High energy efficiency and low memory footprint are the key requirements for the deployment of deep learning based analytics on low-power microcontrollers. Here we present work-in-progress results with Q-bit Quantized Neural Networks (QNNs) deployed on a commercial Cortex-M7 class microcontroller by means of an extension to the ARM CMSIS-NN library. We show that i) for Q=4 and Q=2 low memory footprint QNNs can be deployed with an energy overhead of 30% and 36% respectively against the 8-bit CMSIS-NN due to the lack of quantization support in the ISA; ii) for Q=1 native instructions can be used, yielding an energy and latency reduction of ∼3.8× with respect to CMSIS-NN. Our initial results suggest that a small set of QNN-related specialized instructions could improve performance by as much as 7.5× for Q=4, 13.6× for Q=2 and 6.5× for binary NNs.

Work-in-Progress: Quantized NNs as the Definitive solution for inference on low-power ARM MCUs?

Rusci, Manuele
;
Capotondi, Alessandro;Conti, Francesco;Benini, Luca
2018

Abstract

High energy efficiency and low memory footprint are the key requirements for the deployment of deep learning based analytics on low-power microcontrollers. Here we present work-in-progress results with Q-bit Quantized Neural Networks (QNNs) deployed on a commercial Cortex-M7 class microcontroller by means of an extension to the ARM CMSIS-NN library. We show that i) for Q=4 and Q=2 low memory footprint QNNs can be deployed with an energy overhead of 30% and 36% respectively against the 8-bit CMSIS-NN due to the lack of quantization support in the ISA; ii) for Q=1 native instructions can be used, yielding an energy and latency reduction of ∼3.8× with respect to CMSIS-NN. Our initial results suggest that a small set of QNN-related specialized instructions could improve performance by as much as 7.5× for Q=4, 13.6× for Q=2 and 6.5× for binary NNs.
2018 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)
1
2
Rusci, Manuele; Capotondi, Alessandro; Conti, Francesco; Benini, Luca
File in questo prodotto:
File Dimensione Formato  
Binder2.pdf

embargo fino al 09/05/2019

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 418.99 kB
Formato Adobe PDF
418.99 kB Adobe PDF Visualizza/Apri

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/11585/652922
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 0
social impact