Quantization via fixed-point representation is commonly used to reduce the complexity of Convolutional Neural Networks (ConvNets). It is particularly suited for accelerating edge-inference on embedded devices as it enables to reduce resource requirements with no loss of prediction quality. However, porting integer ConvNets on low-end CPUs is not straightforward: it calls for proper software design and organization with a high degree of hardware awareness. Today there are plenty of fixed-point libraries integrated into different inference engines which provide design support. The aim of this work is to review the most stable tools and analyze their performance on different use-cases processed on embedded boards powered by Arm Cortex-A cores. The collected results provide an interesting analysis with useful guidelines for developers and hardware designers.

Integer ConvNets on embedded CPUs: Tools and performance assessment on the cortex-A cores / Peluso, V.; Cipolletta, A.; Vaiana, F.; Calimera, A.. - (2019), pp. 598-601. (Intervento presentato al convegno 26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019 tenutosi a ita nel 2019) [10.1109/ICECS46596.2019.8965168].

Integer ConvNets on embedded CPUs: Tools and performance assessment on the cortex-A cores

Peluso V.;Cipolletta A.;Vaiana F.;Calimera A.
2019

Abstract

Quantization via fixed-point representation is commonly used to reduce the complexity of Convolutional Neural Networks (ConvNets). It is particularly suited for accelerating edge-inference on embedded devices as it enables to reduce resource requirements with no loss of prediction quality. However, porting integer ConvNets on low-end CPUs is not straightforward: it calls for proper software design and organization with a high degree of hardware awareness. Today there are plenty of fixed-point libraries integrated into different inference engines which provide design support. The aim of this work is to review the most stable tools and analyze their performance on different use-cases processed on embedded boards powered by Arm Cortex-A cores. The collected results provide an interesting analysis with useful guidelines for developers and hardware designers.
2019
978-1-7281-0996-1
File in questo prodotto:
File Dimensione Formato  
icecs19.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 215.64 kB
Formato Adobe PDF
215.64 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
ICECS19.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 548.99 kB
Formato Adobe PDF
548.99 kB Adobe PDF Visualizza/Apri
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/11583/2816980