TY - GEN
T1 - Convolutional neural network implementations using Vitis AI
AU - Ushiroyama, Akihiko
AU - Watanabe, Minoru
AU - Watanabe, Nobuya
AU - Nagoya, Akira
N1 - Funding Information:
This research was partly supported by the Initiatives for Atomic Energy Basic and Generic Strategic Research No.
Funding Information:
JPJA19F19209710 and the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Scientific Research(B), No. 21H03407.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Recently, Xilinx has provided a field programmable gate array (FPGA)-based Vitis AI development environment, which is a deep learning framework to accel-erate AI operations and to seek a suitable neural network construction for a target application. We have implemented convolutional neural networks of three types onto the Vitis AI development environment and then we have evaluated their performance, power consumption, design man-hours, and so on. Results confirmed the Vitis AI benefits. Most notably, the FPGA platform power consumption is 4.96 times less than that of a GPU.
AB - Recently, Xilinx has provided a field programmable gate array (FPGA)-based Vitis AI development environment, which is a deep learning framework to accel-erate AI operations and to seek a suitable neural network construction for a target application. We have implemented convolutional neural networks of three types onto the Vitis AI development environment and then we have evaluated their performance, power consumption, design man-hours, and so on. Results confirmed the Vitis AI benefits. Most notably, the FPGA platform power consumption is 4.96 times less than that of a GPU.
KW - Convolutional Neural Network (CNN)
KW - FPGA
KW - Vitis AI
UR - http://www.scopus.com/inward/record.url?scp=85127670992&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127670992&partnerID=8YFLogxK
U2 - 10.1109/CCWC54503.2022.9720794
DO - 10.1109/CCWC54503.2022.9720794
M3 - Conference contribution
AN - SCOPUS:85127670992
T3 - 2022 IEEE 12th Annual Computing and Communication Workshop and Conference, CCWC 2022
SP - 365
EP - 371
BT - 2022 IEEE 12th Annual Computing and Communication Workshop and Conference, CCWC 2022
A2 - Paul, Rajashree
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2022
Y2 - 26 January 2022 through 29 January 2022
ER -