We study the adaptation of a parallel distributed-memory solver towards a shared-memory code, targeting multi-core architectures. The advantage of adapting the code over a new design is to fully benefit from its numerical kernels, range of functionalities and internal features. Although the studied code is a direct solver for sparse systems of linear equations, the approaches described in this paper are general and could be useful to a wide range of applications. We show how existing parallel algorithms can be adapted to an OpenMP environment while, at the same time, also relying on third-party optimized multithreaded libraries. We propose simple approaches to take advantage of NUMA architectures, and original optimizations to limit thread ...
Recent advances in processor technology have lead to affordable multi-core processors, which could e...
The recent growth in the number of precessing units in today's multicore processor architectures ena...
Modern multicore systems are based on a Non-Uniform Memory Access (NUMA) design. In a NUMA system, c...
La résolution de systèmes d'équations linéaires creux est au cœur de nombreux domaines d'application...
The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems involv...
International audienceThis report presents a study of techniques used to speedup a scientific simula...
International audienceWe introduce shared-memory parallelism in a parallel distributed-memory solver...
Since several years, classical multiprocessor systems have evolved to multicores, which tightly inte...
We consider the solution of very large sparse systems of linear equations on parallel architectures....
MUMPS is a parallel sparse direct solver, using message passing (MPI) for parallelism. In this repor...
NUMA nodes are potentially powerful but taking benefit of their capabilities is challenging due to t...
Performing large, intensive or non-trivial computing on array like datastructures is one of the most...
Performance analysis is the task of monitor the behavior of a program execution. The main goal is to...
En este trabajo se presentan las alternativas y los resultados de rendimiento obtenidos del análisis...
Direct methods for the solution of sparse systems of linear equations are used in a wide range of nu...
Recent advances in processor technology have lead to affordable multi-core processors, which could e...
The recent growth in the number of precessing units in today's multicore processor architectures ena...
Modern multicore systems are based on a Non-Uniform Memory Access (NUMA) design. In a NUMA system, c...
La résolution de systèmes d'équations linéaires creux est au cœur de nombreux domaines d'application...
The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems involv...
International audienceThis report presents a study of techniques used to speedup a scientific simula...
International audienceWe introduce shared-memory parallelism in a parallel distributed-memory solver...
Since several years, classical multiprocessor systems have evolved to multicores, which tightly inte...
We consider the solution of very large sparse systems of linear equations on parallel architectures....
MUMPS is a parallel sparse direct solver, using message passing (MPI) for parallelism. In this repor...
NUMA nodes are potentially powerful but taking benefit of their capabilities is challenging due to t...
Performing large, intensive or non-trivial computing on array like datastructures is one of the most...
Performance analysis is the task of monitor the behavior of a program execution. The main goal is to...
En este trabajo se presentan las alternativas y los resultados de rendimiento obtenidos del análisis...
Direct methods for the solution of sparse systems of linear equations are used in a wide range of nu...
Recent advances in processor technology have lead to affordable multi-core processors, which could e...
The recent growth in the number of precessing units in today's multicore processor architectures ena...
Modern multicore systems are based on a Non-Uniform Memory Access (NUMA) design. In a NUMA system, c...