Future of Information and Communication Conference (FICC) 2024
4-5 April 2024
Publication Links
IJACSA
Special Issues
Future of Information and Communication Conference (FICC)
Computing Conference
Intelligent Systems Conference (IntelliSys)
Future Technologies Conference (FTC)
International Journal of Advanced Computer Science and Applications(IJACSA), Volume 14 Issue 12, 2023.
Abstract: To overcome challenges associated with deploying Convolutional Neural Networks (CNNs) on edge computing devices with limited memory and computing resources, we propose a mixed-precision CNN calculation method on a Field Programmable Gate Array (FPGA). This approach involves a collaborative design encompassing both software and hardware aspects. Initially, we devised a CNN quantization method tailored for the fixed-point operation characteristics of FPGA, addressing the computational challenges posed by floating-point parameters. We introduce a bit-width strategy search algorithm that assigns bit-widths to each layer based on CNN loss variation induced by quantization. Through retraining, this strategy mitigates the degradation in CNN inference accuracy. For FPGA acceleration design, we employ a flow processing architecture with multiple Processing Elements (PEs) to support mixed-precision CNNs. Our approach incorporates a folding design method to implement shared PEs between layers, significantly reducing FPGA resource usage. Furthermore, we designed a data reading method, incorporating a register set buffer between memory and processing elements to alleviate issues related to mismatched data reading and computing speeds. Our implementation of the mixed-precision ResNet20 model on the Kintex-7 Eco R2 development board achieves an inference accuracy of 91.68% and a computing speed 4.27 times faster than the Central Processing Unit (CPU) on the CIFAR-10 dataset, with an accuracy drop of only 1.21%. Compared to a unified 16-bit FPGA accelerator design method, our proposed approach demonstrates an 89-fold increase in computing speed while maintaining similar accuracy.
Yizhi He, Wenlong Liu, Muhammad Tahir, Zhao Li, Shaoshuang Zhang and Hussain Bux Amur, “Research on Efficient CNN Acceleration Through Mixed Precision Quantization: A Comprehensive Methodology” International Journal of Advanced Computer Science and Applications(IJACSA), 14(12), 2023. http://dx.doi.org/10.14569/IJACSA.2023.0141282
@article{He2023,
title = {Research on Efficient CNN Acceleration Through Mixed Precision Quantization: A Comprehensive Methodology},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2023.0141282},
url = {http://dx.doi.org/10.14569/IJACSA.2023.0141282},
year = {2023},
publisher = {The Science and Information Organization},
volume = {14},
number = {12},
author = {Yizhi He and Wenlong Liu and Muhammad Tahir and Zhao Li and Shaoshuang Zhang and Hussain Bux Amur}
}
Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.