SOC-based data reuse convolutional neural network accelerator

A convolutional neural network and data multiplexing technology, applied in the field of convolutional neural networks for embedded devices, can solve problems such as low computing efficiency, time delay and power consumption waste, and achieve state machine simplification, area overhead and power consumption Small, the effect of improving computing efficiency

Active Publication Date: 2018-06-15
BEIJING MXTRONICS CORP +1
View PDF1 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The problem to be solved by the technology of the present invention is: to overcome the shortcomings of the existing convolutional neural network, such as low operational efficiency and the time delay and waste of power consumption caused by a large number of accesses t...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • SOC-based data reuse convolutional neural network accelerator
  • SOC-based data reuse convolutional neural network accelerator
  • SOC-based data reuse convolutional neural network accelerator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0094] The computational load of the convolutional neural network mainly includes image input, weight parameters and bias parameters of the convolutional neural network model itself. The feature of image input is that the two dimensions of the two-dimensional plane direction are relatively large, ranging from 1 to 107, and as the number of layers of the convolutional neural network deepens, the number of channels gradually increases, from 3 to 512; the weight parameter is generally Convolution kernel data, the two-dimensional plane direction dimensions are 7×7, 5×5, 3×3, 1×1, and the number of channels is 3 to 512; there is only one bias parameter for each channel, so each layer parameter is only 3 to 512 512. In view of these characteristics, the present invention stores different data separately, and adopts a block method, that is, group and store image input and weight parameters with large dimensions in the two-dimensional plane direction, and divide image storage and weig...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an SOC-based data reuse convolutional neural network accelerator. Input data of image input, weight parameters, offset parameters and the like of a convolutional neural networkis grouped; a large amount of the input data is classified into reusable block data; and reusable data blocks are read through a control state machine. The convolutional neural network has large parameter quantity and requires strong calculation capability, so that the convolutional neural network accelerator needs to provide very large data bandwidth and calculation capability. A large load is subjected to reusable segmentation, and data reuse is realized through a control unit and an address generation unit, so that the calculation delay and the required bandwidth of the convolutional neuralnetwork are shortened and reduced, and the calculation efficiency is improved.

Description

technical field [0001] The invention relates to a SOC-based data multiplexing convolutional neural network accelerator, in particular to the convolutional neural network for embedded devices, and belongs to the field of embedded applications. Background technique [0002] With the continuous development and optimization of convolutional neural network CNN (Convolutional Neural Network), it has been widely used in the field of pattern recognition, including image recognition, target recognition, image segmentation, target tracking and other fields, and has achieved remarkable results. Shows the dominance of convolutional neural networks in pattern recognition algorithms. [0003] However, deep convolutional neural networks consume a lot of computing resources and storage resources, and cannot be directly applied to the embedded side. Convolutional neural network AlexNet for image recognition, convolution and fully connected operations include a total of 1.45G operations, and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/04G06T1/60
CPCG06T1/60G06N3/045
Inventor 秦智勇陈雷于立新庄伟彭和平倪玮琳张世远
Owner BEIJING MXTRONICS CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap