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

Large eddy simulation system and method for realizing cooperative computing based on latticed-Boltzmann theory

A large eddy simulation and lattice technology, applied in the field of large eddy simulation, can solve the problems that single-node processing cannot meet the requirements, and achieve the effects of reducing construction costs and management, simple implementation, and low development costs

Inactive Publication Date: 2014-05-07
INSPUR BEIJING ELECTRONICS INFORMATION IND
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The fast large eddy simulation method using the MIC coprocessor for CPU+MIC collaborative computing in a single node is a very efficient method, but for ultra-large-scale data, the processing of a single node still cannot meet the requirements, so using Based on the LBM method, it is imperative to perform large-eddy simulation with CPU / MIC collaborative calculation on multiple nodes, which can greatly meet the needs of many scientists for processing large-scale data in fluid mechanics

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
  • Large eddy simulation system and method for realizing cooperative computing based on latticed-Boltzmann theory
  • Large eddy simulation system and method for realizing cooperative computing based on latticed-Boltzmann theory
  • Large eddy simulation system and method for realizing cooperative computing based on latticed-Boltzmann theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and preferred embodiments. The following examples are only used to illustrate and explain the present invention, but not to limit the technical solution of the present invention.

[0047] Before realizing the method of the present invention, first use professional tools on a single node to analyze the performance bottleneck test of the large eddy simulation method with lattice Boltzmann, analyze the feasibility of transplanting to the corresponding platform of multiple MIC nodes, and find out the time-consuming problem of realizing large eddy simulation. Hot codes, test the time proportion of these hot codes in the whole process of large eddy simulation, analyze the difficulty of improving the performance of the whole method, and then pass the test results to show that when using the lattice Boltzmann theory to realize the large eddy simulation...

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 large eddy simulation system and a large eddy simulation method for realizing cooperative computing based on a latticed-Boltzmann theory. The system adopts the technical scheme that a master process module broadcasts input data to other process modules in the system and outputs calculation results of all nodes after all the MIC (many integrated core) process modules and all the CPU (central processing unit) process modules finish all computing tasks; the MIC process modules unload the input data to corresponding MICs for computing and perform data communication with the MIC process modules or CPU process modules of the adjacent nodes, and then the next iteration is executed; the CPU process modules control the cooperative computing of the node and start a corresponding thread for each CPU kernel according to the number of kernels of CPUs so as to compute part of distributed data; meanwhile, data communication with the MIC process modules or CPU process modules of the adjacent nodes is executed, and the next iteration is executed. The large eddy simulation system and the large eddy simulation method implement cooperative computing under multiple nodes by using the advantage of reducing the power consumption of the CPUs and the MICs, so that implementation is simple, and the cost is low.

Description

technical field [0001] The invention relates to a large eddy simulation method based on the lattice Boltzmann theory, in particular to a method and a system for performing large eddy simulation based on the lattice Boltzmann theory and using a CPU and MIC cooperative computing mode. Background technique [0002] The Lattice-Boltzmann Method (LBM, Lattice-Boltzmann Method) has been 20 years since its birth. During this period, it has achieved rapid development in both theoretical and applied research, and has gradually become one of the international hotspots in related fields, attracting the attention of many scholars at home and abroad. Unlike traditional simulation methods, the lattice Boltzmann method is based on molecular kinetic theory with a clear physical background. This method is a special discrete form of the Boltzmann equation. It is a discrete method at the macroscopic level, and a continuous method at the microscopic level, so it is called a mesoscopic simulat...

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): G06F15/16G06F9/46
Inventor 卢晓伟张清
Owner INSPUR BEIJING ELECTRONICS INFORMATION IND
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