Energy optimization for scientific programs using auto-tuning language ppOpen-AT

Takahiro Katagiri; Cheng Luo; Reiji Suda; Shoichi Hirasawa; Satoshi Ohshima

doi:10.1109/MCSoC.2013.14

Energy optimization for scientific programs using auto-tuning language ppOpen-AT

Takahiro Katagiri, Cheng Luo, Reiji Suda, Shoichi Hirasawa, Satoshi Ohshima

研究成果: 書籍/レポートタイプへの寄稿 › 会議への寄与

2 被引用数 (Scopus)

抄録

In this paper, we demonstrate a new approach for power-consumption optimization using a dedicated Auto-tuning (AT) language. Our approach is based on recently developed technologies: (1) a power measurement application programming interface, (2) an AT mathematical core library. Preliminary performance evaluation enables us to select the best kernel for a real-world scientific program using either the CPU or Graphics Processing Unit, with respect to energy consumption. From the results of the evaluation, we found the performance-changing point in the experimental environment.

本文言語	英語
ホスト出版物のタイトル	Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013
出版社	IEEE Computer Society
ページ	123-128
ページ数	6
ISBN（印刷版）	9780768550862
DOI	https://doi.org/10.1109/MCSoC.2013.14
出版ステータス	出版済み - 2013
外部発表	はい
イベント	2013 IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013 - Tokyo, 日本継続期間: 9月 26 2013 → 9月 28 2013

出版物シリーズ

名前	Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013

その他

その他	2013 IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013
国/地域	日本
City	Tokyo
Period	9/26/13 → 9/28/13

!!!All Science Journal Classification (ASJC) codes

ハードウェアとアーキテクチャ

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/MCSoC.2013.14

他のファイルとリンク

引用スタイル

Katagiri, T., Luo, C., Suda, R., Hirasawa, S., & Ohshima, S. (2013). Energy optimization for scientific programs using auto-tuning language ppOpen-AT. In Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013 (pp. 123-128). [6657916] (Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013). IEEE Computer Society. https://doi.org/10.1109/MCSoC.2013.14

Energy optimization for scientific programs using auto-tuning language ppOpen-AT. / Katagiri, Takahiro; Luo, Cheng; Suda, Reiji その他.
Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013. IEEE Computer Society, 2013. p. 123-128 6657916 (Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013).

研究成果: 書籍/レポートタイプへの寄稿 › 会議への寄与

Katagiri, T, Luo, C, Suda, R, Hirasawa, S & Ohshima, S 2013, Energy optimization for scientific programs using auto-tuning language ppOpen-AT. in Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013., 6657916, Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013, IEEE Computer Society, pp. 123-128, 2013 IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013, Tokyo, 日本, 9/26/13. https://doi.org/10.1109/MCSoC.2013.14

Katagiri T, Luo C, Suda R, Hirasawa S, Ohshima S. Energy optimization for scientific programs using auto-tuning language ppOpen-AT. In Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013. IEEE Computer Society. 2013. p. 123-128. 6657916. (Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013). doi: 10.1109/MCSoC.2013.14

Katagiri, Takahiro ; Luo, Cheng ; Suda, Reiji その他. / Energy optimization for scientific programs using auto-tuning language ppOpen-AT. Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013. IEEE Computer Society, 2013. pp. 123-128 (Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013).

@inproceedings{4af8f5c56bf44eca8dd2202346a9e747,

title = "Energy optimization for scientific programs using auto-tuning language ppOpen-AT",

abstract = "In this paper, we demonstrate a new approach for power-consumption optimization using a dedicated Auto-tuning (AT) language. Our approach is based on recently developed technologies: (1) a power measurement application programming interface, (2) an AT mathematical core library. Preliminary performance evaluation enables us to select the best kernel for a real-world scientific program using either the CPU or Graphics Processing Unit, with respect to energy consumption. From the results of the evaluation, we found the performance-changing point in the experimental environment.",

author = "Takahiro Katagiri and Cheng Luo and Reiji Suda and Shoichi Hirasawa and Satoshi Ohshima",

note = "Copyright: Copyright 2014 Elsevier B.V., All rights reserved.; 2013 IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013 ; Conference date: 26-09-2013 Through 28-09-2013",

year = "2013",

doi = "10.1109/MCSoC.2013.14",

language = "English",

isbn = "9780768550862",

series = "Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013",

publisher = "IEEE Computer Society",

pages = "123--128",

booktitle = "Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013",

address = "United States",

}

TY - GEN

T1 - Energy optimization for scientific programs using auto-tuning language ppOpen-AT

AU - Katagiri, Takahiro

AU - Luo, Cheng

AU - Suda, Reiji

AU - Hirasawa, Shoichi

AU - Ohshima, Satoshi

PY - 2013

Y1 - 2013

N2 - In this paper, we demonstrate a new approach for power-consumption optimization using a dedicated Auto-tuning (AT) language. Our approach is based on recently developed technologies: (1) a power measurement application programming interface, (2) an AT mathematical core library. Preliminary performance evaluation enables us to select the best kernel for a real-world scientific program using either the CPU or Graphics Processing Unit, with respect to energy consumption. From the results of the evaluation, we found the performance-changing point in the experimental environment.

AB - In this paper, we demonstrate a new approach for power-consumption optimization using a dedicated Auto-tuning (AT) language. Our approach is based on recently developed technologies: (1) a power measurement application programming interface, (2) an AT mathematical core library. Preliminary performance evaluation enables us to select the best kernel for a real-world scientific program using either the CPU or Graphics Processing Unit, with respect to energy consumption. From the results of the evaluation, we found the performance-changing point in the experimental environment.

UR - http://www.scopus.com/inward/record.url?scp=84892664299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892664299&partnerID=8YFLogxK

U2 - 10.1109/MCSoC.2013.14

DO - 10.1109/MCSoC.2013.14

M3 - Conference contribution

AN - SCOPUS:84892664299

SN - 9780768550862

T3 - Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013

SP - 123

EP - 128

BT - Proceedings - IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013

PB - IEEE Computer Society

T2 - 2013 IEEE 7th International Symposium on Embedded Multicore/Manycore System-on-Chip, MCSoC 2013

Y2 - 26 September 2013 through 28 September 2013

ER -

Energy optimization for scientific programs using auto-tuning language ppOpen-AT

抄録

出版物シリーズ

その他

!!!All Science Journal Classification (ASJC) codes

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