The difficulty of programming distributed memory parallel architectures is an impediment to the exploitation of their potential computational power. Among the different approaches proposed for getting around this difficulty, the data-driven compilation seems promising. The source program, expressed for instance in HPF, is an imperative sequential program in which it is specified how data are distributed amongst the processors; the compiler produces a parallel code from this program according to the data distribution. Implementing this approach requires the development of complete environments. This thesis presents the work carried out in the framework of such an environment, the Pandore environment. Our main concerns are the design and the ...
(eng) This paper focuses on the use of distributed memory multithreaded environments in data paralle...
This paper focuses on the use of distributed memory multithreaded environments in data parallel prog...
International audienceIn this paper, the problem of evaluating the performance of parallel programs ...
The difficulty of programming distributed memory parallel architectures is an impediment to the expl...
International audienceThis paper presents an environment for programming distributed memory computer...
This paper presents an environment for programming distributed memory computers using HPF-like data ...
Scientific and simulation programs often use clusters for their execution. Programmers need new prog...
Les grilles de calculs sont des architectures distribuées couramment utilisées pour l'exécution de p...
Parallelization of programs for distributed memory parallel computers is always difficult because of...
International audienceIn this paper, we present the overall design of Pandore II, an Environment ded...
International audienceIn this paper, we present original techniques for the generation and the effic...
In the data parallel programming style the user usually specifies the data parallelism explicitly so...
International audienceThe paper presents the parallelization process of a wave propagation applicati...
Invited paper. Extended version published in the Parallel Processing Letters, URL: http://hal.inria....
We describe the compilation and execution of data-parallel languages for networks of workstations. E...
(eng) This paper focuses on the use of distributed memory multithreaded environments in data paralle...
This paper focuses on the use of distributed memory multithreaded environments in data parallel prog...
International audienceIn this paper, the problem of evaluating the performance of parallel programs ...
The difficulty of programming distributed memory parallel architectures is an impediment to the expl...
International audienceThis paper presents an environment for programming distributed memory computer...
This paper presents an environment for programming distributed memory computers using HPF-like data ...
Scientific and simulation programs often use clusters for their execution. Programmers need new prog...
Les grilles de calculs sont des architectures distribuées couramment utilisées pour l'exécution de p...
Parallelization of programs for distributed memory parallel computers is always difficult because of...
International audienceIn this paper, we present the overall design of Pandore II, an Environment ded...
International audienceIn this paper, we present original techniques for the generation and the effic...
In the data parallel programming style the user usually specifies the data parallelism explicitly so...
International audienceThe paper presents the parallelization process of a wave propagation applicati...
Invited paper. Extended version published in the Parallel Processing Letters, URL: http://hal.inria....
We describe the compilation and execution of data-parallel languages for networks of workstations. E...
(eng) This paper focuses on the use of distributed memory multithreaded environments in data paralle...
This paper focuses on the use of distributed memory multithreaded environments in data parallel prog...
International audienceIn this paper, the problem of evaluating the performance of parallel programs ...