A Modified KNN Algorithm for High-Performance Computing on FPGA of Real-Time m-QAM Demodulators

A methodology for scalable and concurrent real-time implementation of highly recurrent algorithms is presented and experimentally validated using the AWS-FPGA. This paper presents a parallel implementation of a KNN algorithm focused on the m-QAM demodulators using high-level synthesis for fast prototyping, parameterization, and scalability of the design. The proposed design shows the successful implementation of the KNN algorithm for interchannel interference mitigation in a 3 × 16 Gbaud 16-QAM Nyquist WDM system. Additionally, we present a modified version of the KNN algorithm in which comparisons among data symbols are reduced by identifying the closest neighbor using the rule of the 8-connected clusters used for image processing. Real-time implementation of the modified KNN on a Xilinx Virtex UltraScale+ VU9P AWS-FPGA board was compared with the results obtained in previous work using the same data from the same experimental setup but offline DSP using Matlab. The results show that the difference is negligible below FEC limit. Additionally, the modified KNN shows a reduction of operations from 43 percent to 75 percent, depending on the symbol’s position in the constellation, achieving a reduction 47.25% reduction in total computational time for 100 K input symbols processed on 20 parallel cores compared to the KNN algorithm.

[1]  Luca Barletta,et al.  Machine-learning method for quality of transmission prediction of unestablished lightpaths , 2018, IEEE/OSA Journal of Optical Communications and Networking.

[2]  Jason Cong,et al.  AutoDSE: Enabling Software Programmers to Design Efficient FPGA Accelerators , 2020, ACM Trans. Design Autom. Electr. Syst..

[3]  Jhon James Granada Torres,et al.  Radio-over-Fiber signal demodulation in the presence of non-Gaussian distortions based on subregion constellation processing , 2019 .

[4]  Torsten Hoefler,et al.  Transformations of High-Level Synthesis Codes for High-Performance Computing , 2018, IEEE Transactions on Parallel and Distributed Systems.

[5]  Jie Yang,et al.  An SVM-Based Detection for Coherent Optical APSK Systems With Nonlinear Phase Noise , 2014, IEEE Photonics Journal.

[6]  Qi Zhang,et al.  Robust weighted K-means clustering algorithm for a probabilistic-shaped 64QAM coherent optical communication system. , 2019, Optics express.

[7]  Yi Cai,et al.  Approaching Terabits Per Carrier Metro-Regional Transmission Using Beyond-100GBd Coherent Optics With Probabilistically Shaped DP-64QAM Modulation , 2019, Journal of Lightwave Technology.

[8]  Mathieu Chagnon,et al.  Optical Communications for Short Reach , 2019, 2018 European Conference on Optical Communication (ECOC).

[9]  Ryan Kastner,et al.  Parallel Programming for FPGAs , 2018, ArXiv.

[10]  Vijay Vusirikala,et al.  Field and lab experimental demonstration of nonlinear impairment compensation using neural networks , 2019, Nature Communications.

[11]  Horácio C. Neto,et al.  kNN-STUFF: kNN STreaming Unit for Fpgas , 2019, IEEE Access.

[12]  Mingyi Gao,et al.  Intelligent adaptive coherent optical receiver based on convolutional neural network and clustering algorithm. , 2018, Optics express.

[13]  Tsutomu Maruyama,et al.  Performance comparison of FPGA, GPU and CPU in image processing , 2009, 2009 International Conference on Field Programmable Logic and Applications.

[14]  Jun Peng,et al.  An Efficient KNN Algorithm Implemented on FPGA Based Heterogeneous Computing System Using OpenCL , 2015, 2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines.

[15]  Zuyuan He,et al.  Machine Learning for Nonlinearity Mitigation in CAP Modulated Optical Interconnect System by Using K-Nearest Neighbour Algorithm , 2016, 2016 Asia Communications and Photonics Conference (ACP).

[16]  Jekan Thangavelautham,et al.  FPGA architecture for deep learning and its application to planetary robotics , 2017, 2017 IEEE Aerospace Conference.

[17]  Min Zhang,et al.  Nonlinearity Mitigation Using a Machine Learning Detector Based on $k$ -Nearest Neighbors , 2016, IEEE Photonics Technology Letters.

[18]  Kaiyuan Jiang,et al.  A Novel Digital Modulation Recognition Algorithm Based on Deep Convolutional Neural Network , 2020, Applied Sciences.

[19]  J. Kahn,et al.  Signal Design and Detection in Presence of Nonlinear Phase Noise , 2007, Journal of Lightwave Technology.

[20]  Min Zhang,et al.  Intelligent constellation diagram analyzer using convolutional neural network-based deep learning. , 2017, Optics express.

[21]  Jhon James Granada Torres,et al.  KNN-based Demodulation in gridless Nyquist-WDM Systems affected by Interchannel Interference , 2019, OSA Advanced Photonics Congress (AP) 2019 (IPR, Networks, NOMA, SPPCom, PVLED).

[22]  J. A. Connelly.  Integrated Circuits , .

[23]  Elias S. Manolakos,et al.  Parallel architectures for the kNN classifier -- design of soft IP cores and FPGA implementations , 2013, TECS.

[24]  Min Zhang,et al.  Optimized Compression for Implementing Convolutional Neural Networks on FPGA , 2019, Electronics.

[25]  Tao Xie,et al.  A Memory-Access-Efficient Adaptive Implementation of kNN on FPGA through HLS , 2019, 2019 IEEE 37th International Conference on Computer Design (ICCD).

[26]  Taisuke Boku,et al.  Performance Evaluation of OpenCL-Enabled Inter-FPGA Optical Link Communication Framework CIRCUS and SMI , 2021, HPC Asia.

[27]  Jie Yang,et al.  Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios , 2019, IEEE Transactions on Vehicular Technology.