One of the most promising architectures for performing deep neural network inferences on resource-constrained embedded devices is based on massive parallel and specialized cores interconnected by means of a Network-on-Chip (NoC). In this paper, we extensively evaluate NoC-based deep neural network accelerators by exploring the design space spanned by several architectural parameters. We show how latency is mainly dominated by the on-chip communication whereas energy consumption is mainly accounted by memory (both on-chip and off-chip).
Analyzing networks-on-chip based deep neural networks
Ascia G.;Catania V.;Monteleone S.;Palesi M.;Patti D.;
2019-01-01
Abstract
One of the most promising architectures for performing deep neural network inferences on resource-constrained embedded devices is based on massive parallel and specialized cores interconnected by means of a Network-on-Chip (NoC). In this paper, we extensively evaluate NoC-based deep neural network accelerators by exploring the design space spanned by several architectural parameters. We show how latency is mainly dominated by the on-chip communication whereas energy consumption is mainly accounted by memory (both on-chip and off-chip).File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
2019_NOCS2019.pdf
solo gestori archivio
Tipologia:
Versione Editoriale (PDF)
Dimensione
582.97 kB
Formato
Adobe PDF
|
582.97 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.