作者:
Lv, Ang
(Lv, Ang.)
|
Wang, Chao
(Wang, Chao.)
|
Hou, Ligang
(Hou, Ligang.)
|
Zeng, Zhiyong
(Zeng, Zhiyong.)
|
Guo, Jia
(Guo, Jia.)
|
Jiang, Nan
(Jiang, Nan.)
展开
摘要:
In this paper, a floating point multiplication and accumulation operator based on FPGA is designed for neural network calculation, and a custom 32 bit floating-point data format is used to change the amount of computation by changing the overall structure of the data, and the performance of the operator is optimized. Finally, the simulation results in FPGA are given to verify the correctness of the design. The design saves the resources by comparing the floating point operation with the common algorithm of 32 bit floating-point data of the IEEE standard. © 2018 IEEE.
关键词:
Integrated circuit design
Field programmable gate arrays (FPGA)
Microsystems
IEEE Standards
Digital arithmetic
Integrated circuits
会议名称
3rd IEEE International Conference on Integrated Circuits and Microsystems, ICICM 2018
分类号
714.2 Semiconductor Devices and Integrated Circuits - 721.1 Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory - 721.2 Logic Elements
资助项目类型
ACKNOWLEDGEMENT This work is supported by Inner Mongolia Science and Technology Project named Research and Development of Smart Monitoring System for Inner Mongolia Ecological Animal Husbandry Based on Internet of Things.