Design and Implementation of Convolutional Neural Network Accelerator Based on FPGA
DOI:
https://doi.org/10.54097/fcis.v3i1.6354Keywords:
Field Programmable Gate Array, Convolutional Neural Network, Parallelization, AcceleratorAbstract
Convolutional neural network, as a kind of feed-forward neural network, has been widely used in image recognition, speech processing and other fields in recent years. In this paper, an FPGA-based CNN gas pedal is designed to solve the problem of slow running and high-power consumption of CNN on resource-constrained hardware. The design invokes multi-stage pipeline parallel processing technology to accelerate convolutional operations; quantifies network parameters from 32-bit floating-point to 8-bit fixed-point while guaranteeing CNN accuracy, and uses data multiplexing to reduce resource consumption. Experimental results show that the design is 10 times faster than the intel i7-8700 and consumes only 1% of the power of the RTX 2060 at 50MHz.
Downloads
References
Mao YH, Gui XL, Li QIAN, He XS. Research on deep learning application techniques [J]. Computer Application Research, 2016, 33(11): 3201-3205.
Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks [C]. In Advances in neural information processing systems.2012: 1097–1105.
Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions [C]. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1–9.
Xu Z, Yang Y, Hauptmann A G. A discriminative CNN video representation for event detection [C]. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1798–1807.
Karpathy A, Toderici G, Shetty S, et al. Large-scale video classification with convolutional neural networks [C]. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2014: 1725–1732.
Dos Santos C, Gatti M. Deep convolutional neural networks for sentiment analysis of short texts [C]. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. 2014: 69–78.
Abdel-Hamid O, Mohamed A-r, Jiang H, et al. Convolutional neural networks for speech recognition [J]. IEEE/ACM Transactions on audio, speech, and language processing, 2014, 22 (10): 1533–1545.
Jouppi N P, Young C, Patil N, et al. In-Datacenter Performance Analysis of a Tensor Processing Unit [J]. 2017.
Patterson, David A, Hennessy, John L, Goldberg, David. Computer architecture: a quantitative approach[M]// Computer Architecture: A Quantitative Approach. Morgan Kaufmann Publishers Inc. 2008.
Zhao BY. Research on the design and implementation of hardware accelerator based on convolutional neural network[D]. Harbin Institute of Technology,2018.
Ye J, Hu Y, Li X. Hardware Trojan in FPGA CNN Accelerator[C]//2018 IEEE 27th Asian Test Symposium (ATS). IEEE, 2018: 68-73.
Gong J, Zhao S, He h, Deng N. FPGA-based quantized CNN acceleration system design[J].Computer Engineering ,2022,48(03):170-174+196.
Ahmad S, Sadiq M, Aiman E. FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review. [J]. IEEE Access, 2019, 7: 7823-7859.
MIYAMA M. FPGA Implementation of 3-Bit Quantized Multi-Task CNN for Contour Detection and Disparity Estimation[J]. IEICE Transactions on Information and Systems,2022, E105.D(2).
Chen Y, Tushar K, Joel S, et al. Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks. [J]. J. Solid-State Circuits, 2017, 52(1): 127-138.
