BEAUMONT, Olivier; EYRAUD-DUBOIS, Lionel; GUERMOUCHE, Abdou; LAMBERT, Thomas

Métadonnées

Licence d’utilisation du document

BEAUMONT, Olivier
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Reformulations based algorithms for Combinatorial Optimization [Realopt]

EYRAUD-DUBOIS, Lionel
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
Reformulations based algorithms for Combinatorial Optimization [Realopt]

GUERMOUCHE, Abdou
Laboratoire Bordelais de Recherche en Informatique [LaBRI]
High-End Parallel Algorithms for Challenging Numerical Simulations [HiePACS]

Langue

Communication dans un congrès

Ce document a été publié dans

IEEE 27th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2015, IEEE 27th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2015, 26th IEEE International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2015, 2015-10-19, Florianopolis. 2015-10-19

Résumé en anglais

The tremendous increase in the size and heterogeneity of supercomputers makes it very difficult to predict the performance of a scheduling algorithm. In this context, relying on purely static scheduling and resource allocation strategies, that make scheduling and allocation decisions based on the dependency graph and the platform description, is expected to lead to large and unpredictable makespans whenever the behavior of the platform does not match the predictions. For this reason, the common practice in most runtime libraries is to rely on purely dynamic scheduling strategies, that make short-sighted scheduling decisions at runtime based on the estimations of the duration of the different tasks on the different available resources and on the state of the machine. In this paper, we consider the special case of Matrix Multiplication, for which a number of static allocation algorithms to minimize the amount of communications have been proposed. Through a set of extensive simulations, we analyze the behavior of static, dynamic, and hybrid strategies, and we assess the possible benefits of introducing more static knowledge and allocation decisions in runtime libraries.< Réduire

Mots clés en anglais

runtime scheduling

static scheduling

dynamic scheduling

Matrix Multiplication

hybrid strategies

URI

https://oskar-bordeaux.fr/handle/20.500.12278/194292

Project ANR

Solveurs pour architectures hétérogènes utilisant des supports d'exécution - ANR-13-MONU-0007

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251