A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things

07/08/2017
by   Li Du, et al.
0

Convolutional neural network (CNN) offers significant accuracy in image detection. To implement image detection using CNN in the internet of things (IoT) devices, a streaming hardware accelerator is proposed. The proposed accelerator optimizes the energy efficiency by avoiding unnecessary data movement. With unique filter decomposition technique, the accelerator can support arbitrary convolution window size. In addition, max pooling function can be computed in parallel with convolution by using separate pooling unit, thus achieving throughput improvement. A prototype accelerator was implemented in TSMC 65nm technology with a core size of 5mm2. The accelerator can support major CNNs and achieve 152GOPS peak throughput and 434GOPS/W energy efficiency at 350mW, making it a promising hardware accelerator for intelligent IoT devices.

READ FULL TEXT

page 8

page 9

research
09/15/2017

A Streaming Accelerator for Deep Convolutional Neural Networks with Image and Feature Decomposition for Resource-limited System Applications

Deep convolutional neural networks (CNN) are widely used in modern artif...
research
05/22/2017

A Low-Power Accelerator for Deep Neural Networks with Enlarged Near-Zero Sparsity

It remains a challenge to run Deep Learning in devices with stringent po...
research
10/12/2021

Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression

Existing deep convolutional neural networks (CNNs) generate massive inte...
research
05/12/2020

ChewBaccaNN: A Flexible 223 TOPS/W BNN Accelerator

Binary Neural Networks enable smart IoT devices, as they significantly r...
research
05/20/2019

A Bi-Directional Co-Design Approach to Enable Deep Learning on IoT Devices

Developing deep learning models for resource-constrained Internet-of-Thi...
research
12/23/2021

Batch Processing and Data Streaming Fourier-based Convolutional Neural Network Accelerator

Decision-making by artificial neural networks with minimal latency is pa...
research
08/08/2017

Snowflake: A Model Agnostic Accelerator for Deep Convolutional Neural Networks

Deep convolutional neural networks (CNNs) are the deep learning model of...

Please sign up or login with your details

Forgot password? Click here to reset