This brief introduces Topology Voltage Frequency Scaling (TVFS), a performance management technique for embedded Convolutional Neural Networks (ConvNets) deployed on low-power CPUs. Using TVFS, pre-trained ConvNets can be efficiently processed over a continuous stream of data, enabling reliable and predictable multi-inference tasks under latency constraints. Experimental results, collected from an image classification task built with MobileNet-v1 and ported into an ARM Cortex-A15 core, reveal TVFS holds fast and continuous inference (from few runs, up to 2000), ensuring a limited accuracy loss (from 0.9% to 3.1%), and better thermal profiles (average temperature 16.4 °C below the on-chip critical threshold).

TVFS: Topology Voltage Frequency Scaling for Reliable Embedded ConvNets / Rizzo, Roberto Giorgio; Peluso, Valentino; Calimera, Andrea. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. II, EXPRESS BRIEFS. - ISSN 1549-7747. - 68:2(2021), pp. 672-676. [10.1109/TCSII.2020.3017538]

TVFS: Topology Voltage Frequency Scaling for Reliable Embedded ConvNets

Rizzo, Roberto Giorgio;Peluso, Valentino;Calimera, Andrea
2021

Abstract

This brief introduces Topology Voltage Frequency Scaling (TVFS), a performance management technique for embedded Convolutional Neural Networks (ConvNets) deployed on low-power CPUs. Using TVFS, pre-trained ConvNets can be efficiently processed over a continuous stream of data, enabling reliable and predictable multi-inference tasks under latency constraints. Experimental results, collected from an image classification task built with MobileNet-v1 and ported into an ARM Cortex-A15 core, reveal TVFS holds fast and continuous inference (from few runs, up to 2000), ensuring a limited accuracy loss (from 0.9% to 3.1%), and better thermal profiles (average temperature 16.4 °C below the on-chip critical threshold).
File in questo prodotto:
File Dimensione Formato  
FINAL VERSION.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 928.65 kB
Formato Adobe PDF
928.65 kB Adobe PDF Visualizza/Apri
09170585.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.17 MB
Formato Adobe PDF
1.17 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento 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: http://hdl.handle.net/11583/2851354