Mapping method applied to network-on-chip IP core mapping problem

A mapping method and network-on-chip technology, applied in the field of network-on-chip design and application, can solve problems such as insufficient premature convergence, achieve the effect of avoiding premature convergence, improving the ability of premature convergence, and improving quality

Pending Publication Date: 2022-01-28
SUN YAT SEN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of insufficient premature convergence in the above existing genetic algorithm, the present invention provides a mapping method applied to the IP core mapping problem of the network on chip

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
  • Mapping method applied to network-on-chip IP core mapping problem
  • Mapping method applied to network-on-chip IP core mapping problem
  • Mapping method applied to network-on-chip IP core mapping problem

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] like figure 1 As shown, a mapping method applied to the network-on-chip IP core problem, this embodiment will be illustrated by applying the mapping method to solve the IP core mapping problem of 2Dmesh's communication power consumption awareness, and the entire solution includes the following steps:

[0060] S1: In the genetic algorithm, the chromosome of the individual is used as a feasible solution to mark, where each value m i Represents a gene in a chromosome and indicates the IP core Placed at NoC node r i , A represents the total number of IP cores, and A=4 is set in this embodiment. individual fitness The corresponding negative communication power consumption is evaluated. Then, the lower the fitness of the chromosome, the higher the corresponding communication power consumption. In this embodiment, a genetic algorithm is used to solve the IP core mapping problem.

[0061] S2: Randomly generate an initialization population, and initialize the learnable m...

Embodiment 2

[0106] A computer system includes a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the steps of the method are as follows:

[0107] S1: In the genetic algorithm, the chromosome of the individual is used as a feasible solution to mark, where each value m i Represents a gene in a chromosome and indicates the IP core Placed at NoC node r i , A represents the total number of IP cores;

[0108] S2: Randomly generate an initialization population, and initialize the learnable model as a pre-trained model parameter, and the learnable model estimates the probability distribution of the optimal solution in the entire solution space according to the prior knowledge obtained from the pre-training;

[0109] S3: Perform population iteration on the population initialized in step S2 sequentially through intelligent evolution, biological evolution, and learning modes, and repeat iterative ev...

Embodiment 3

[0111] A computer device, comprising a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the steps of the method are as follows:

[0112] S1: In the genetic algorithm, the chromosome of the individual is used as a feasible solution to mark, where each value m i Represents a gene in a chromosome and indicates the IP core Placed at NoC node r i , A represents the total number of IP cores;

[0113] S2: Randomly generate an initialization population, and initialize the learnable model as a pre-trained model parameter, and the learnable model estimates the probability distribution of the optimal solution in the entire solution space according to the prior knowledge obtained from the pre-training;

[0114]S3: Perform population iteration on the population initialized in step S2 sequentially through intelligent evolution, biological evolution, and learning modes, and repeat iterative ...

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 mapping method applied to a network-on-chip IP core problem, and the method comprises the following steps: S1, marking the chromosome of an individual with a feasible solution in a genetic algorithm; S2, randomly generating an initialized population, and initializing a learnable model into pre-trained model parameters, wherein the learnable model estimates probability distribution of an optimal solution in the whole solution space according to priori knowledge obtained through pre-training; and S3, performing population iteration on the population initialized in the step S2 through intelligent evolution, biological evolution and a learning mode in sequence, and repeating iterative evolution until the maximum number of iterations is reached. The IP core mapping problem is solved by comprehensively utilizing the advantages of the learnable model and the genetic algorithm, the premature convergence avoiding capability of the genetic algorithm is improved, and the quality of the mapping solution is further improved.

Description

technical field [0001] The present invention relates to the technical field of network-on-chip (Network-on-Chip, NoC) IP core mapping. Background technique [0002] With the development of semiconductor technology, the network on chip gradually replaces the traditional communication architecture (such as bus and switch) and becomes the preferred on-chip communication architecture on the System-on-Chip (SoC), providing better scalability and lower cost. transmit power consumption and greater throughput. The network on chip draws lessons from the design ideas of parallel computing and computer network, and different IPs are connected to different on-chip routers. As the number of IP cores connected to the NoC increases, the connection of the IP cores to different routers greatly affects the performance of the NoC design. Therefore, the IP core mapping problem is a key issue in the design of the network on a chip. [0003] IP core mapping refers to assigning IP cores to NoC ...

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): G06N3/063G06N3/04G06N3/08G06N3/12
CPCG06N3/063G06N3/08G06N3/126G06N3/047G06N3/044
Inventor 黄以华陈清坤
Owner SUN YAT SEN 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