Article: Implementation of quasi-Newton algorithm on FPGA for IoT endpoint devices Journal: International Journal of Security and Networks (IJSN) 2022 Vol.17 No.2 pp.124 - 134 Abstract: With the recent developments in the internet of things (IoT), there has been a significant rapid generation of data. Theoretically, machine learning can help edge devices by providing a better analysis and processing of data near the data source. However, solving the nonlinear optimisation problem is time-consuming for IoT edge devices. A standard method for solving the nonlinear optimisation problems in machine learning models is the Broyden-Fletcher-Goldfarb-Shanno (BFGS-QN) method. Since the field-programmable gate arrays (FPGAs) are customisable, reconfigurable, highly parallel and cost-effective, the present study envisaged the implementation of the BFGS-QN algorithm on an FPGA platform. The use of half-precision floating-point numbers and single-precision floating-point numbers to save the FPGA resources were adopted to implement the BFGS-QN algorithm on an FPGA platform. The results indicate that compared to the single-precision floating-point numbers, the implementation of the mixed-precision BFGS-QN algorithm reduced 27.1% look-up tables, 18.2% flip-flops and 17.9% distributed random memory. Inderscience Publishers - linking academia, business and industry through research

Title: Implementation of quasi-Newton algorithm on FPGA for IoT endpoint devices

Authors: Shizhen Huang; Anhua Guo; Kaikai Su; Siyu Chen; Ruiqi Chen

Addresses: College of Physics and Information Engineering, Fuzhou University, Fuzhou 350000, China ' College of Physics and Information Engineering, Fuzhou University, Fuzhou 350000, China ' College of Physics and Information Engineering, Fuzhou University, Fuzhou 350000, China ' VeriMake Innovation Lab, Nanjing Renmian Integrated Circuit Co., Ltd., Nanjing 210000, China ' VeriMake Innovation Lab, Nanjing Renmian Integrated Circuit Co., Ltd., Nanjing 210000, China

Abstract: With the recent developments in the internet of things (IoT), there has been a significant rapid generation of data. Theoretically, machine learning can help edge devices by providing a better analysis and processing of data near the data source. However, solving the nonlinear optimisation problem is time-consuming for IoT edge devices. A standard method for solving the nonlinear optimisation problems in machine learning models is the Broyden-Fletcher-Goldfarb-Shanno (BFGS-QN) method. Since the field-programmable gate arrays (FPGAs) are customisable, reconfigurable, highly parallel and cost-effective, the present study envisaged the implementation of the BFGS-QN algorithm on an FPGA platform. The use of half-precision floating-point numbers and single-precision floating-point numbers to save the FPGA resources were adopted to implement the BFGS-QN algorithm on an FPGA platform. The results indicate that compared to the single-precision floating-point numbers, the implementation of the mixed-precision BFGS-QN algorithm reduced 27.1% look-up tables, 18.2% flip-flops and 17.9% distributed random memory.

Keywords: internet of things; IoT; edge computing; machine learning; nonlinear optimisation; BFGS-QN; field-programmable gate array; FPGA.

DOI: 10.1504/IJSN.2022.123300

International Journal of Security and Networks, 2022 Vol.17 No.2, pp.124 - 134

Received: 12 Jul 2021
Accepted: 17 Jul 2021
Published online: 08 Jun 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Implementation of quasi-Newton algorithm on FPGA for IoT endpoint devices

Keep up-to-date