Abstract
Deep Neural Networks (DNNs) have been recently in the focus of interest owing to their high-quality results in various application domains of big data analytics. The lack of end-to-end toolchains that can automatically optimize and translate a DNN algorithm, usually implemented in high-level languages, on FPGA-based platform hinders software developers to exploit such platforms. A few available toolchains, namely Xilinx DPU, have been optimized for computational expensive applications, e.g., real-time image and video processing, and therefore they introduce large performance overhead on lightweight applications, e.g., sensor-driven decision analytics. In this paper, we introduce the FLight framework to fully automatize the acceleration of lightweight DNN algorithms on FPGA-based embedded platforms. The framework takes a trained model in TensorFlow/Keras as input and generates an optimized synthesizable C++ version and maps it on the target platform using HLS tools. FLight is an easy-to-use framework and does not require deep knowledge of embedded system design since it automatically performs all the required mapping steps. FLight supports the acceleration of various deep learning algorithms, e.g., Feed-Forward Neural networks (FFNNs), Convolutional Neural Networks (CNNs), and sequential models like Recurrent Neural Networks (RNNs). We evaluated the applicability of FLight with various DNN models on both academic and industrial datasets. As a case study, we exploited the FLight framework for wind turbine condition monitoring using an industrial dataset provided by Weidmüller Monitoring Systems GmbH. The experimental results revealed the 40 times speedup compared to the Xilinx DPU framework.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
BLADEcontrol condition monitoring system. Weidmüller Monitoring Systems GmbH. https://mdcop.weidmueller.com/mediadelivery/asset/900_87890
Keras: The Python Deep Learning API. https://keras.io
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press, Cambridge (2016)
Kusiak, A., Verma, A.: Analyzing bearing faults in wind turbines: a data-mining approach. Renewable Energy 48, 110–116 (2012)
Lu, D., Qiao, W.: Frequency demodulation-aided condition monitoring for drivetrain gearboxes. In: 2013 IEEE Transportation Electrification Conference and Expo (ITEC), pp. 1–6. IEEE (2013)
Mohammadi, H.G., et al.: DeepWind: an accurate wind turbine condition monitoring framework via deep learning on embedded platforms. In: 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), vol. 1, pp. 1431–1434. IEEE (2020)
Mousouliotis, P.G., Petrou, L.P.: CNN-grinder: from algorithmic to high-level synthesis descriptions of CNNs for low-end-low-cost FPGA SoCs. Microprocess. Microsyst. 73, 102990 (2020)
Oyague, F., Butterfield, C., Sheng, S.: NREL gearbox reliability collaborative analysis round robin. Technical report, National Renewable Energy Lab. (NREL), Golden, CO, United States (2009)
Qiu, J., et al.: Going deeper with embedded FPGA platform for convolutional neural network. In: Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 26–35 (2016)
Schlechtingen, M., Santos, I.F., Achiche, S.: Wind turbine condition monitoring based on SCADA data using normal behavior models. Part 1: system description. Appl. Soft Comput. 13(1), 259–270 (2013)
Steinarsson, S.: Downsampling time series for visual representation. Ph.D. thesis (2013)
Stone, J.E., Gohara, D., Shi, G.: OpenCL: a parallel programming standard for heterogeneous computing systems. Comput. Sci. Eng. 12(3), 66 (2010)
Venieris, S.I., Bouganis, C.S.: fpgaConvNet: mapping regular and irregular convolutional neural networks on FPGAs. IEEE Trans. Neural Netw. Learn. Syst. 30(2), 326–342 (2018)
Wirbel, L.: Xilinx SDAccel: a unified development environment for tomorrow’s data center. The Linley Group Inc, p. 24 (2014)
Xing, Y., et al.: DNNVM: end-to-end compiler leveraging heterogeneous optimizations on FPGA-based CNN accelerators. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 39(10), 2668–2681 (2019)
Zhang, C., Sun, G., Fang, Z., Zhou, P., Pan, P., Cong, J.: Caffeine: toward uniformed representation and acceleration for deep convolutional neural networks. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 38(11), 2072–2085 (2018)
Zhu, J., Wang, L., Liu, H., Tian, S., Deng, Q., Li, J.: An efficient task assignment framework to accelerate DPU-based convolutional neural network inference on FPGAs. IEEE Access 8, 83224–83237 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Mohammadi, H.G. et al. (2021). FLight: FPGA Acceleration of Lightweight DNN Model Inference in Industrial Analytics. In: Kamp, M., et al. Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2021. Communications in Computer and Information Science, vol 1524. Springer, Cham. https://doi.org/10.1007/978-3-030-93736-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-93736-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93735-5
Online ISBN: 978-3-030-93736-2
eBook Packages: Computer ScienceComputer Science (R0)