ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article A layer-wise frequency scaling for a neural processing unit
Cited 1 time in scopus Download 191 time Share share facebook twitter linkedin kakaostory
Authors
Jaehoon Chung, HyunMi Kim, Kyoungseon Shin, Chun-Gi Lyuh, Yong Cheol Peter Cho, Jinho Han, Youngsu Kwon, Young-Ho Gong, Sung Woo Chung
Issue Date
2022-10
Citation
ETRI Journal, v.44, no.5, pp.849-858
ISSN
1225-6463
Publisher
한국전자통신연구원 (ETRI)
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.4218/etrij.2022-0094
Project Code
22HS5600, Artificial Intelligence Processor Research Laboratory, Kwon Young-Su
Abstract
Dynamic voltage frequency scaling (DVFS) has been widely adopted for run-time power management of various processing units. In the case of neural processing units (NPUs), power management of neural network applications is required to adjust the frequency and voltage every layer to consider the power behavior and performance of each layer. Unfortunately, DVFS is inappropriate for layer-wise run-time power management of NPUs due to the long latency of voltage scaling compared with each layer execution time. Because the frequency scaling is fast enough to keep up with each layer, we propose a layer-wise dynamic frequency scaling (DFS) technique for an NPU. Our proposed DFS exploits the highest frequency under the power limit of an NPU for each layer. To determine the highest allowable frequency, we build a power model to predict the power consumption of an NPU based on a real measurement on the fabricated NPU. Our evaluation results show that our proposed DFS improves frame per second (FPS) by 33% and saves energy by 14% on average, compared with DVFS.
KSP Keywords
Dynamic Frequency Scaling, Dynamic voltage and frequency scaling, Neural network applications, Neural processing, Power Consumption, Power Limit, Power behavior, Power model, Processing unit, Run time, Voltage scaling
This work is distributed under the term of Korea Open Government License (KOGL)
(Type 4: : Type 1 + Commercial Use Prohibition+Change Prohibition)
Type 4: