among processors running at different speeds. The main result of this paper is to provide a static data distribution scheme that leads to an asymptotically perfect load balancing for LU decomposition, thereby providing solid foundations toward the design of a cluster-oriented version of ScaLAPACK.Dans ce rapport, nous nous intéressons au problème de la distribution de données pour des noyaux d'algèbre linéaire ( tels que le produit de matrices ou la décomposition LU) adap...
International audienceThis paper adresses static resource allocation problems for irregular distribu...
De nos jours, les applications d'algèbre linéraire sont couramment utilisées pour traiter des problè...
This paper presents and analyzes two different strategies of heterogeneous distribution of computati...
(eng) In this paper, we deal with algorithmic issues on heterogeneous platforms. We concentrate on d...
National audienceIn this paper, we deal with algorithmic issues on heterogeneous platforms. We conce...
This paper discusses some algorithmic issues when computing with a heterogeneous network of workstat...
International audienceThis paper discusses some algorithmic issues when computing with a heterogeneo...
In this paper, we deal with redistribution issues for dense linear algebra kernels on heterogeneous ...
This paper discusses the design and the implementation of the LU factorization routines included in ...
International audienceLarge clusters and supercomputers are rapidly evolving and may be subject to r...
In this paper, we deal with redistribution issues for dense linear algebra kernels on heterogeneous ...
(eng) Implementing linear algebra kernels on distributed memory parallel computers raises the proble...
(eng) We study the implementation of dense linear algebra computations, such as matrix multiplicatio...
This paper presents some works on the LU factorization from the ScaLAPACK library. First, a complexi...
International audienceThis paper adresses static resource allocation problems for irregular distribu...
De nos jours, les applications d'algèbre linéraire sont couramment utilisées pour traiter des problè...
This paper presents and analyzes two different strategies of heterogeneous distribution of computati...
(eng) In this paper, we deal with algorithmic issues on heterogeneous platforms. We concentrate on d...
National audienceIn this paper, we deal with algorithmic issues on heterogeneous platforms. We conce...
This paper discusses some algorithmic issues when computing with a heterogeneous network of workstat...
International audienceThis paper discusses some algorithmic issues when computing with a heterogeneo...
In this paper, we deal with redistribution issues for dense linear algebra kernels on heterogeneous ...
This paper discusses the design and the implementation of the LU factorization routines included in ...
International audienceLarge clusters and supercomputers are rapidly evolving and may be subject to r...
In this paper, we deal with redistribution issues for dense linear algebra kernels on heterogeneous ...
(eng) Implementing linear algebra kernels on distributed memory parallel computers raises the proble...
(eng) We study the implementation of dense linear algebra computations, such as matrix multiplicatio...
This paper presents some works on the LU factorization from the ScaLAPACK library. First, a complexi...
International audienceThis paper adresses static resource allocation problems for irregular distribu...
De nos jours, les applications d'algèbre linéraire sont couramment utilisées pour traiter des problè...
This paper presents and analyzes two different strategies of heterogeneous distribution of computati...