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

Machine learning-oriented distributed computing interconnection network system and communication method

A distributed computing and interconnection network technology, applied in the field of distributed computing interconnection network system and communication, can solve the problems of large network diameter, increase the execution time of machine learning tasks, and lack of self-regulation, so as to improve balance ability, The effect of improving the ability to deal with complex network environments and reducing communication time

Active Publication Date: 2020-05-22
XIDIAN UNIV
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, its shortcomings are: 1. The network diameter of the interconnection network system is large, which increases the execution time of machine learning tasks; 2. The communication method can only complete the transmission of data packets between communication node pairs, and does not have Ability to self-regulate

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
  • Machine learning-oriented distributed computing interconnection network system and communication method
  • Machine learning-oriented distributed computing interconnection network system and communication method
  • Machine learning-oriented distributed computing interconnection network system and communication method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0046] Reference figure 1 , A distributed computing interconnection network system oriented to machine learning, including optical switching subsystems and computing subsystems.

[0047] The optical switching subsystem includes number A 0 , A 1 ,..., A i ,..., A 2N-1 2N optical switches, where N≥1, A i Represents the i-th optical switch. For the convenience of observation and description, in this embodiment N=4, the number of optical switches included in the optical switching subsystem is 8, and the specific number is A 0 , A 1 ,..., A 6 , A 7 , Each optical switch includes N switching ports, that is, each optical switch includes 4 switching ports.

[0048] The computing subsystem includes N computing units, and the number of computing units included in the computing subsystem in this embodiment is 4, and the number of computing units is consistent with ...

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 a machine learning-oriented distributed computing interconnection network system and a communication method. The communication efficiency of an interconnection network is improved, and meanwhile, the flow load in the distributed computing interconnection network can be better balanced. The optical switching subsystem of the distributed computing interconnection network comprises 2N optical switches. The computing subsystem comprises N computing units. Each computing unit comprises N sub-computing units, and each sub-computing unit comprises a photoelectric hybrid switchand N computing nodes. The communication process is as follows: the computing node pairs communicating in the same computing unit can finish a communication task only by forwarding of the photoelectric hybrid switch, and the computing node pairs not communicating in the same computing unit need cooperation of the photoelectric hybrid switch and the optical switch to finish the communication task.According to the invention, the system has good expandability; the network diameter is reduced; the communication time delay of the system is reduced; and the capability of the system for coping witha complex network environment is improved.

Description

Technical field [0001] The present invention belongs to the field of communication technology, and further relates to a machine learning-oriented distributed computing interconnection network system and communication method in the field of interconnection network communication technology. The present invention uses an optical switch, a photoelectric hybrid switch and a computing node to form an interconnection network system. Connect the network system to realize efficient communication between various computing nodes in the distributed computing interconnection network system. Background technique [0002] With the development of computing technology, many emerging applications require huge computing power to complete, especially machine learning applications based on big data and large models. Centralized computing completely relies on the processing power of a large central computer. Contrary to centralized computing, in distributed computing, multiple computing nodes interco...

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): H04Q11/00
CPCH04Q11/0005H04Q2011/0007H04Q2011/0052
Inventor 顾华玺鹿云峰余晓杉王琨任泽昂
Owner XIDIAN UNIV
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