Un modèle de programmation à grain fin pour la parallélisation de solveurs linéaires creux. (A fine grain model programming for parallelization of sparse linear solver)
نویسنده
چکیده
A fine grain model programming for parallelization of sparse linear solver
منابع مشابه
Algorithmes parallèles à grain adaptatif et applications
RÉSUMÉ. Nous proposons un schéma algorithmique générique original pour contrôler la granularité du parallélisme en cours d’exécution. Ce schéma est basé sur le couplage de deux algorithmes, l’un séquentiel, l’autre parallèle à grain fin. La génération de parallélisme n’est effectuée qu’en cas d’inactivité d’un processeur. Lors de l’exécution sur un nombre restreint ou variable de ressources, ce...
متن کاملSparse approximations of the Schur complement for parallel algebraic hybrid linear solvers in 3D
In this report we study the computational performance of variants of an algebraic additive Schwarz preconditioner for the Schur complement for the solution of large sparse linear systems. In earlier works, the local Schur complements were computed exactly using a sparse direct solver. The robustness of the preconditioner comes at the price of this memory and time intensive computation that is t...
متن کاملCoping with silent errors in HPC applications
This report describes a unified framework for the detection and correction of silent errors, which constitute a major threat for scientific applications at extremescale. We first motivate the problem and explain why checkpointing must be combined with some verification mechanism. Then we introduce a general-purpose technique based upon computational patterns that periodically repeat over time. ...
متن کاملCombining Processor Virtualization and Component-Based Engineering in C for Heterogeneous Many-Core Platforms
Embedded system design is driven by strong efficiency constraints in terms of performance, silicon area and power consumption, as well as pressure on the cost and time-to-market. As of today, this forms three tough problems: 1) many-core systems are becoming mainstream, however there is still no decent approach for distributing software applications on those platforms; 2) these systems still in...
متن کاملFine-grained parallelization of similarity search between protein sequences
This report presents the implementation of a protein sequence comparison algorithm specifically designed for speeding up time consuming part on parallel hardware such as SSE instructions, multicore architectures or graphic boards. Three programs have been developed: PLAST-P, TPLAST-N and PLAST-X. They provide equivalent results compared to the NCBI BLAST family programs (BLAST-P, TBLAST-N and B...
متن کامل