Heterogeneous computing system low-power-consumption method based on task scheduling

A computing system and task scheduling technology, applied in computing, energy-saving computing, program control design, etc., can solve the problems of under-utilization, under-utilization, over-utilization of GPU, etc., and achieve the effect of saving energy and reducing average energy consumption

Pending Publication Date: 2020-06-05
QIANNAN NORMAL UNIV FOR NATTIES
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not consider the remaining time of the current task to execute in the corresponding GPU, which will lead to the over-utilization and under-utilization of the corresponding GPU
For example, if all tasks to be executed are assigned to the first GPU according to the ratio value above, the first GPU will be utilized and the remaining GPUs will become underutilized

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
  • Heterogeneous computing system low-power-consumption method based on task scheduling
  • Heterogeneous computing system low-power-consumption method based on task scheduling
  • Heterogeneous computing system low-power-consumption method based on task scheduling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with the accompanying drawings and embodiments, but not as a basis for limiting the present invention.

[0062] Example. A low-power method for heterogeneous computing systems based on task scheduling, such as Figure 5 shown, including the following steps:

[0063] a. Obtain the number of tasks under a given time interval and task threshold number; where the time interval controls the system sensitivity, and the task threshold number will affect the performance of the method;

[0064] b. Compare the number of tasks with the number of GPUs, when the number of tasks is less than or equal to the number of GPUs, use the first-in-first-out strategy to assign tasks to each GPU; when the number of tasks is greater than the number of GPUs, use the 0-1 planning model Assign corresponding tasks to each GPU.

[0065]In the aforementioned step b, the 0-1 programming model is as follows:

[0066]

[0067] A...

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 heterogeneous computing system low-power-consumption method based on task scheduling. The method comprises the following steps: a, obtaining the number of tasks under the condition that a time interval and a task threshold number are given; b, comparing the number of the tasks with the number of the GPUs, and when the number of the tasks is smaller than or equal to the number of the GPUs, allocating the tasks to the GPUs by using a first-in first-out strategy; and when the number of the tasks is greater than the number of the GPUs, allocating a corresponding task to each GPU by using the 0-1 planning model. The method has the characteristic of reducing the average energy consumption of the system.

Description

technical field [0001] The invention relates to the technical field of high-performance computers in heterogeneous environments, in particular to a low-power consumption method for heterogeneous computing systems based on task scheduling. Background technique [0002] In recent years, thanks to the promotion of computer systems, the world has entered the era of big data. As the most important processor in computer systems, multi-core GPU has attracted extensive attention. Due to the parallelism of graphics drawing, the inherent large number of parallel processing units of GPU makes its processing capability more powerful, and more and more computer systems integrate multiple GPU processors (which can be regarded as computing resources) to obtain high performance. Due to its powerful computing power, it can efficiently process massive data and enable "value-added" data processing. In the field of general computing, a computer system using a GPU is generally called a heterog...

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): G06F1/329G06F9/48G06F9/50
CPCG06F1/329G06F9/4806G06F9/5027Y02D10/00
Inventor 李君科刘凯郭顺超胡洋
Owner QIANNAN NORMAL UNIV FOR NATTIES
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