Given the computational complexity of Recurrent Neural Networks (RNNs) inference, IoT and mobile devices typically offload this task to the cloud. However, the execution time and energy consumption of RNN inference strongly depends on the length of the processed input. Therefore, considering also communication costs, it may be more convenient to process short input sequences locally and only offload long ones to the cloud. In this paper, we propose a low-overhead runtime tool that performs this choice automatically. Results based on real edge and cloud devices show that our method is able to simultaneously reduce the total execution time and energy consumption of the system compared to solutions that run RNN inference fully locally or fully in the cloud.

Input-dependent edge-cloud mapping of recurrent neural networks inference / Jahier Pagliari, D.; Chiaro, R.; Chen, Y.; Vinco, S.; Macii, E.; Poncino, M.. - ELETTRONICO. - 2020:(2020), pp. 1-6. (Intervento presentato al convegno 57th ACM/IEEE Design Automation Conference, DAC 2020 tenutosi a usa nel 2020) [10.1109/DAC18072.2020.9218595].

Input-dependent edge-cloud mapping of recurrent neural networks inference

Jahier Pagliari D.;Chiaro R.;Chen Y.;Vinco S.;Macii E.;Poncino M.
2020

Abstract

Given the computational complexity of Recurrent Neural Networks (RNNs) inference, IoT and mobile devices typically offload this task to the cloud. However, the execution time and energy consumption of RNN inference strongly depends on the length of the processed input. Therefore, considering also communication costs, it may be more convenient to process short input sequences locally and only offload long ones to the cloud. In this paper, we propose a low-overhead runtime tool that performs this choice automatically. Results based on real edge and cloud devices show that our method is able to simultaneously reduce the total execution time and energy consumption of the system compared to solutions that run RNN inference fully locally or fully in the cloud.
2020
978-1-7281-1085-1
File in questo prodotto:
File Dimensione Formato  
pre-print.pdf

accesso aperto

Descrizione: Articolo principale (post-print)
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 5.52 MB
Formato Adobe PDF
5.52 MB Adobe PDF Visualizza/Apri
09218595.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.29 MB
Formato Adobe PDF
1.29 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2850700