In this paper, we present the early results of an ongoing project aimed at giving an existing software system a more eco-sustainable lease of life. We defined a strategy and a process for migrating a subject system that performs intensive and massive computation to a Graphics Processing Unit (GPU) based architecture. We validated our solutions on a software system for path finding robot simulations. An initial comparison on the energy consumption of the original system and the greened one has been also executed. The obtained results suggested that the application of our solution produced more eco-sustainable software.
Using the GPU to Green an Intensive and Massive Computation System
SCANNIELLO, GIUSEPPE;ERRA, UGO;CAGGIANESE, GIUSEPPE;
2013-01-01
Abstract
In this paper, we present the early results of an ongoing project aimed at giving an existing software system a more eco-sustainable lease of life. We defined a strategy and a process for migrating a subject system that performs intensive and massive computation to a Graphics Processing Unit (GPU) based architecture. We validated our solutions on a software system for path finding robot simulations. An initial comparison on the energy consumption of the original system and the greened one has been also executed. The obtained results suggested that the application of our solution produced more eco-sustainable software.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
scanniello2013.pdf
accesso aperto
Descrizione: Versione finale pre-print.
Tipologia:
Documento in Pre-print
Licenza:
DRM non definito
Dimensione
664.44 kB
Formato
Adobe PDF
|
664.44 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.