Integer ConvNets on embedded CPUs: Tools and performance assessment on the cortex-A cores
| Autor: | Antonio Cipolletta, Andrea Calimera, Valentino Peluso, Francesco Vaiana |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Computer science
Quantization (signal processing) 05 social sciences 010501 environmental sciences 01 natural sciences Porting Convolutional neural network Computer architecture 0502 economics and business Software design 050207 economics Inference engine Design support 0105 earth and related environmental sciences |
| Zdroj: | ICECS |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|