Neural network compiling method and system, and corresponding heterogeneous computing platform

A neural network and computing platform technology, applied in the field of deep learning, can solve problems such as accelerating neural network calculations and failing to meet the performance requirements of deep learning algorithms, and achieve the effect of improving code execution efficiency

Pending Publication Date: 2020-05-05
XILINX INC
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to its calculation-intensive (multiply and add operations required for calculation are on the order of G) and data-intensive (parameters required for calculation are on the order of M to hundreds of Mbytes), the computing platform based on the traditional general-purpose processor CPU does not work well To meet the performance requirements of deep learning algorithms, a large number of heterogeneous platforms for accelerating neural network computing have emerged in recent years

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
  • Neural network compiling method and system, and corresponding heterogeneous computing platform
  • Neural network compiling method and system, and corresponding heterogeneous computing platform
  • Neural network compiling method and system, and corresponding heterogeneous computing platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0038]Artificial intelligence has developed rapidly in recent years, and has achieved good application results in the fields of image classification, detection, video and voice processing, and still has great development prospects. Neural network is the core of artificial intelligence applications, and deep learning neural network algorithm is one of the most common neural network models. The workload of neural networks is characterized by ...

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 discloses a neural network compiling method and a system, and a corresponding heterogeneous computing platform. The method comprises the steps that a trained NN model is acquired; and the trained NN model is input to an NN compiler to generate an NN binary file including graph structure information corresponding to the NN model. Therefore, graph optimization during operation is realized. Furthermore, the graph structure information can be realized as a node resource pool in the NN binary file, together with file headers and free segmentation settings, so that the compiling universality and flexibility for various neural network algorithms can be improved.

Description

technical field [0001] The present invention relates to the field of deep learning, in particular to a compiling method for neural networks, a compiling system and a corresponding heterogeneous computing platform. Background technique [0002] Artificial intelligence has developed rapidly in recent years, and has achieved good application results in the fields of image classification, detection, video and voice processing, and still has great development prospects. Neural network is the core of artificial intelligence applications, and deep learning neural network algorithm is one of the most common neural network models. Due to its calculation-intensive (multiply and add operations required for calculation are on the order of G) and data-intensive (parameters required for calculation are on the order of M to hundreds of Mbytes), the computing platform based on the traditional general-purpose processor CPU does not work well To meet the performance requirements of deep lear...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F8/41G06F8/30G06N3/10
CPCG06F8/447G06F8/37G06N3/10
Inventor 王晓静孙晓明李天平
Owner XILINX INC
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