Swarm clustering and swarm routing method for large-scale brain-like computing network

A computing network and large-scale technology, applied in computing, computing models, biological neural network models, etc., can solve problems such as increased memory channel load, large storage burden, and limited reading rate, so as to reduce storage overhead and improve performance , the effect of improving efficiency

Active Publication Date: 2020-12-29
FUDAN UNIV +1
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the growth of the neuron size, the routing entries increase geometrically, which brings a huge storage burden
At the same time, the reading of huge routing entries further increases the load on the memory channel, limiting the reading rate

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
  • Swarm clustering and swarm routing method for large-scale brain-like computing network
  • Swarm clustering and swarm routing method for large-scale brain-like computing network
  • Swarm clustering and swarm routing method for large-scale brain-like computing network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0019] The population clustering method used in the present invention aims to reduce the communication frequency across chips. For the neuron topology of the brain-like computing network, it will show the characteristics of dense short-range connections and sparse and strong long-range connections, which is also learned from the structure of the biological nervous system. The neuron topology in this brain-like computing network is essentially a d...

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 swarm clustering and swarm routing method for a large-scale brain-like computing network, and relates to the technical field of routing. The brain-like computing network is deployed on a plurality of CPUs or GPUs or FPGAs and ASIC chips capable of performing brain-like computing and is composed of neurons and a topological connection relationship among the neurons. The method comprises the steps: dividing the neurons into different swarms, wherein the corresponding neurons in the swarm are closely associated, the corresponding neurons among the swarms are sparsely associated, the neurons in the same swarm are placed on the same chip and share the same routing entry and routing path, and the neurons in different swarms are placed in the same chip or different chips. According to the method, the neurons are reasonably clustered into the swarms, so that the cross-chip communication frequency and the routing storage overhead are effectively reduced, and the systemefficiency is improved.

Description

technical field [0001] The invention relates to the technical field of class routing, in particular to population clustering and population routing methods for large-scale brain-inspired computing networks. Background technique [0002] Brain-like computing aims to create and develop forms of intelligence close to the human brain. By referring to the structure of the brain, learning the intelligence of the brain, and imitating the behavior of the human brain, the machine can have certain reasoning, memory and analysis capabilities when performing brain-like calculations, and finally realize some or all of the functions that the human brain can complete. In the process of developing brain-like computing, it can also help us better understand what gives human intelligence, and even bring about major breakthroughs in strong artificial intelligence or general artificial intelligence. [0003] Neuromorphic computing is an interdisciplinary field of computer science, neuroscience...

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): G06N3/063G06N3/00
CPCG06N3/063G06N3/006Y02D10/00
Inventor 环宇翔邹卓郑立荣丁宸贾浩闫钰龙
Owner FUDAN UNIV
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