An energy optimization method for vector processing mechanisms

Ye Gao; Masayuki Sato; Ryusuke Egawa; Hiroyuki Takizawa; Hiroaki Kobayashi

doi:10.1109/CoolChips.2014.6842957

An energy optimization method for vector processing mechanisms

Ye Gao, Masayuki Sato, Ryusuke Egawa, Hiroyuki Takizawa, Hiroaki Kobayashi

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

Abstract

In order to achieve a low energy execution for any multimedia applications (MMAs) on a vector processing mechanism (VPM), the number of parallel arithmetic pipelines and the number of cache ports of VPM must be properly configured for each MMAs. Therefore, this paper proposes an energy optimization method for VPMs (EOM-VP), which finds the lowest energy configuration by using the greedy searching method and an analytical model. As the evaluation results suggest, EOM-VP could find the lowest or the second lowest energy configuration for all the benchmark programs in the evaluation.

Original language	English
Title of host publication	IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII
Publisher	IEEE Computer Society
ISBN (Print)	9781479938094
DOIs	https://doi.org/10.1109/CoolChips.2014.6842957
Publication status	Published - 2014
Event	17th IEEE Symposium on Low-Power and High-Speed Chips, COOL Chips 2014 - Yokohama, Japan Duration: 2014 Apr 14 → 2014 Apr 16

Publication series

Name	IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII

Other

Other	17th IEEE Symposium on Low-Power and High-Speed Chips, COOL Chips 2014
Country	Japan
City	Yokohama
Period	14/4/14 → 14/4/16

Keywords

energy
multimedia application
optimization
power consumption
vector architecture

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1109/CoolChips.2014.6842957

Fingerprint Dive into the research topics of 'An energy optimization method for vector processing mechanisms'. Together they form a unique fingerprint.

Cite this

Gao, Y., Sato, M., Egawa, R., Takizawa, H., & Kobayashi, H. (2014). An energy optimization method for vector processing mechanisms. In IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII [6842957] (IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII). IEEE Computer Society. https://doi.org/10.1109/CoolChips.2014.6842957

An energy optimization method for vector processing mechanisms. / Gao, Ye; Sato, Masayuki; Egawa, Ryusuke; Takizawa, Hiroyuki ; Kobayashi, Hiroaki.

IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII. IEEE Computer Society, 2014. 6842957 (IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII).

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

Gao, Y, Sato, M, Egawa, R, Takizawa, H & Kobayashi, H 2014, An energy optimization method for vector processing mechanisms. in IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII., 6842957, IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII, IEEE Computer Society, 17th IEEE Symposium on Low-Power and High-Speed Chips, COOL Chips 2014, Yokohama, Japan, 14/4/14. https://doi.org/10.1109/CoolChips.2014.6842957

Gao Y, Sato M, Egawa R, Takizawa H , Kobayashi H. An energy optimization method for vector processing mechanisms. In IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII. IEEE Computer Society. 2014. 6842957. (IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII). https://doi.org/10.1109/CoolChips.2014.6842957

Gao, Ye ; Sato, Masayuki ; Egawa, Ryusuke ; Takizawa, Hiroyuki ; Kobayashi, Hiroaki. / An energy optimization method for vector processing mechanisms. IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII. IEEE Computer Society, 2014. (IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII).

@inproceedings{7affaa888ac3413c914207bdb08985d0,

title = "An energy optimization method for vector processing mechanisms",

abstract = "In order to achieve a low energy execution for any multimedia applications (MMAs) on a vector processing mechanism (VPM), the number of parallel arithmetic pipelines and the number of cache ports of VPM must be properly configured for each MMAs. Therefore, this paper proposes an energy optimization method for VPMs (EOM-VP), which finds the lowest energy configuration by using the greedy searching method and an analytical model. As the evaluation results suggest, EOM-VP could find the lowest or the second lowest energy configuration for all the benchmark programs in the evaluation.",

keywords = "energy, multimedia application, optimization, power consumption, vector architecture",

author = "Ye Gao and Masayuki Sato and Ryusuke Egawa and Hiroyuki Takizawa and Hiroaki Kobayashi",

year = "2014",

doi = "10.1109/CoolChips.2014.6842957",

language = "English",

isbn = "9781479938094",

series = "IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII",

publisher = "IEEE Computer Society",

booktitle = "IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII",

}

TY - GEN

T1 - An energy optimization method for vector processing mechanisms

AU - Gao, Ye

AU - Sato, Masayuki

AU - Egawa, Ryusuke

AU - Takizawa, Hiroyuki

AU - Kobayashi, Hiroaki

PY - 2014

Y1 - 2014

N2 - In order to achieve a low energy execution for any multimedia applications (MMAs) on a vector processing mechanism (VPM), the number of parallel arithmetic pipelines and the number of cache ports of VPM must be properly configured for each MMAs. Therefore, this paper proposes an energy optimization method for VPMs (EOM-VP), which finds the lowest energy configuration by using the greedy searching method and an analytical model. As the evaluation results suggest, EOM-VP could find the lowest or the second lowest energy configuration for all the benchmark programs in the evaluation.

AB - In order to achieve a low energy execution for any multimedia applications (MMAs) on a vector processing mechanism (VPM), the number of parallel arithmetic pipelines and the number of cache ports of VPM must be properly configured for each MMAs. Therefore, this paper proposes an energy optimization method for VPMs (EOM-VP), which finds the lowest energy configuration by using the greedy searching method and an analytical model. As the evaluation results suggest, EOM-VP could find the lowest or the second lowest energy configuration for all the benchmark programs in the evaluation.

KW - energy

KW - multimedia application

KW - optimization

KW - power consumption

KW - vector architecture

UR - http://www.scopus.com/inward/record.url?scp=84904641765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904641765&partnerID=8YFLogxK

U2 - 10.1109/CoolChips.2014.6842957

DO - 10.1109/CoolChips.2014.6842957

M3 - Conference contribution

AN - SCOPUS:84904641765

SN - 9781479938094

T3 - IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII

BT - IEEE Symposium on Low-Power and High-Speed Chips - Proceedings for 2014 IEEE COOL Chips XVII

PB - IEEE Computer Society

T2 - 17th IEEE Symposium on Low-Power and High-Speed Chips, COOL Chips 2014

Y2 - 14 April 2014 through 16 April 2014

ER -