Nona: Accurate Power Prediction Model Using Neural Networks
Article No.: 38, Pages 1 - 6
Abstract
This paper proposes a neural-network-based power model, Nona, that accurately predicts the power consumption of heterogeneous CPUs on a commercial mobile device. With aggressive on-device power management in action, it becomes increasingly challenging to make accurate power predictions for diverse applications. To overcome the limitations of the existing power models based on linear regression, Nona uses a lightweight neural network with a small number of performance monitoring counters (PMCs) chosen from a system analysis and a loss function designed for power prediction. Experiments on Google Pixel 6 show that Nona has a 3.4% average prediction error, improving on prior work by 2.6x.
References
[1]
Arm® Cortex®-A55 Core Technical Reference Manual, Arm Limited, June 2023, Available: https://developer.arm.com/documentation/100442/latest/.
[2]
Arm® Cortex®-A76 Core Technical Reference Manual, Arm Limited, June 2023, Available: https://developer.arm.com/documentation/100798/latest/.
[3]
Arm® Cortex®-X1 Core Technical Reference Manual, Arm Limited, June 2023, Available: https://developer.arm.com/documentation/101433/latest/.
[4]
S. Das, J. Werner, M. Antonakakis, M. Polychronakis, and F. Monrose, "SoK: The Challenges, Pitfalls, and Perils of Using Hardware Performance Counters for Security," IEEE Symposium on Security and Privacy, Sept. 2019, pp. 20--38.
[5]
G. Dhiman, K. Mihic, and T. Rosing, "A System for Online Power Prediction in Virtualized Environments Using Gaussian Mixture Models," ACM/IEEE Design Automation Conference, June 2010, pp. 807--812.
[6]
C. Dormann, J. Elith, S. Bacher, C. Buchmann, G. Carl, G. Carré, J. Marquéz, B. Gruber, B. Lafourcade, P. Leitão, T. Münkemüller, C. McClean, P. Osborne, B. Reineking, B. Schröder, A. Skidmore, D. Zurell, and S. Lautenbach, "Collinearity: A Review of Methods to Deal with It and A Simulation Study Evaluating Their Performance," Ecography, vol. 36, no. 1, pp. 27--46, May 2013.
[7]
C. King, "stress-ng," Available: https://github.com/ColinIanKing/stress-ng.
[8]
S. Li, J. Ahn, R. Strong, J. Brockman, D. Tullsen, and N. Jouppi, "McPAT: An Integrated Power, Area, and Timing Modeling Framework for Multicore and Manycore Architectures," International Symposium on Microarchitecture, Dec. 2009, pp. 469--480.
[9]
W. Lin, G. Wu, X. Wang, and K. Li, "An Artificial Neural Network Approach to Power Consumption Model Construction for Servers in Cloud Data Centers," IEEE Transactions on Sustainable Computing, vol. 5, no. 3, pp. 329--340, July 2020.
[10]
F. Nie, H. Huang, X. Cai, and C. Ding, "Efficient and Robust Feature Selection via Joint l2,1-Norms Minimization," Advances in Neural Information Processing Systems, Dec. 2010, pp. 1--9.
[11]
F. Oboril, J. Ewert, and M. Tahoori, "High-Resolution Online Power Monitoring for Modern Microprocessors," Design, Automation & Test in Europe Conference Exhibition, Mar. 2015, pp. 265--268.
[12]
M. Sagi, N. Doan, M. Rapp, T. Wild, J. Henkel, and A. Herkersdorf, "A Lightweight Nonlinear Methodology to Accurately Model Multicore Processor Power," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, no. 11, pp. 3152--3164, Oct. 2020.
[13]
M. Walker, S. Diestelhorst, A. Hansson, A. Das, S. Yang, B. Al-Hashimi, and G. Merrett, "Accurate and Stable Run-Time Power Modeling for Mobile and Embedded CPUs," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 36, no. 1, pp. 106--119, Jan. 2017.
[14]
S. Xi, H. Jacobson, P. Bose, G. Wei, and D. Brooks, "Quantifying Sources of Error in McPAT and Potential Impacts on Architectural Studies," IEEE International Symposium on High-Performance Computer Architecture, Feb. 2015, pp. 577--589.
[15]
Y. Zhang, B. Kang, B. Hooi, S. Yan, and J. Feng, "Deep Long-Tailed Learning: A Survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 9, pp. 10 795--10 816, Sept. 2023.
Index Terms
- Nona: Accurate Power Prediction Model Using Neural Networks
Recommendations
Predicting Server Power Consumption from Standard Rating Results
ICPE '19: Proceedings of the 2019 ACM/SPEC International Conference on Performance EngineeringData center providers and server operators try to reduce the power consumption of their servers. Finding an energy efficient server for a specific target application is a first step in this regard. Estimating the power consumption of an application on ...
Power Issues Related to Branch Prediction
HPCA '02: Proceedings of the 8th International Symposium on High-Performance Computer ArchitectureThis paper explores the role of branch predictor organization in power/energy/performance tradeoffs for processor design. We find that as a general rule, to reduce overall energy consumption in the processor it is worthwhile to spend more power in the ...
Power-Aware Branch Prediction: Characterization and Design
Abstract--This paper uses Wattch and the SPEC 2000 integer and floating-point benchmarks to explore the role of branch predictor organization in power/energy/performance trade offs for processor design. Even though the direction predictor by itself ...
Comments
Information & Contributors
Information
Published In
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 November 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Samsung Electronics Co., Ltd
- National Research Foundation of Korea
- Korea Evaluation Institute of Industrial Technology
Conference
DAC '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,770 of 5,499 submissions, 32%
Upcoming Conference
DAC '25
- Sponsor:
- sigda
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 223Total Downloads
- Downloads (Last 12 months)223
- Downloads (Last 6 weeks)87
Reflects downloads up to 02 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in