Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel

Yasuaki Okamoto; Hideharu Amano

doi:10.1109/CANDARW.2019.00056

Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel

Yasuaki Okamoto, Hideharu Amano

情報工学科

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Radiation transfer (RT) is an important physical processes of energy transfer in the form of electromagnetic wave, and ART method is a ray-tracing for computing RT of re-connected photons in the simulation of protogalaxies formation. It requires a heavy computational power and complicated memory accesses which are not suitable to acceleration with GPUs. Here, for the future use of FPGA-in-Cloud, the acceleration of ART method with SDAccel on Xilinx's cost efficient FPGA board KCU1500 was tried. Although the execution time was not reduced compared with the host CPU with various combination of derivatives, the energy consumption was reduced to 1/3.35.

本文言語	English
ホスト出版物のタイトル	Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019
出版社	Institute of Electrical and Electronics Engineers Inc.
ページ	280-284
ページ数	5
ISBN（電子版）	9781728152684
DOI	https://doi.org/10.1109/CANDARW.2019.00056
出版ステータス	Published - 2019 11月
イベント	7th International Symposium on Computing and Networking Workshops, CANDARW 2019 - Nagasaki, Japan 継続期間: 2019 11月 26 → 2019 11月 29

出版物シリーズ

名前	Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019

Conference

Conference	7th International Symposium on Computing and Networking Workshops, CANDARW 2019
国/地域	Japan
City	Nagasaki
Period	19/11/26 → 19/11/29

ASJC Scopus subject areas

ハードウェアとアーキテクチャ
情報システム
人工知能
コンピュータネットワークおよび通信

UN SDG

この成果は、次の持続可能な開発目標に貢献しています

文献へのアクセス

10.1109/CANDARW.2019.00056

他のファイルとリンク

引用スタイル

Okamoto, Y., & Amano, H. (2019). Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel. In Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019 (pp. 280-284). 記事 8951517 (Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CANDARW.2019.00056

Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel. / Okamoto, Yasuaki; Amano, Hideharu.
Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 280-284 8951517 (Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019).

研究成果: Conference contribution

Okamoto, Y & Amano, H 2019, Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel. in Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019., 8951517, Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019, Institute of Electrical and Electronics Engineers Inc., pp. 280-284, 7th International Symposium on Computing and Networking Workshops, CANDARW 2019, Nagasaki, Japan, 19/11/26. https://doi.org/10.1109/CANDARW.2019.00056

Okamoto Y, Amano H. Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel. In Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 280-284. 8951517. (Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019). doi: 10.1109/CANDARW.2019.00056

Okamoto, Yasuaki ; Amano, Hideharu. / Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel. Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 280-284 (Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019).

@inproceedings{e6d974401fe742bfa27a09e7ac16a8fb,

title = "Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel",

abstract = "Radiation transfer (RT) is an important physical processes of energy transfer in the form of electromagnetic wave, and ART method is a ray-tracing for computing RT of re-connected photons in the simulation of protogalaxies formation. It requires a heavy computational power and complicated memory accesses which are not suitable to acceleration with GPUs. Here, for the future use of FPGA-in-Cloud, the acceleration of ART method with SDAccel on Xilinx's cost efficient FPGA board KCU1500 was tried. Although the execution time was not reduced compared with the host CPU with various combination of derivatives, the energy consumption was reduced to 1/3.35.",

keywords = "ART Algorithm, FPGA in cloud, SDAccel",

author = "Yasuaki Okamoto and Hideharu Amano",

note = "Funding Information: Acknowledgment A part of this work was supported by JSPS KAKENHI Grant Number JP18H03246. We would like to offer our special thanks to Prof. Yoshiki Yamaguchi and Dr. Norihisa Fujita. Publisher Copyright: {\textcopyright} 2019 IEEE.; 7th International Symposium on Computing and Networking Workshops, CANDARW 2019 ; Conference date: 26-11-2019 Through 29-11-2019",

year = "2019",

month = nov,

doi = "10.1109/CANDARW.2019.00056",

language = "English",

series = "Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019",

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

pages = "280--284",

booktitle = "Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019",

}

TY - GEN

T1 - Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel

AU - Okamoto, Yasuaki

AU - Amano, Hideharu

N1 - Funding Information: Acknowledgment A part of this work was supported by JSPS KAKENHI Grant Number JP18H03246. We would like to offer our special thanks to Prof. Yoshiki Yamaguchi and Dr. Norihisa Fujita. Publisher Copyright: © 2019 IEEE.

PY - 2019/11

Y1 - 2019/11

N2 - Radiation transfer (RT) is an important physical processes of energy transfer in the form of electromagnetic wave, and ART method is a ray-tracing for computing RT of re-connected photons in the simulation of protogalaxies formation. It requires a heavy computational power and complicated memory accesses which are not suitable to acceleration with GPUs. Here, for the future use of FPGA-in-Cloud, the acceleration of ART method with SDAccel on Xilinx's cost efficient FPGA board KCU1500 was tried. Although the execution time was not reduced compared with the host CPU with various combination of derivatives, the energy consumption was reduced to 1/3.35.

AB - Radiation transfer (RT) is an important physical processes of energy transfer in the form of electromagnetic wave, and ART method is a ray-tracing for computing RT of re-connected photons in the simulation of protogalaxies formation. It requires a heavy computational power and complicated memory accesses which are not suitable to acceleration with GPUs. Here, for the future use of FPGA-in-Cloud, the acceleration of ART method with SDAccel on Xilinx's cost efficient FPGA board KCU1500 was tried. Although the execution time was not reduced compared with the host CPU with various combination of derivatives, the energy consumption was reduced to 1/3.35.

KW - ART Algorithm

KW - FPGA in cloud

KW - SDAccel

UR - http://www.scopus.com/inward/record.url?scp=85078817157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078817157&partnerID=8YFLogxK

U2 - 10.1109/CANDARW.2019.00056

DO - 10.1109/CANDARW.2019.00056

M3 - Conference contribution

AN - SCOPUS:85078817157

T3 - Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019

SP - 280

EP - 284

BT - Proceedings - 2019 7th International Symposium on Computing and Networking Workshops, CANDARW 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Symposium on Computing and Networking Workshops, CANDARW 2019

Y2 - 26 November 2019 through 29 November 2019

ER -

Acceleration of ART Algorithm on an FPGA Board with Xilinx SDAccel

抄録

出版物シリーズ

Conference

ASJC Scopus subject areas

UN SDG

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル