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.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.
https://hdl.handle.net/11583/2816980