@article{LIU2025, 
author = {Qiang LIU and Wei YIN and Kai LI},
title = {Image preprocessing acceleration method based on RISC-V vector extension},
year = {2025},
journal = {Journal of Beijing University of Aeronautics and Astronautics},
volume = {51},
number = {4},
pages = {1074-1084},
keywords = {convolutional neural network, preprocessing, RISC-V, vector extension, algorithm acceleration},
url = {https://www.sciopen.com/article/10.13700/j.bh.1001-5965.2023.0208},
doi = {10.13700/j.bh.1001-5965.2023.0208},
abstract = {As the pre-order step of convolutional neural network (CNN) computing, image preprocessing is indispensable but time-consuming. To accelerate image preprocessing, a method based on RISC-V vector extension was proposed to accelerate eleven image preprocessing algorithms such as gray scale processing, standardization, and Gaussian filtering. Firstly, eleven image preprocessing algorithms were classified into four categories according to the computing mode, and acceleration schemes for the preprocessing algorithms were designed based on RISC-V vector extension. In order to further improve the performance, six customized vector instructions were added. The customized instructions were implemented by modifying the compiler and designing the hardware module. Finally, a field programmable gate array (FPGA) was used for testing, and the impact of vector processor configuration on performance and resource consumption was analyzed. The results showed that the proposed method achieves 3.13–9.97 times speedup compared with scalar processors, which effectively solves the performance bottleneck problem of image preprocessing in deep learning.}
}