Affiliation:
1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
2. Shanghai Engineering Research Center of Intelligent Computing System, Shanghai University, Shanghai 200444, China
Abstract
Convolutional neural networks (CNNs) have made impressive achievements in image classification and object detection. For hardware with limited resources, it is not easy to achieve CNN inference with a large number of parameters without external storage. Model parallelism is an effective way to reduce resource usage by distributing CNN inference among several devices. However, parallelizing a CNN model is not easy, because CNN models have an essentially tightly-coupled structure. In this work, we propose a novel model parallelism method to decouple the CNN structure with group convolution and a new channel shuffle procedure. Our method could eliminate inter-device synchronization while reducing the memory footprint of each device. Using the proposed model parallelism method, we designed a parallel FPGA accelerator for the classic CNN model ShuffleNet. This accelerator was further optimized with features such as aggregate read and kernel vectorization to fully exploit the hardware-level parallelism of the FPGA. We conducted experiments with ShuffleNet on two FPGA boards, each of which had an Intel Arria 10 GX1150 and 16GB DDR3 memory. The experimental results showed that when using two devices, ShuffleNet achieved a 1.42× speed increase and reduced its memory footprint by 34%, as compared to its non-parallel counterpart, while maintaining accuracy.
Funder
Chinese Universities Industry-University-Research Innovation Fund
Natural Science Foundation of Shandong Province
Subject
Computational Mathematics,Computational Theory and Mathematics,Numerical Analysis,Theoretical Computer Science
Reference25 articles.
1. A survey of Convolutional Neural Networks: Analysis, applications, and prospects;Li;IEEE Trans. Neural Netw. Learn. Syst.,2021
2. Ma, Y., and Huang, C. (2021, January 26–28). Facial expression recognition based on deep learning and attention mechanism. Proceedings of the 2021 3rd International Conference on Advanced Information Science and System (AISS 2021), Sanya, China.
3. Image Recognition Based on Multiscale Pooling Deep Convolution Neural Networks;Sang;Complexity,2020
4. Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., and Cong, J. (2015, January 22–24). Optimizing FPGA-based accelerator design for deep convolutional Neural Networks. Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, CA, USA.
5. Gokhale, V., Jin, J., Dundar, A., Martini, B., and Culurciello, E. (2014, January 23–28). A 240 G-ops/S mobile coprocessor for Deep Neural Networks. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献