We propose a data flow based run time system as an efficient tool for supporting execution of parallel code on heterogeneous architectures hosting both multicore CPUs and GPUs. We discuss how the proposed run time system may be the target of both structured parallel applications developed using algorithmic skeletons/parallel design patterns and also more ???domain specific??? programming models. Experimental results demonstrating the feasibility of the approach are presented.
Targeting heterogeneous architectures via macro data flow
ALDINUCCI, MARCO;
2012-01-01
Abstract
We propose a data flow based run time system as an efficient tool for supporting execution of parallel code on heterogeneous architectures hosting both multicore CPUs and GPUs. We discuss how the proposed run time system may be the target of both structured parallel applications developed using algorithmic skeletons/parallel design patterns and also more ???domain specific??? programming models. Experimental results demonstrating the feasibility of the approach are presented.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
2012_mdf_PPL-hplgpu.pdf
Accesso riservato
Descrizione: editoriale
Tipo di file:
PDF EDITORIALE
Dimensione
601.96 kB
Formato
Adobe PDF
|
601.96 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
2012_mdf_PPL-hplgpu-draft.pdf
Accesso aperto
Descrizione: preprint
Tipo di file:
PREPRINT (PRIMA BOZZA)
Dimensione
481.02 kB
Formato
Adobe PDF
|
481.02 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.