CPU/GPU (Central Processing Unit/ Graphic Processing Unit) cooperative processing method oriented to mass data high-performance computation

A high-performance computing and collaborative processing technology, applied in various digital computer combinations, concurrent instruction execution, machine execution devices, etc., can solve the problems of low efficiency in massive data computing and achieve the effect of easy learning

Inactive Publication Date: 2012-10-03
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the defects of the prior art, and to solve the problem of low operation efficiency of massive data calculation in fields such as energy exploration industry data imaging, fast radar im...

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
  • CPU/GPU (Central Processing Unit/ Graphic Processing Unit) cooperative processing method oriented to mass data high-performance computation
  • CPU/GPU (Central Processing Unit/ Graphic Processing Unit) cooperative processing method oriented to mass data high-performance computation
  • CPU/GPU (Central Processing Unit/ Graphic Processing Unit) cooperative processing method oriented to mass data high-performance computation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The specific implementation manners of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0032] A CPU / GPU collaborative processing method for high-performance computing of massive data. The basic principle is: first design a set of JAVA annotation code specifications, and design a new Java bytecode identifiable on the basis of traditional Java class loaders The Java class loader in the annotated part is named GPU Class loader. By building a computer cluster composed of multiple computers, and deploying the improved Hadoop platform in the cluster. A well-designed Java annotation code specification and GPU Classloader are added to the improved platform. A certain version of CUDA is installed on each computing node, so that users can conveniently use GPU computing resources in the Map function of MapReduce through comment codes when writing programs. like figure 2 , image 3 shown.

[0033] The specific...

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 provides a CPU/GPU (Central Processing Unit/ Graphic Processing Unit) cooperative processing method oriented to mass data high-performance computation, which is used for solving the problem of lower operating efficiency of mass data computation. By designing a set of JAVA comment code criterion and building a computer cluster composed of multiple computers, an improved Hadoop platform is arranged in the cluster, and the designed JAVA comment code criterion and a GPU Class loader are added in the improved platform; a CUDA (Compute Unified Device Architecture) of a certain edition is mounted on each computing node, so that the user can conveniently use the CPU computation resource in a Map function of a MapReduce through the commend code when programming. The method realizes unified dispatch and utilization of CPU and GPU computing power on the computer cluster, so that the application having both data-intensive property and computation-intensive property can be realized efficiently, and the programmed source code is transplantable, and convenient for the programmer to develop.

Description

technical field [0001] The invention relates to a method for establishing a CPU / GPU collaborative computing platform, and belongs to the technical field of mass data processing and high-performance computing processing. Background technique [0002] In today's computer field, there are many applications that require massive data processing. Currently, the most widely used massive data processing method is the MapReduce computing model. MapReduce is a programming model proposed by Google to implement distributed parallel computing tasks. It can distribute massive data on large-scale clusters for parallel processing. The MapReduce programming model divides the calculation process into a Map phase and a Reduce phase. The principle is that the data is divided into blocks of a specific size, which are distributed and stored in the cluster in the form of <Key, Value>. Each node in the cluster has some Map and Reduce tasks. The Map task processes the input <Key, Value...

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): G06F15/16G06F9/38
Inventor 翟岩龙刘培志罗壮黄河燕宿红毅郭琨毅
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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