A 5.2-GS/s 8-Parallel 1024-Point MDC FFT | IEEE Conference Publication | IEEE Xplore

A 5.2-GS/s 8-Parallel 1024-Point MDC FFT


Abstract:

This paper presents an efficient 8-parallel 1024-point multi-path delay commutator (MDC) fast Fourier transform (FFT) implementation on a field-programmable gate array (F...Show More

Abstract:

This paper presents an efficient 8-parallel 1024-point multi-path delay commutator (MDC) fast Fourier transform (FFT) implementation on a field-programmable gate array (FPGA). The selection of the FFT algorithm and the data orders allow for obtaining an architecture with 23 non-trivial rotators, which is the minimum number achieved so far. Additionally, the non-general rotators in the architecture are trivial rotators, constant rotators, and 1-rots, which require very few resources to be implemented. The deep pipelining in the architecture allows for reaching a throughput of 5.2 GS/s.
Date of Conference: 15-17 November 2023
Date Added to IEEE Xplore: 11 December 2023
ISBN Information:

ISSN Information:

Conference Location: Málaga, Spain

Funding Agency:


I. Introduction

The fast Fourier transform (FFT) is one of the most commonly used algorithms in digital signal processing applications such as radio astronomy [1] and wireless communications [2]. In wireless communications, future 6G systems will demand higher data rates [3]. In order to satisfy the demands of 6G, efficient hardware architectures are required [4] – [15]. There are three main types of FFT hardware architectures: Memory-based [13], [14], fully parallel [15] and pipelined [4] – [10]. Memory-based FFT architectures consist of one or more processing elements and several banks of memory. They process the FFT iteratively and can not receive new data while an FFT is being computed. Fully parallel FFT architectures are the direct implementation of the flow graph of an FFT algorithm. They obtain the maximum throughput but also require a large amount of resources to be implemented. Pipelined FFT architectures consist of a series of stages that include butterflies and rotators. They allow to process a continuous flow of data without requiring too many resources.

Contact IEEE to Subscribe

References

References is not available for this document.