An Energy-Efficient Accelerator Architecture with Serial Accumulation Dataflow for Deep CNNs

02/15/2020
by   Mehdi Ahmadi, et al.
0

Convolutional Neural Networks (CNNs) have shown outstanding accuracy for many vision tasks during recent years. When deploying CNNs on portable devices and embedded systems, however, the large number of parameters and computations result in long processing time and low battery life. An important factor in designing CNN hardware accelerators is to efficiently map the convolution computation onto hardware resources. In addition, to save battery life and reduce energy consumption, it is essential to reduce the number of DRAM accesses since DRAM consumes orders of magnitude more energy compared to other operations in hardware. In this paper, we propose an energy-efficient architecture which maximally utilizes its computational units for convolution operations while requiring a low number of DRAM accesses. The implementation results show that the proposed architecture performs one image recognition task using the VGGNet model with a latency of 393 ms and only 251.5 MB of DRAM accesses.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/01/2020

CARLA: A Convolution Accelerator with a Reconfigurable and Low-Energy Architecture

Convolutional Neural Networks (CNNs) have proven to be extremely accurat...
research
10/15/2019

Refresh Triggered Computation: Improving the Energy Efficiency of Convolutional Neural Network Accelerators

Recently, many studies proposed CNN accelerator architectures with custo...
research
10/16/2018

Morph: Flexible Acceleration for 3D CNN-based Video Understanding

The past several years have seen both an explosion in the use of Convolu...
research
03/29/2020

Data-Driven Neuromorphic DRAM-based CNN and RNN Accelerators

The energy consumed by running large deep neural networks (DNNs) on hard...
research
05/26/2021

ATRIA: A Bit-Parallel Stochastic Arithmetic Based Accelerator for In-DRAM CNN Processing

With the rapidly growing use of Convolutional Neural Networks (CNNs) in ...
research
06/13/2021

FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack

Convolutional Neural Networks (CNN) have shown impressive performance in...
research
02/12/2023

AGNI: In-Situ, Iso-Latency Stochastic-to-Binary Number Conversion for In-DRAM Deep Learning

Recent years have seen a rapid increase in research activity in the fiel...

Please sign up or login with your details

Forgot password? Click here to reset