Content-aware line-based power modeling methodology for image signal processor

Chun Wei Chen, Ming-Der Shieh, Juin Ming Lu, Hsun Lun Huang, Yao Hua Chen

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

Abstract

Early power modeling and analysis using electronic system-level methodology enables designers to explore energy saving opportunities more efficiently at a higher abstraction level. However, power modeling for third party IPs are challenging due to the limited observability and unknown architecture details. To model the data dependency for blackbox IPs, several works rely on adopting Hamming distance of input data to approximate the switching activity, which might be not enough for modeling complex IPs such as image signal processors (ISP). This work introduces a content-aware line-based power modeling method for ISP by training an associated energy table. To effectively estimate ISP energy consumption which involves many two-dimensional data processing, this work presents a direct energy-mapping strategy using pixel luminance and gradient. Moreover, an iterative box-constrained least-squares estimation and its associated constraint refinement scheme is proposed to increase the robustness of the trained energy table even with limited training data. Simulation results show that the proposed method can reduce at least 11.54% of average error and 55.52% of max error as compared to the existing content-blind power model.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE International System on Chip Conference, SOCC 2017
EditorsJurgen Becker, Ramalingam Sridhar, Hai Li, Ulf Schlichtmann, Massimo Alioto
PublisherIEEE Computer Society
Pages346-350
Number of pages5
ISBN (Electronic)9781538640333
DOIs
Publication statusPublished - 2017 Dec 18
Event30th IEEE International System on Chip Conference, SOCC 2017 - Munich, Germany
Duration: 2017 Sep 52017 Sep 8

Publication series

NameInternational System on Chip Conference
Volume2017-September
ISSN (Print)2164-1676
ISSN (Electronic)2164-1706

Other

Other30th IEEE International System on Chip Conference, SOCC 2017
CountryGermany
CityMunich
Period17-09-0517-09-08

Fingerprint

Hamming distance
Observability
Luminance
Energy conservation
Energy utilization
Pixels

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Chen, C. W., Shieh, M-D., Lu, J. M., Huang, H. L., & Chen, Y. H. (2017). Content-aware line-based power modeling methodology for image signal processor. In J. Becker, R. Sridhar, H. Li, U. Schlichtmann, & M. Alioto (Eds.), Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017 (pp. 346-350). (International System on Chip Conference; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/SOCC.2017.8226075
Chen, Chun Wei ; Shieh, Ming-Der ; Lu, Juin Ming ; Huang, Hsun Lun ; Chen, Yao Hua. / Content-aware line-based power modeling methodology for image signal processor. Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017. editor / Jurgen Becker ; Ramalingam Sridhar ; Hai Li ; Ulf Schlichtmann ; Massimo Alioto. IEEE Computer Society, 2017. pp. 346-350 (International System on Chip Conference).
@inproceedings{f9bbe6d509844c2ebb8e1f9ef27407f0,
title = "Content-aware line-based power modeling methodology for image signal processor",
abstract = "Early power modeling and analysis using electronic system-level methodology enables designers to explore energy saving opportunities more efficiently at a higher abstraction level. However, power modeling for third party IPs are challenging due to the limited observability and unknown architecture details. To model the data dependency for blackbox IPs, several works rely on adopting Hamming distance of input data to approximate the switching activity, which might be not enough for modeling complex IPs such as image signal processors (ISP). This work introduces a content-aware line-based power modeling method for ISP by training an associated energy table. To effectively estimate ISP energy consumption which involves many two-dimensional data processing, this work presents a direct energy-mapping strategy using pixel luminance and gradient. Moreover, an iterative box-constrained least-squares estimation and its associated constraint refinement scheme is proposed to increase the robustness of the trained energy table even with limited training data. Simulation results show that the proposed method can reduce at least 11.54{\%} of average error and 55.52{\%} of max error as compared to the existing content-blind power model.",
author = "Chen, {Chun Wei} and Ming-Der Shieh and Lu, {Juin Ming} and Huang, {Hsun Lun} and Chen, {Yao Hua}",
year = "2017",
month = "12",
day = "18",
doi = "10.1109/SOCC.2017.8226075",
language = "English",
series = "International System on Chip Conference",
publisher = "IEEE Computer Society",
pages = "346--350",
editor = "Jurgen Becker and Ramalingam Sridhar and Hai Li and Ulf Schlichtmann and Massimo Alioto",
booktitle = "Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017",
address = "United States",

}

Chen, CW, Shieh, M-D, Lu, JM, Huang, HL & Chen, YH 2017, Content-aware line-based power modeling methodology for image signal processor. in J Becker, R Sridhar, H Li, U Schlichtmann & M Alioto (eds), Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017. International System on Chip Conference, vol. 2017-September, IEEE Computer Society, pp. 346-350, 30th IEEE International System on Chip Conference, SOCC 2017, Munich, Germany, 17-09-05. https://doi.org/10.1109/SOCC.2017.8226075

Content-aware line-based power modeling methodology for image signal processor. / Chen, Chun Wei; Shieh, Ming-Der; Lu, Juin Ming; Huang, Hsun Lun; Chen, Yao Hua.

Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017. ed. / Jurgen Becker; Ramalingam Sridhar; Hai Li; Ulf Schlichtmann; Massimo Alioto. IEEE Computer Society, 2017. p. 346-350 (International System on Chip Conference; Vol. 2017-September).

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

TY - GEN

T1 - Content-aware line-based power modeling methodology for image signal processor

AU - Chen, Chun Wei

AU - Shieh, Ming-Der

AU - Lu, Juin Ming

AU - Huang, Hsun Lun

AU - Chen, Yao Hua

PY - 2017/12/18

Y1 - 2017/12/18

N2 - Early power modeling and analysis using electronic system-level methodology enables designers to explore energy saving opportunities more efficiently at a higher abstraction level. However, power modeling for third party IPs are challenging due to the limited observability and unknown architecture details. To model the data dependency for blackbox IPs, several works rely on adopting Hamming distance of input data to approximate the switching activity, which might be not enough for modeling complex IPs such as image signal processors (ISP). This work introduces a content-aware line-based power modeling method for ISP by training an associated energy table. To effectively estimate ISP energy consumption which involves many two-dimensional data processing, this work presents a direct energy-mapping strategy using pixel luminance and gradient. Moreover, an iterative box-constrained least-squares estimation and its associated constraint refinement scheme is proposed to increase the robustness of the trained energy table even with limited training data. Simulation results show that the proposed method can reduce at least 11.54% of average error and 55.52% of max error as compared to the existing content-blind power model.

AB - Early power modeling and analysis using electronic system-level methodology enables designers to explore energy saving opportunities more efficiently at a higher abstraction level. However, power modeling for third party IPs are challenging due to the limited observability and unknown architecture details. To model the data dependency for blackbox IPs, several works rely on adopting Hamming distance of input data to approximate the switching activity, which might be not enough for modeling complex IPs such as image signal processors (ISP). This work introduces a content-aware line-based power modeling method for ISP by training an associated energy table. To effectively estimate ISP energy consumption which involves many two-dimensional data processing, this work presents a direct energy-mapping strategy using pixel luminance and gradient. Moreover, an iterative box-constrained least-squares estimation and its associated constraint refinement scheme is proposed to increase the robustness of the trained energy table even with limited training data. Simulation results show that the proposed method can reduce at least 11.54% of average error and 55.52% of max error as compared to the existing content-blind power model.

UR - http://www.scopus.com/inward/record.url?scp=85044329281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044329281&partnerID=8YFLogxK

U2 - 10.1109/SOCC.2017.8226075

DO - 10.1109/SOCC.2017.8226075

M3 - Conference contribution

T3 - International System on Chip Conference

SP - 346

EP - 350

BT - Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017

A2 - Becker, Jurgen

A2 - Sridhar, Ramalingam

A2 - Li, Hai

A2 - Schlichtmann, Ulf

A2 - Alioto, Massimo

PB - IEEE Computer Society

ER -

Chen CW, Shieh M-D, Lu JM, Huang HL, Chen YH. Content-aware line-based power modeling methodology for image signal processor. In Becker J, Sridhar R, Li H, Schlichtmann U, Alioto M, editors, Proceedings - 30th IEEE International System on Chip Conference, SOCC 2017. IEEE Computer Society. 2017. p. 346-350. (International System on Chip Conference). https://doi.org/10.1109/SOCC.2017.8226075