Hybrid scheduling for the parallel solution of linear systems
AMESTOY, Patrick
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
PRALET, Stéphane
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
Leer más >
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
AMESTOY, Patrick
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
PRALET, Stéphane
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
Algorithmes Parallèles et Optimisation [IRIT-APO]
Institut National Polytechnique (Toulouse) [Toulouse INP]
GUERMOUCHE, Abdou
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Algorithms and high performance computing for grand challenge applications [SCALAPPLIX]
< Leer menos
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Algorithms and high performance computing for grand challenge applications [SCALAPPLIX]
Idioma
en
Article de revue
Este ítem está publicado en
Parallel Computing. 2006, vol. 32, n° 2, p. 136-156
Elsevier
Resumen en inglés
We consider the problem of designing a dynamic scheduling strategy that takes into account both workload and memory information in the context of the parallel multifrontal factorization. The originality of our approach is ...Leer más >
We consider the problem of designing a dynamic scheduling strategy that takes into account both workload and memory information in the context of the parallel multifrontal factorization. The originality of our approach is that we base our estimations (work and memory) on a static optimistic scenario during the analysis phase. This scenario is then used during the factorization phase to constrain the dynamic decisions that compute fully irregular partitions in order to better balance the workload. We show that our new scheduling algorithm significantly improves both the memory behaviour and the factorization time. We give experimental results for large challenging real-life 3D problems on 64 and 128 processors.< Leer menos
Orígen
Importado de HalCentros de investigación