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

Reduction method applied to realization of parallel data competition in particle simulation

A data competition and data technology, which is used in concurrent instruction execution, electrical digital data processing, special data processing applications, etc., can solve the problems that the reduction algorithm cannot be directly processed, the impact of multi-grid data competition in the data set, etc., and achieves the degree of parallelism. boosted effect

Active Publication Date: 2018-02-16
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] In view of the above problems or deficiencies, in order to solve the problem that the existing reduction algorithm cannot directly deal with the data competition of multi-grid points in the data set and the problem that the data preprocessing will greatly affect the performance of the program, the present invention provides a method for solving particle A Reduction Method for Simulating Parallel Data Races

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
  • Reduction method applied to realization of parallel data competition in particle simulation
  • Reduction method applied to realization of parallel data competition in particle simulation
  • Reduction method applied to realization of parallel data competition in particle simulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0041] In the example, the current source solution model in the particle simulation is used, and the 10 grid points are numbered from 0 to 9 in the comparative test. There are 500 macro electrons around each grid point (the atomic operation ratio is 500:1), and each electron acts on it The grid points of are assigned a current with a size of 1, and the ultimate goal is to find out the current size of each grid point.

[0042] The specific implementation steps are as follows:

[0043] Step 1. When solving the current source, each thread calculates the current distribution of an electron, and stores the distributed current with grid attributes and current size into the array to be sorted (set as array 1, such as Figure 9 ), the current value assigned to each electron is 1.

[0044] Step 2. Use the odd-even sorting method to sort the array 1, so...

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 belongs to the field of a particle simulation parallel technology, and particularly relates to a reduction method applied to the realization of parallel data competition in particle simulation. By adopting the reduction method, the parallelism of data competition parts in the particle simulation is realized; each thread selects three pieces of constant data to perform processing andconstantly outputs two pieces of data to serve as return values; the problem of data address writing conflicts of different threads does not occur and the data does not need to be subjected to separation preprocessing; and the problem of data writing conflicts caused by an inconstant output data quantity in original reduction is solved, so that the data competition parts in the particle simulationcan be efficiently and accurately parallelized, and the parallelism degree of a whole particle simulation program is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of parallel particle simulation. Specifically, it relates to a reduction method applied to solving parallel data competition in particle simulation. Background technique [0002] In recent years, the rapid development of computer technology has enabled people to use high-speed, large-capacity computers to simulate complex physical problems, so a new discipline - computational physics has emerged, and one of the prominent applications is the particle simulation method. [0003] The particle simulation method is a method to obtain the macroscopic characteristics and motion laws by tracking the motion of a large number of charged particles in an external and self-consistent electromagnetic field and statistically averaging them. The particle simulation method can not only be used in the study of basic theoretical issues whose physical laws are still unclear, but also in the research and design of practical pla...

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
IPC IPC(8): G06F9/30G06F9/38G06F9/52G06F17/50
CPCG06F9/3001G06F9/3885G06F9/52G06F30/20
Inventor 金晓林刘腾宇李斌杨中海
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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