Task scheduling algorithm for tradeoff optimization of time and energy consumption under heterogeneous parallel system

A task scheduling and execution time technology, applied in energy-saving computing, computing, multi-program devices, etc., can solve problems such as complex task scheduling, and achieve the effect of high weighted performance

Active Publication Date: 2016-08-10
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, many studies assume that tasks are independent, and the task model is more complicated for task-dependent task scheduling, which is not applicable to this situation

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
  • Task scheduling algorithm for tradeoff optimization of time and energy consumption under heterogeneous parallel system
  • Task scheduling algorithm for tradeoff optimization of time and energy consumption under heterogeneous parallel system
  • Task scheduling algorithm for tradeoff optimization of time and energy consumption under heterogeneous parallel system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0012] Such as figure 1 As shown, the present invention provides a task scheduling algorithm based on the importance ratio of time-energy consumption, including determination of task sequence, initial assignment of tasks, and re-optimization of assignment. We simulate the heterogeneous parallel system as a set PR={PR 1 ,PR 2 ,...,PR p}, PR j is the jth processor, and the jth processor has m j voltage level; each application program can be divided into n atomic parallel tasks with dependencies, we simulate this group of parallel tasks as a task set V={v 1 ,v 2 ,...,v n}. The present invention specifically ...

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 parallel task scheduling algorithm based on the significance proportion of time and energy consumption to realize tradeoff optimization of the time and the energy consumption which are used by a task under a heterogeneous parallel system when double restrictions of the time and the energy consumption are met. The algorithm considers that the task in the actual condition is affected by various factors, the execution time is not fixed and determined and is approximate to normal distribution, so that when the task scheduling order is determined, the method for utilizing a mean value of the execution time in the prior art is not adopted, but the mean value and the variance of the execution time are simultaneously considered to utilize an approximate weight. During a task allocation stage, two performance indexes, namely the time and the energy consumption, are simultaneously considered, and the task is allocated to the proper processor according to the significance proportion of the time and the energy consumption, so that the tradeoff optimization of the time and the energy consumption according to the specific gravity is realized, and thus the system obtains higher weighting performance. The algorithm is combined with a DVFS (Dynamic Voltage and Frequency Scaling) technology and is also suitable for an isomorphic parallel system and a computer system without embedment of the DVFS technology.

Description

technical field [0001] The invention belongs to the field of task scheduling under heterogeneous parallel systems, and more specifically, relates to a parallel task scheduling algorithm based on the importance ratio of time-energy consumption, which can realize the time and energy consumption of parallel tasks under the dual constraints of time and energy consumption. Energy consumption trade-off optimization. Background technique [0002] In the past few decades, most people only paid attention to the calculation speed of computers. In order to meet the needs of calculation speed, the computer performance has been improved by increasing the number of transistors, increasing the frequency of processors, and increasing the parallelism of processors. Constructed parallel systems also came into being. However, while the speed of computers is getting faster and faster, the problem of energy consumption is becoming more and more prominent. Due to the importance of energy consum...

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): G06F1/32G06F9/50
CPCG06F1/329G06F9/5094Y02D10/00
Inventor 廖小飞吕新桥金海杨雨晴
Owner HUAZHONG UNIV OF SCI & TECH
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