Multi-GPU (Graphics Processing Unit) parallel finite-difference time domain electromagnetic simulation method, equipment and medium

A finite difference in time domain and electromagnetic simulation technology, which is applied in design optimization/simulation, resource allocation, multi-programming devices, etc., can solve problems such as long computing time, large memory consumption, and low computing efficiency, and achieve computing performance improvement, The effect of saving calculation time and improving simulation speed

Active Publication Date: 2022-03-01
ZWCAD SOFTWARE CO LTD
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of the prior art, one of the purposes of the present invention is to provide a multi-GPU parallel finite difference time-domain electromagnetic simulation method, which can effectively solve the problem of large memory consumption in the process of solving electromagnetic FDTD algorithms for large-scale simulation cases. , low calculation efficiency, long calculation time, etc.

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
  • Multi-GPU (Graphics Processing Unit) parallel finite-difference time domain electromagnetic simulation method, equipment and medium
  • Multi-GPU (Graphics Processing Unit) parallel finite-difference time domain electromagnetic simulation method, equipment and medium
  • Multi-GPU (Graphics Processing Unit) parallel finite-difference time domain electromagnetic simulation method, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045]This embodiment provides a multi-GPU parallel finite difference time-domain electromagnetic simulation method, which can effectively solve the problems of large memory consumption, low calculation efficiency, and long calculation time in the process of solving electromagnetic FDTD algorithms for large-scale simulation cases; at the same time , in the calculation process of a variety of boundary conditions, excitations, dispersive media and other cases, it can effectively solve the problems of the traditional FDTD algorithm in the multi-GPU calculation of poor versatility or low parallel performance.

[0046] refer to figure 1 As shown, the simulation method of this embodiment specifically includes the following steps:

[0047] Step S1: Solution area grid division and coefficient calculation

[0048] This embodiment performs Yee grid division for the input three-dimensional electromagnetic model, such as figure 2 As shown, the number of grids corresponding to the three...

Embodiment 2

[0104] This embodiment provides a multi-GPU parallel finite-difference time-domain electromagnetic simulation system, which executes the multi-GPU parallel finite-difference time-domain electromagnetic simulation method as described in Embodiment 1, including:

[0105] The regional decomposition module is used to decompose the spatial grid according to the preset GPU parallel number, so that adjacent sub-domains after decomposition contain the same overlapping grid; Divided to obtain;

[0106] The data update module is used to match the regional parameters of its corresponding sub-domain for each GPU, and control each GPU to combine the regional parameters to perform electromagnetic field data update on the overlapping grid corresponding to its sub-domain and the area other than the overlapping grid. iterative operation;

[0107] The result storage module is used for data storage of the iterative calculation results of the electromagnetic field data.

[0108] In addition, th...

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 multi-GPU parallel time domain finite difference electromagnetic simulation method and system. The simulation method comprises the following steps: performing regional decomposition on a space grid according to a preset GPU parallel number, so that adjacent sub-domains after decomposition contain the same overlapped grid; the space grid is obtained by performing Yee grid division on a three-dimensional electromagnetic model; and matching the regional parameters of the corresponding sub-domains for each GPU, controlling each GPU to carry out iterative operation of the electromagnetic field data on the overlapped grids corresponding to the sub-domains and the regions outside the overlapped grids by combining the regional parameters, and carrying out data storage on an electromagnetic field data iterative operation result. According to the method, the problems of high memory consumption, low calculation efficiency, long calculation time and the like in the process of solving an electrically large simulation case by an electromagnetic FDTD algorithm can be effectively solved.

Description

technical field [0001] The invention relates to the fields of electromagnetic simulation analysis and high-performance computing, in particular to a multi-GPU parallel time domain finite difference electromagnetic simulation method, electronic equipment and a computer-readable storage medium. Background technique [0002] CAE electromagnetic simulation is widely used in mobile phones, computers, automobiles, electronic components, aerospace, medical equipment and other industries. Finite-Difference Time-Domain (FDTD) is a commonly used electromagnetic simulation method. It is a numerical method based on the concept of finite difference and is used to solve the electric field and magnetic field distribution of Maxwell's equations in the time and space domains. FDTD adopts the explicit leap-frog format in the time step and space point, and adopts the discrete method of alternate sampling in space and time for the E and H components of the electromagnetic field. Using this disc...

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): G06F30/23G06F9/50
CPCG06F30/23G06F9/5027
Inventor 聂雅琴张军飞李会江彭超彬
Owner ZWCAD SOFTWARE CO LTD
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