short-paper

AI Waste Prevention: Time and Power Estimation for Edge Tensor Processing Units: Poster

Authors:

Stefan Reif,

Benedict Herzog,

Judith Hemp,

Wolfgang Schröder-Preikschat,

Timo HönigAuthors Info & Claims

e-Energy '21: Proceedings of the Twelfth ACM International Conference on Future Energy Systems

Pages 300 - 301

https://doi.org/10.1145/3447555.3466579

Published: 22 June 2021 Publication History

Get Access

Abstract

Artificial Intelligence (AI) has changed our daily lives. The evolution from centralised cloud-hosted services towards embedded and mobile devices has shifted the focus from quality-related aspects towards the resource demand of machine learning. Its pervasiveness demands for "green" AI---both the development and the operation of AI models still include significant resource investments in terms of processing time and power demand. In order to prevent such AI Waste, this paper presents Precious, an approach, as well as practical implementation, that estimates execution time and power draw of neural networks (NNs) that execute on a commercially-available off-the-shelf accelerator hardware (i.e., Google Coral Edge TPU). The evaluation of our implementations shows that Precious accurately estimates time and power demand.

References

[1]

M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In Proc. OSDI'16. USENIX, 265--283.

Google Scholar

[2]

S. Cass. 2019. Taking AI to the edge: Google's TPU now comes in a maker-friendly package. IEEE Spectrum 56, 5 (May 2019), 16--17.

Crossref

Google Scholar

[3]

S. Greengard. 2020. AI on Edge. CACM 63, 9 (Aug. 2020), 18--20.

Digital Library

Google Scholar

[4]

Google LLC. 2020. Tensorflow Keras. https://www.tensorflow.org/versions/r2-0/api_docs/python/tf/keras. Acc. 2020-02-20.

Google Scholar

[5]

Google LLC. 2020. USB Accelerator. https://www.coral.ai/products/accelerator. Acc. 2020-02-20.

Google Scholar

[6]

S. S. L. Oskouei, H. Golestani, M. Hashemi, and S. Ghiasi. 2016. CNNdroid: GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android. In Proc. MM'16. ACM, 1201--1205.

Google Scholar

[7]

S. Reif, B. Herzog, J. Hemp, T. Hönig, and W. Schröder-Preikschat. 2020. Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators. In Proc. Challenge'20.

Google Scholar

[8]

R. Schwartz, J. Dodge, N. Smith, and O. Etzioni. 2020. Green AI. CACM 63, 12 (Nov. 2020), 54--63.

Digital Library

Google Scholar

[9]

M. Xu, J. Liu, Y. Liu, F. X. Lin, Y. Liu, and X. Liu. 2019. A First Look at Deep Learning Apps on Smartphones. In Proc. WWW'19. ACM, 2125--2136.

Google Scholar

Cited By

View all

Herzog BReif SHemp JHönig TSchröder-Preikschat W(2022)Resource-demand Estimation for Edge Tensor Processing UnitsACM Transactions on Embedded Computing Systems10.1145/352013221:5(1-24)Online publication date: 8-Oct-2022
https://dl.acm.org/doi/10.1145/3520132
Hemp J(2022)Ausführungszeit und Stromverbrauch von Inferenzen künstlicher neuronaler Netze auf einem TensorprozessorEchtzeit 202110.1007/978-3-658-37751-9_3(13-24)Online publication date: 25-May-2022
https://doi.org/10.1007/978-3-658-37751-9_3

Index Terms

AI Waste Prevention: Time and Power Estimation for Edge Tensor Processing Units: Poster
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Embedded systems
2. Hardware
  1. Power and energy

Recommendations

Resource-demand Estimation for Edge Tensor Processing Units
Machine learning has shown tremendous success in a large variety of applications. The evolution of machine-learning applications from cloud-based systems to mobile and embedded devices has shifted the focus from only quality-related aspects towards the ...
Green AI Quotient : Assessing Greenness of AI-Based Software and the Way Forward
ASE '23: Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering

As the world takes cognizance of AI's growing role in greenhouse gas(GHG) and carbon emissions, the focus of AI research & development is shifting towards inclusion of energy efficiency as another core metric. Sustainability, a core agenda for most ...
A Synthesis of Green Architectural Tactics for ML-Enabled Systems
ICSE-SEIS'24: Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Society

The rapid adoption of artificial intelligence (AI) and machine learning (ML) has generated growing interest in understanding their environmental impact and the challenges associated with designing environmentally friendly ML-enabled systems. While Green ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

e-Energy '21: Proceedings of the Twelfth ACM International Conference on Future Energy Systems

June 2021

528 pages

ISBN:9781450383332

DOI:10.1145/3447555

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 June 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper
Research
Refereed limited

Conference

e-Energy '21

e-Energy '21: The Twelfth ACM International Conference on Future Energy Systems

June 28 - July 2, 2021

Virtual Event, Italy

Acceptance Rates

Overall Acceptance Rate 160 of 446 submissions, 36%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
100
Total Downloads

Downloads (Last 12 months)19
Downloads (Last 6 weeks)6

Reflects downloads up to 22 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Herzog BReif SHemp JHönig TSchröder-Preikschat W(2022)Resource-demand Estimation for Edge Tensor Processing UnitsACM Transactions on Embedded Computing Systems10.1145/352013221:5(1-24)Online publication date: 8-Oct-2022
https://dl.acm.org/doi/10.1145/3520132
Hemp J(2022)Ausführungszeit und Stromverbrauch von Inferenzen künstlicher neuronaler Netze auf einem TensorprozessorEchtzeit 202110.1007/978-3-658-37751-9_3(13-24)Online publication date: 25-May-2022
https://doi.org/10.1007/978-3-658-37751-9_3

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Resource-demand Estimation for Edge Tensor Processing Units

Green AI Quotient : Assessing Greenness of AI-Based Software and the Way Forward

A Synthesis of Green Architectural Tactics for ML-Enabled Systems