TY - JOUR
T1 - Empirical Power-performance Analysis of Layer-wise CNN Inference on Single Board Computers
AU - Ng, Kuan Yi
AU - Babai, Aalaa M.A.
AU - Tanimoto, Teruo
AU - Kawakami, Satoshi
AU - Inoue, Koji
N1 - Publisher Copyright:
© 2023 Information Processing Society of Japan.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85169468929&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85169468929&partnerID=8YFLogxK
U2 - 10.2197/ipsjjip.31.478
DO - 10.2197/ipsjjip.31.478
M3 - Article
AN - SCOPUS:85169468929
SN - 0387-6101
VL - 31
SP - 478
EP - 494
JO - Journal of information processing
JF - Journal of information processing
ER -