Evaluation of task clustering algorithm by FFT for heterogeneous distributed system

Shuya Hashimoto; Emilia Ndilokelwa Weyulu; Kazuo Hajikano; Hidehiro Kanemitsu; Moo Wan Kim

doi:10.23919/ICACT.2017.7890064

Evaluation of task clustering algorithm by FFT for heterogeneous distributed system

Shuya Hashimoto, Emilia Ndilokelwa Weyulu, Kazuo Hajikano, Hidehiro Kanemitsu, Moo Wan Kim

Global Education Center

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper, the evaluation result of a task clustering heuristic algorithm proposed for heterogeneous distributed systems is shown. The proposed heuristic algorithm is based on our original concept, known as 'Worst Schedule Length (WSL)'. It derives the lower bound of the total execution time of the cluster for each processor using WSL, then the processor which contributes to minimize WSL is chosen as an assignment target. Task clustering is then performed to get minimal response time (i.e., minimal schedule length). We show that our proposed method has advantages over existing conventional approaches through the evaluation results.

Original language	English
Title of host publication	19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	94-97
Number of pages	4
ISBN (Electronic)	9788996865094
DOIs	https://doi.org/10.23919/ICACT.2017.7890064
Publication status	Published - 2017 Mar 29
Event	19th International Conference on Advanced Communications Technology, ICACT 2017 - Pyeongchang, Korea, Republic of Duration: 2017 Feb 19 → 2017 Feb 22

Other

Other	19th International Conference on Advanced Communications Technology, ICACT 2017
Country/Territory	Korea, Republic of
City	Pyeongchang
Period	17/2/19 → 17/2/22

Keywords

Big data
Distributed processing
Fast fourier transform
Task graph

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.23919/ICACT.2017.7890064

Cite this

Hashimoto, S., Weyulu, E. N., Hajikano, K., Kanemitsu, H., & Kim, M. W. (2017). Evaluation of task clustering algorithm by FFT for heterogeneous distributed system. In 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding (pp. 94-97). [7890064] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ICACT.2017.7890064

Evaluation of task clustering algorithm by FFT for heterogeneous distributed system. / Hashimoto, Shuya; Weyulu, Emilia Ndilokelwa; Hajikano, Kazuo et al.

19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding. Institute of Electrical and Electronics Engineers Inc., 2017. p. 94-97 7890064.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hashimoto, S, Weyulu, EN, Hajikano, K, Kanemitsu, H & Kim, MW 2017, Evaluation of task clustering algorithm by FFT for heterogeneous distributed system. in 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding., 7890064, Institute of Electrical and Electronics Engineers Inc., pp. 94-97, 19th International Conference on Advanced Communications Technology, ICACT 2017, Pyeongchang, Korea, Republic of, 17/2/19. https://doi.org/10.23919/ICACT.2017.7890064

Hashimoto S, Weyulu EN, Hajikano K, Kanemitsu H, Kim MW. Evaluation of task clustering algorithm by FFT for heterogeneous distributed system. In 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding. Institute of Electrical and Electronics Engineers Inc. 2017. p. 94-97. 7890064 doi: 10.23919/ICACT.2017.7890064

@inproceedings{c0482a186ded40a884933babab93321c,

title = "Evaluation of task clustering algorithm by FFT for heterogeneous distributed system",

abstract = "In this paper, the evaluation result of a task clustering heuristic algorithm proposed for heterogeneous distributed systems is shown. The proposed heuristic algorithm is based on our original concept, known as 'Worst Schedule Length (WSL)'. It derives the lower bound of the total execution time of the cluster for each processor using WSL, then the processor which contributes to minimize WSL is chosen as an assignment target. Task clustering is then performed to get minimal response time (i.e., minimal schedule length). We show that our proposed method has advantages over existing conventional approaches through the evaluation results.",

keywords = "Big data, Distributed processing, Fast fourier transform, Task graph",

author = "Shuya Hashimoto and Weyulu, {Emilia Ndilokelwa} and Kazuo Hajikano and Hidehiro Kanemitsu and Kim, {Moo Wan}",

year = "2017",

month = mar,

day = "29",

doi = "10.23919/ICACT.2017.7890064",

language = "English",

pages = "94--97",

booktitle = "19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "19th International Conference on Advanced Communications Technology, ICACT 2017 ; Conference date: 19-02-2017 Through 22-02-2017",

}

TY - GEN

T1 - Evaluation of task clustering algorithm by FFT for heterogeneous distributed system

AU - Hashimoto, Shuya

AU - Weyulu, Emilia Ndilokelwa

AU - Hajikano, Kazuo

AU - Kanemitsu, Hidehiro

AU - Kim, Moo Wan

PY - 2017/3/29

Y1 - 2017/3/29

N2 - In this paper, the evaluation result of a task clustering heuristic algorithm proposed for heterogeneous distributed systems is shown. The proposed heuristic algorithm is based on our original concept, known as 'Worst Schedule Length (WSL)'. It derives the lower bound of the total execution time of the cluster for each processor using WSL, then the processor which contributes to minimize WSL is chosen as an assignment target. Task clustering is then performed to get minimal response time (i.e., minimal schedule length). We show that our proposed method has advantages over existing conventional approaches through the evaluation results.

AB - In this paper, the evaluation result of a task clustering heuristic algorithm proposed for heterogeneous distributed systems is shown. The proposed heuristic algorithm is based on our original concept, known as 'Worst Schedule Length (WSL)'. It derives the lower bound of the total execution time of the cluster for each processor using WSL, then the processor which contributes to minimize WSL is chosen as an assignment target. Task clustering is then performed to get minimal response time (i.e., minimal schedule length). We show that our proposed method has advantages over existing conventional approaches through the evaluation results.

KW - Big data

KW - Distributed processing

KW - Fast fourier transform

KW - Task graph

UR - http://www.scopus.com/inward/record.url?scp=85018526868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018526868&partnerID=8YFLogxK

U2 - 10.23919/ICACT.2017.7890064

DO - 10.23919/ICACT.2017.7890064

M3 - Conference contribution

AN - SCOPUS:85018526868

SP - 94

EP - 97

BT - 19th International Conference on Advanced Communications Technology: Opening Era of Smart Society, ICACT 2017 - Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International Conference on Advanced Communications Technology, ICACT 2017

Y2 - 19 February 2017 through 22 February 2017

ER -

Evaluation of task clustering algorithm by FFT for heterogeneous distributed system

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this