Dependency-based parallel computing method for intensive data

A data-intensive, dependent technology, applied in the field of parallel systems, can solve problems such as complex data dependencies, and achieve the effect of improving processing efficiency

Active Publication Date: 2014-03-19
广州粤政网络信息科技有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Digital terrain analysis mainly realizes parallel design by splitting data and tasks, and there are complex data dependencies

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
  • Dependency-based parallel computing method for intensive data
  • Dependency-based parallel computing method for intensive data
  • Dependency-based parallel computing method for intensive data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be described in detail below in conjunction with the accompanying drawings. It should be pointed out that the described embodiments are only considered for the purpose of illustration rather than limitation of the invention.

[0058] Embodiments of the present invention provide a data-intensive and dependent parallel computing method, comprising the following steps:

[0059] 1. Data partition determination method for parallel computing modeling

[0060] Step 101: importing data; for parallel computing modeling with data-intensive features, usually the data is effectively divided, and then each block is calculated separately, and finally the results are fused;

[0061] Step 102: Select a data partitioning method according to the characteristics of the processed data: common data partitioning methods include strip partitioning and block partitioning, where strip partitioning is divided into row partitioning and column partitioning, and block pa...

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 technical field of parallel systems, and relates to quantitative study of data partitioning and parallel scheduling strategies, in particular to a dependency-based parallel computing method for intensive data. The dependency-based parallel computing method for the intensive data comprises the steps that a partitioning method of the intensive data is determined; parallel computing modeling is conducted on the intensive data, and a corresponding parallelization strategy is provided; strategy scheduling is conduced based on the parallel computing modeling and the parallelization strategy. The dependency-based parallel computing method for the intensive data can completely be applied to high-performance computing occasions of parallel digital terrain analysis of large-scale mass data, such as extraction of terrain factors which relate to regular grid parallel interpolation, gradient and exposure parallel computing, depression filling-up parallel computing, analysis of terrain within a visible range and the like. The dependency-based parallel computing method for intensive data can also be applied to high-performance computing of geographic information processing and occasions such as space decision analysis and data mining which are based on geographic information. Processing efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of parallel systems, relates to quantitative research on data division and parallel scheduling strategies, and particularly proposes using a data dependency graph to establish a data relationship model and quantification method and a parallel computing method based on the data model. Background technique [0002] Parallel digital terrain analysis is an organic combination of parallel computing and geography. Parallel computing is one of the important research contents in computer science. It was originally used to solve numerical or non-numerical calculation problems, mainly for scientific calculations with large amounts of data. Digital Terrain Analysis (DTA) is a digital information processing technology for terrain attribute calculation and feature extraction based on Digital Elevation Model (DEM). [0003] With the update of various sensors and measurement technologies, the scale of DEM data increases, ...

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): G06F9/48G06F9/50G06F17/30
Inventor 窦万峰李岩
Owner 广州粤政网络信息科技有限公司
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