Test Harness on a Preconditioned Conjugate ...
Type de document :
Communication dans un congrès avec actes
URL permanente :
Titre :
Test Harness on a Preconditioned Conjugate Gradient Solver on GPUs: An Efficiency Analysis
Auteur(s) :
Rodrigues, Wendell [Auteur]
Contributions of the Data parallelism to real time [DART]
Chevallier, Loic [Auteur]
Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Le Menach, Yvonnick [Auteur correspondant]
Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Guyomarch, Frédéric [Auteur]
Contributions of the Data parallelism to real time [DART]
Contributions of the Data parallelism to real time [DART]
Chevallier, Loic [Auteur]

Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Le Menach, Yvonnick [Auteur correspondant]

Laboratoire d'Électrotechnique et d'Électronique de Puissance (L2EP) - ULR 2697
Guyomarch, Frédéric [Auteur]

Contributions of the Data parallelism to real time [DART]
Titre de la manifestation scientifique :
CEFC - 2012
Ville :
Oita
Pays :
Japon
Date de début de la manifestation scientifique :
2012-11-11
Titre de la revue :
IEEE Transactions on Magnetics
Date de publication :
2012-11-11
Mot(s)-clé(s) en anglais :
Parallel architectures
Numerical simulation
Gradient methods
Software engineering
Numerical simulation
Gradient methods
Software engineering
Discipline(s) HAL :
Informatique [cs]/Modélisation et simulation
Résumé en anglais : [en]
The parallelization of numerical simulation algorithms, i.e., their adaptation to parallel processing architectures, is an aim to reach in order to hinder exorbitant execution times. The parallelism has been imposed at the ...
Lire la suite >The parallelization of numerical simulation algorithms, i.e., their adaptation to parallel processing architectures, is an aim to reach in order to hinder exorbitant execution times. The parallelism has been imposed at the level of processor architectures and graphics cards are now used for general-purpose calculation, also known as " General-Purpose computation on Graphics Processing Unit (GPGPU) ". The clear benefit is the excellent performance over price ratio. Besides hiding the low level programming, software engineering leads to a faster and more secure application development. This paper presents the real interest of using GPU processors to increase performance of larger problems which concern electrical machines simulation. Indeed, we show that our auto-generated code applied to several models allows achieving speedups of the order of 10 .Lire moins >
Lire la suite >The parallelization of numerical simulation algorithms, i.e., their adaptation to parallel processing architectures, is an aim to reach in order to hinder exorbitant execution times. The parallelism has been imposed at the level of processor architectures and graphics cards are now used for general-purpose calculation, also known as " General-Purpose computation on Graphics Processing Unit (GPGPU) ". The clear benefit is the excellent performance over price ratio. Besides hiding the low level programming, software engineering leads to a faster and more secure application development. This paper presents the real interest of using GPU processors to increase performance of larger problems which concern electrical machines simulation. Indeed, we show that our auto-generated code applied to several models allows achieving speedups of the order of 10 .Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Équipe(s) de recherche :
Équipe Outils et Méthodes Numériques
Date de dépôt :
2020-05-15T14:56:02Z
2022-03-08T18:12:45Z
2022-03-08T18:12:45Z
Fichiers
- document
- Accès libre
- Accéder au document