In this thesis, we propose to study the issues of task parallelism with data dependencies onmulticore architectures with accelerators. We target those architectures with the XKaapiruntime system developed by the MOAIS team (INRIA Rhône-Alpes).We first studied the issues on multi-GPU architectures for asynchronous execution andscheduling. Work stealing with heuristics showed significant performance results, but didnot consider the computing power of different resources. Next, we designed a schedulingframework and a performance model to support scheduling strategies over XKaapi runtime.Finally, we performed experimental evaluations over the Intel Xeon Phi coprocessor innative execution.Our conclusion is twofold. First we concluded that data-f...
Many-Task Computing (MTC) is a common scenario for multiple parallel systems, such as cluster, grids...
International audienceMost recent HPC platforms have heterogeneous nodes com- posed of a combination...
Programmable Graphics Processing Units (GPUs) have recently become the most pervasitheve massively p...
In this thesis, we propose to study the issues of task parallelism with data dependencies onmulticor...
In this thesis, we propose to study the issues of task parallelism with data dependencies on multico...
Programming paradigms in High-Performance Computing have been shifting toward taskbased models that ...
Nos últimos anos, uma das alternativas adotadas para aumentar o desempenho de sistemas de processame...
International audienceMost recent HPC platforms have heterogeneous nodes composed of multi-core CPUs...
The Task Scheduling Paradigm is a general technique for leveraging fine and coarse grain parallelism...
International audienceThis paper presents preliminary performance comparisons of parallel applicatio...
Hybrid computing platforms equipped with accelerators are now commonplace in high performance comput...
International audienceTo fully tap into the potential of heterogeneous machines composed of multicor...
International audienceThe race for Exascale computing has naturally led the current technologies to ...
Heterogeneous platforms had become popular to increase the computational power of the systems within...
Multicore machines equipped with accelerators are becoming increasingly popular in the High Performa...
Many-Task Computing (MTC) is a common scenario for multiple parallel systems, such as cluster, grids...
International audienceMost recent HPC platforms have heterogeneous nodes com- posed of a combination...
Programmable Graphics Processing Units (GPUs) have recently become the most pervasitheve massively p...
In this thesis, we propose to study the issues of task parallelism with data dependencies onmulticor...
In this thesis, we propose to study the issues of task parallelism with data dependencies on multico...
Programming paradigms in High-Performance Computing have been shifting toward taskbased models that ...
Nos últimos anos, uma das alternativas adotadas para aumentar o desempenho de sistemas de processame...
International audienceMost recent HPC platforms have heterogeneous nodes composed of multi-core CPUs...
The Task Scheduling Paradigm is a general technique for leveraging fine and coarse grain parallelism...
International audienceThis paper presents preliminary performance comparisons of parallel applicatio...
Hybrid computing platforms equipped with accelerators are now commonplace in high performance comput...
International audienceTo fully tap into the potential of heterogeneous machines composed of multicor...
International audienceThe race for Exascale computing has naturally led the current technologies to ...
Heterogeneous platforms had become popular to increase the computational power of the systems within...
Multicore machines equipped with accelerators are becoming increasingly popular in the High Performa...
Many-Task Computing (MTC) is a common scenario for multiple parallel systems, such as cluster, grids...
International audienceMost recent HPC platforms have heterogeneous nodes com- posed of a combination...
Programmable Graphics Processing Units (GPUs) have recently become the most pervasitheve massively p...