@article{oai:ipsj.ixsq.nii.ac.jp:00227194,
 author = {Kuan, Yi Ng and Aalaa, M.A. Babai and Teruo, Tanimoto and Satoshi, Kawakami and Koji, Inoue and Kuan, Yi Ng and Aalaa, M.A. Babai and Teruo, Tanimoto and Satoshi, Kawakami and Koji, Inoue},
 issue = {1},
 journal = {情報処理学会論文誌コンピューティングシステム（ACS）},
 month = {Jul},
 note = {This paper analyzes the impact of input sparsity and DFS/DVFS configurations for single-board computers on the execution time, power, and energy of each VGG16 layer as the first step towards efficient CNN inference on single-board computers. For this purpose, we first develop a power and execution time measurement environment and perform experiments using Raspberry Pi 4 and NVIDIA Jetson Nano. Our results show that clock frequency strongly correlates with execution time and power. Inversely, input sparsity has a weak correlation with execution time and power. Then, we show that a coarse-grained DVFS model can explain over 96% of the variations in the power of each VGG16 layer even when sets of clock frequency and voltage on the single-board computer are unavailable.
------------------------------
This is a preprint of an article intended for publication Journal of
Information Processing(JIP). This preprint should not be cited. This
article should be cited as: Journal of Information Processing Vol.31(2023) (online)
------------------------------, This paper analyzes the impact of input sparsity and DFS/DVFS configurations for single-board computers on the execution time, power, and energy of each VGG16 layer as the first step towards efficient CNN inference on single-board computers. For this purpose, we first develop a power and execution time measurement environment and perform experiments using Raspberry Pi 4 and NVIDIA Jetson Nano. Our results show that clock frequency strongly correlates with execution time and power. Inversely, input sparsity has a weak correlation with execution time and power. Then, we show that a coarse-grained DVFS model can explain over 96% of the variations in the power of each VGG16 layer even when sets of clock frequency and voltage on the single-board computer are unavailable.
------------------------------
This is a preprint of an article intended for publication Journal of
Information Processing(JIP). This preprint should not be cited. This
article should be cited as: Journal of Information Processing Vol.31(2023) (online)
------------------------------},
 title = {Empirical Power-performance Analysis of Layer-wise CNN Inference on Single Board Computers},
 volume = {16},
 year = {2023}
}