This report discusses a new algorithm for makespan minimization on situations where the workload can be partitioned among heterogeneous resources. Without making any assumptions regarding the behavior or shape of the functions giving the execution time on a resource, we are able to provide optimal solutions with a dynamic programming algorithm in O(T^2n) for a workload of T tasks and n heterogeneous resources. This report includes a short state of the art, the problem's model, the algorithm, and its optimality proof.Ce rapport discute d'un nouvel algorithme pour la minimisation du makespan dans des situations où la charge de travail peut être partitionnée entre des ressources hétérogènes. Sans faire aucune hypothèse sur le comportement ou l...
International audienceWe consider a natural generalization of classical scheduling problems in which...
Today, computing grids, that are shared and heterogeneous platforms, are ubiquitous. Furthermore, th...
Recent applications, both in industry and research often need massive calculations. They have diffe...
This report discusses a new algorithm for makespan minimization on situations where the workload can...
Les travaux présentés dans cette thèse portent sur l’ordonnancement d’applications multi-tâches liné...
In this document we tackle scheduling problems of multitask linear workflow applications ondistribut...
Nous étudions des stratégies d'ordonnancement et d'équilibrage de charge pour des plates-formes hété...
Aujourd'hui, les plates-formes hétérogènes et partagées que sont les grilles de calcul sont omniprés...
This thesis mainly deals with the mapping and the scheduling of applications on large heteroge- neou...
International audienceThis paper presents an efficient approximation algorithm to solve the task sch...
Membres du jury : Rapporteurs : Henri Casanova, Jean-Jacques Pansiot, Denis Trystram Examinateur : H...
Aujourd'hui, le développement des plates-formes de calcul haute performance (HPC) est considérable, ...
This paper investigates co-scheduling algorithms for processing a set of parallel applications. Inst...
In this paper, we discuss several algorithms for scheduling divisible loads on heterogeneous systems...
International audienceWe propose a model for scheduling jobs in a parallel machine setting that take...
International audienceWe consider a natural generalization of classical scheduling problems in which...
Today, computing grids, that are shared and heterogeneous platforms, are ubiquitous. Furthermore, th...
Recent applications, both in industry and research often need massive calculations. They have diffe...
This report discusses a new algorithm for makespan minimization on situations where the workload can...
Les travaux présentés dans cette thèse portent sur l’ordonnancement d’applications multi-tâches liné...
In this document we tackle scheduling problems of multitask linear workflow applications ondistribut...
Nous étudions des stratégies d'ordonnancement et d'équilibrage de charge pour des plates-formes hété...
Aujourd'hui, les plates-formes hétérogènes et partagées que sont les grilles de calcul sont omniprés...
This thesis mainly deals with the mapping and the scheduling of applications on large heteroge- neou...
International audienceThis paper presents an efficient approximation algorithm to solve the task sch...
Membres du jury : Rapporteurs : Henri Casanova, Jean-Jacques Pansiot, Denis Trystram Examinateur : H...
Aujourd'hui, le développement des plates-formes de calcul haute performance (HPC) est considérable, ...
This paper investigates co-scheduling algorithms for processing a set of parallel applications. Inst...
In this paper, we discuss several algorithms for scheduling divisible loads on heterogeneous systems...
International audienceWe propose a model for scheduling jobs in a parallel machine setting that take...
International audienceWe consider a natural generalization of classical scheduling problems in which...
Today, computing grids, that are shared and heterogeneous platforms, are ubiquitous. Furthermore, th...
Recent applications, both in industry and research often need massive calculations. They have diffe...