Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A task processing method based on a neural network and related equipment

A neural network and task processing technology, applied in the field of neural network-based task processing methods and related equipment, can solve problems such as low computing efficiency, achieve the effects of covering time-consuming, improving operating efficiency, and solving low computing efficiency

Active Publication Date: 2019-03-01
BIGO TECH PTE LTD
View PDF14 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a neural network-based task processing method and related equipment to improve the acceleration ratio and solve the technical problem of low computational efficiency of neural network-related applications on multi-core processors in the prior art

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
  • A task processing method based on a neural network and related equipment
  • A task processing method based on a neural network and related equipment
  • A task processing method based on a neural network and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

[0031] When implementing the present invention, the inventors found that the computing tasks in the neural network are performed sequentially, that is, the data input into the neural network is sequentially processed by different layers of the neural network to obtain the final output result. In the prior art, multi-core processor capabilities are often used to accelerate task processing of neural network-related applications. Specifically, for applications that do not need to be executed synchronously, such as fa...

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 embodiment of the invention discloses a task processing method based on a neural network and related equipment, which relates to the technical field of a computer network. The method comprises thefollowing steps: obtaining input data, wherein, the input data is used for triggering a thread task, and the input data is source input data or cache exchange data; according to the triggered at least two thread tasks, the corresponding at least two module threads are dispatched in parallel to process the input data and generate the processing result data. At least two module thread correspond toat least two network modules divide according to that network layer in the neural network; Output the processing result data to the cache as cache swap data for other module threads or output the processing result data as a processing result for the source input data. The embodiment of the invention assigns tasks of different network modules in the neural network to different module threads for parallel execution, and improves the operation efficiency of the neural network related application on the multi-core processor.

Description

technical field [0001] The invention relates to the technical field of computer networks, in particular to a neural network-based task processing method and related equipment. Background technique [0002] With the rapid development of artificial intelligence technology, machine learning methods represented by deep neural networks have achieved practical applications in fields such as computer vision and speech recognition, and have become research hotspots. [0003] When actually deploying neural network-based applications, not only the computing overhead of the network itself, but also the overall delay and throughput control of the application must be considered. At present, in practical applications, especially real-time applications deployed on mobile terminals, multi-core processors are usually used to accelerate the calculation of each layer in the neural network, that is, to distribute the calculation tasks of each network layer in the neural network to multiple Pro...

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): G06N3/063
CPCG06N3/063G06N3/08G06F9/4881G06N3/045G06F9/485G06N3/082
Inventor 熊祎易松松
Owner BIGO TECH PTE LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com