We first expose in this memoir efficient matrix multiplication techniques. We set up new schedules that allow us to minimize the extra memory requirements during a Winograd-style matrix multiplication, while keeping the complexity competitive. In order to get them, we develop external tools (pebble game), tight complexity computations and new hybrid algorithms. Then we use parallel technologies (multicore CPU and GPU) in order to accelerate efficiently the sparse matrix--dense vector multiplication (SpMV), crucial to /blackbox/ algorithms and we set up new hybrid formats to store them. Finally, we establish generic design methods focusing on efficiency, especially via building block conceptions or self-optimization. We also propose tools fo...
AbstractThe main purpose of this paper is to present a fast matrix multiplication algorithm taken fr...
Parallelism in today's computer architectures is ubiquitous whether it be in supercomputers, worksta...
This Master Thesis examines if a matrix multiplication program that combines the two efficiency stra...
We first expose in this memoir efficient matrix multiplication techniques. We set up new schedules t...
Dans ce mémoire de thèse, nous développons d'abord des multiplications matricielles efficaces. Nous ...
For a few decades, numerical linear algebra has seen intensive developments in both mathematical an...
LinBox is a high-performance generic software library for black box linear algebra over symbolic (ex...
The implementations of matrix multiplication on contemporary, vector-oriented, and multicore-oriente...
We propose different implementations of the sparse matrix–dense vec-tor multiplication (SpMV) for fi...
LinBox is a C++ template library of routines for solution of linear algebra problems including linea...
We describe the design and implementation of two components in the LinBox library. The first is an i...
This "habilitation à diriger des recherches" manuscript concerns the efficiency in exact linear alge...
International audienceWe propose different implementations of the sparse matrix--dense vector multip...
AbstractThe main purpose of this paper is to present a fast matrix multiplication algorithm taken fr...
Parallelism in today's computer architectures is ubiquitous whether it be in supercomputers, worksta...
This Master Thesis examines if a matrix multiplication program that combines the two efficiency stra...
We first expose in this memoir efficient matrix multiplication techniques. We set up new schedules t...
Dans ce mémoire de thèse, nous développons d'abord des multiplications matricielles efficaces. Nous ...
For a few decades, numerical linear algebra has seen intensive developments in both mathematical an...
LinBox is a high-performance generic software library for black box linear algebra over symbolic (ex...
The implementations of matrix multiplication on contemporary, vector-oriented, and multicore-oriente...
We propose different implementations of the sparse matrix–dense vec-tor multiplication (SpMV) for fi...
LinBox is a C++ template library of routines for solution of linear algebra problems including linea...
We describe the design and implementation of two components in the LinBox library. The first is an i...
This "habilitation à diriger des recherches" manuscript concerns the efficiency in exact linear alge...
International audienceWe propose different implementations of the sparse matrix--dense vector multip...
AbstractThe main purpose of this paper is to present a fast matrix multiplication algorithm taken fr...
Parallelism in today's computer architectures is ubiquitous whether it be in supercomputers, worksta...
This Master Thesis examines if a matrix multiplication program that combines the two efficiency stra...