GPGPU aided method for real-time systems

Yusuke Iwase, Daiki Abe, Takahiro Yakoh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Guaranteeing real-time is required in the field of digital control. This is to start a task at a predetermined time, and complete the task before the predetermined deadline. However recently, it is getting difficult to guarantee such a completion. This is due to the fact that the amount of calculation within a period is increasing, and the period itself is being required to be shorter. As a method for parallel processing, GPGPU (General-Purpose computation on GPU) is recently attracting attention. However, tools to apply GPGPU to real-time system are not provided from the GPU vendor, and related research is not yet found. Therefore, this paper proposes and evaluates a method to operate GPGPU in real-time systems. From the experimental results, the proposed method dramatically reduced the jitter and the elapsed time comparing to the CPU itself, and also the conventional method. This shows that the proposed method improves the predictability of the completion time, and the GPU can be applied to real-time systems.

Original languageEnglish
Title of host publicationIEEE International Conference on Industrial Informatics (INDIN)
Pages841-845
Number of pages5
DOIs
Publication statusPublished - 2012
EventIEEE 10th International Conference on Industrial Informatics, INDIN 2012 - Beijing, China
Duration: 2012 Jul 252012 Jul 27

Other

OtherIEEE 10th International Conference on Industrial Informatics, INDIN 2012
CountryChina
CityBeijing
Period12/7/2512/7/27

Fingerprint

Real time systems
Jitter
Program processors
Processing
Graphics processing unit

Keywords

  • GPGPU
  • PC-based-control
  • Real-time system
  • RTAI

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Iwase, Y., Abe, D., & Yakoh, T. (2012). GPGPU aided method for real-time systems. In IEEE International Conference on Industrial Informatics (INDIN) (pp. 841-845). [6301204] https://doi.org/10.1109/INDIN.2012.6301204

GPGPU aided method for real-time systems. / Iwase, Yusuke; Abe, Daiki; Yakoh, Takahiro.

IEEE International Conference on Industrial Informatics (INDIN). 2012. p. 841-845 6301204.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iwase, Y, Abe, D & Yakoh, T 2012, GPGPU aided method for real-time systems. in IEEE International Conference on Industrial Informatics (INDIN)., 6301204, pp. 841-845, IEEE 10th International Conference on Industrial Informatics, INDIN 2012, Beijing, China, 12/7/25. https://doi.org/10.1109/INDIN.2012.6301204
Iwase Y, Abe D, Yakoh T. GPGPU aided method for real-time systems. In IEEE International Conference on Industrial Informatics (INDIN). 2012. p. 841-845. 6301204 https://doi.org/10.1109/INDIN.2012.6301204
Iwase, Yusuke ; Abe, Daiki ; Yakoh, Takahiro. / GPGPU aided method for real-time systems. IEEE International Conference on Industrial Informatics (INDIN). 2012. pp. 841-845
@inproceedings{0681b691b3e84aa397d35c703c34b23e,
title = "GPGPU aided method for real-time systems",
abstract = "Guaranteeing real-time is required in the field of digital control. This is to start a task at a predetermined time, and complete the task before the predetermined deadline. However recently, it is getting difficult to guarantee such a completion. This is due to the fact that the amount of calculation within a period is increasing, and the period itself is being required to be shorter. As a method for parallel processing, GPGPU (General-Purpose computation on GPU) is recently attracting attention. However, tools to apply GPGPU to real-time system are not provided from the GPU vendor, and related research is not yet found. Therefore, this paper proposes and evaluates a method to operate GPGPU in real-time systems. From the experimental results, the proposed method dramatically reduced the jitter and the elapsed time comparing to the CPU itself, and also the conventional method. This shows that the proposed method improves the predictability of the completion time, and the GPU can be applied to real-time systems.",
keywords = "GPGPU, PC-based-control, Real-time system, RTAI",
author = "Yusuke Iwase and Daiki Abe and Takahiro Yakoh",
year = "2012",
doi = "10.1109/INDIN.2012.6301204",
language = "English",
isbn = "9781467303118",
pages = "841--845",
booktitle = "IEEE International Conference on Industrial Informatics (INDIN)",

}

TY - GEN

T1 - GPGPU aided method for real-time systems

AU - Iwase, Yusuke

AU - Abe, Daiki

AU - Yakoh, Takahiro

PY - 2012

Y1 - 2012

N2 - Guaranteeing real-time is required in the field of digital control. This is to start a task at a predetermined time, and complete the task before the predetermined deadline. However recently, it is getting difficult to guarantee such a completion. This is due to the fact that the amount of calculation within a period is increasing, and the period itself is being required to be shorter. As a method for parallel processing, GPGPU (General-Purpose computation on GPU) is recently attracting attention. However, tools to apply GPGPU to real-time system are not provided from the GPU vendor, and related research is not yet found. Therefore, this paper proposes and evaluates a method to operate GPGPU in real-time systems. From the experimental results, the proposed method dramatically reduced the jitter and the elapsed time comparing to the CPU itself, and also the conventional method. This shows that the proposed method improves the predictability of the completion time, and the GPU can be applied to real-time systems.

AB - Guaranteeing real-time is required in the field of digital control. This is to start a task at a predetermined time, and complete the task before the predetermined deadline. However recently, it is getting difficult to guarantee such a completion. This is due to the fact that the amount of calculation within a period is increasing, and the period itself is being required to be shorter. As a method for parallel processing, GPGPU (General-Purpose computation on GPU) is recently attracting attention. However, tools to apply GPGPU to real-time system are not provided from the GPU vendor, and related research is not yet found. Therefore, this paper proposes and evaluates a method to operate GPGPU in real-time systems. From the experimental results, the proposed method dramatically reduced the jitter and the elapsed time comparing to the CPU itself, and also the conventional method. This shows that the proposed method improves the predictability of the completion time, and the GPU can be applied to real-time systems.

KW - GPGPU

KW - PC-based-control

KW - Real-time system

KW - RTAI

UR - http://www.scopus.com/inward/record.url?scp=84868258498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868258498&partnerID=8YFLogxK

U2 - 10.1109/INDIN.2012.6301204

DO - 10.1109/INDIN.2012.6301204

M3 - Conference contribution

AN - SCOPUS:84868258498

SN - 9781467303118

SP - 841

EP - 845

BT - IEEE International Conference on Industrial Informatics (INDIN)

ER -