CoDR: Computation and Data Reuse Aware CNN Accelerator

04/20/2021
by   Alireza Khadem, et al.
0

Computation and Data Reuse is critical for the resource-limited Convolutional Neural Network (CNN) accelerators. This paper presents Universal Computation Reuse to exploit weight sparsity, repetition, and similarity simultaneously in a convolutional layer. Moreover, CoDR decreases the cost of weight memory access by proposing a customized Run-Length Encoding scheme and the number of memory accesses to the intermediate results by introducing an input and output stationary dataflow. Compared to two recent compressed CNN accelerators with the same area of 2.85 mm^2, CoDR decreases SRAM access by 5.08x and 7.99x, and consumes 3.76x and 6.84x less energy.

READ FULL TEXT

page 3

page 4

page 6

research
09/02/2019

SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference

CNNs outperform traditional machine learning algorithms across a wide ra...
research
09/30/2018

Mini-batch Serialization: CNN Training with Inter-layer Data Reuse

Training convolutional neural networks (CNNs) requires intense computati...
research
11/08/2019

Communication Lower Bound in Convolution Accelerators

In current convolutional neural network (CNN) accelerators, communicatio...
research
06/15/2021

ShortcutFusion: From Tensorflow to FPGA-based accelerator with reuse-aware memory allocation for shortcut data

Residual block is a very common component in recent state-of-the art CNN...
research
06/18/2018

Partitioning Compute Units in CNN Acceleration for Statistical Memory Traffic Shaping

The design complexity of CNNs has been steadily increasing to improve ac...
research
04/18/2018

UCNN: Exploiting Computational Reuse in Deep Neural Networks via Weight Repetition

Convolutional Neural Networks (CNNs) have begun to permeate all corners ...
research
09/04/2020

Sparse Systolic Tensor Array for Efficient CNN Hardware Acceleration

Convolutional neural network (CNN) inference on mobile devices demands e...

Please sign up or login with your details

Forgot password? Click here to reset