Streaming Convolutional Neural Network FPGA architecture for RFSoC data converters

MacLellan, Andrew and Crockett, Louise H. and Stewart, Robert W. (2023) Streaming Convolutional Neural Network FPGA architecture for RFSoC data converters. In: 21st IEEE Interregional New Circuit and Systems (NEWCAS) Conference, 2023-06-26 - 2023-06-28, John McIntyre Conference Centre.

[thumbnail of MacLellan-etal-NEWCAS2023-Streaming-Convolutional-Neural-Network-FPGA-architecture]
Preview
 Text. Filename: MacLellan_etal_NEWCAS2023_Streaming_Convolutional_Neural_Network_FPGA_architecture.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (639kB)| Preview

Abstract

This paper presents a novel Convolutional Neural Network (CNN) FPGA architecture designed to perform processing of radio data in a streaming manner without interruption. The proposed architecture is evaluated for radio modulation classification tasks implemented on an AMD RFSoC 2x2 development board and operating in real-time. The proposed architecture leverages optimisation such as the General Matrix-to-Matrix (GEMM) transform, on-chip weights, fixed-point arithmetic, and efficient utilisation of FPGA resources to achieve constant processing of a stream of samples. The performance of the proposed architecture is demonstrated through accuracy results obtained during live modulation classification, while operating at a sampling frequency of 128 MHz before decimation. The proposed architecture demonstrates promising results for real-time, time-critical CNN applications.

ORCID iDs

MacLellan, Andrew, Crockett, Louise H. ORCID logoORCID: https://orcid.org/0000-0003-4436-0254 and Stewart, Robert W. ORCID logoORCID: https://orcid.org/0000-0002-7779-8597;
CORE (COnnecting REpositories)