一种流水线架构的2D-FFT加速引擎设计

doi:10.16257/j.cnki.1681-1070.2025.0166

电子与封装 ›› 2025, Vol. 25 ›› Issue (12): 120302 . doi: 10.16257/j.cnki.1681-1070.2025.0166

一种流水线架构的2D-FFT加速引擎设计

王培富¹，李振涛^1,2

1.长沙理工大学物理与电子科学学院，长沙 410114；2.湖南毂梁微电子有限公司，长沙 410003

收稿日期:2025-08-03 出版日期:2025-12-26 发布日期:2025-08-28
作者简介:王培富（2002—），男，湖南省衡阳市人，硕士研究生，主要研究方向为数字集成电路设计。

Design of a 2D-FFT Acceleration Engine with Pipelined Architecture

WANG Peifu¹, LI Zhentao^{1, 2}

1.School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha,410114, China; 2.Hunan Guliang Microelectronics Co.,Ltd., Changsha 410003, China

Received:2025-08-03 Online:2025-12-26 Published:2025-08-28

摘要/Abstract

摘要： 为满足毫米波雷达信号处理中对距离维和速度维进行高效、小点数二维快速傅里叶变换（2D-FFT）的需求，设计一种基于单路径延迟反馈的流水线架构2D-FFT加速引擎。该引擎在每级前引入数据选通模块，支持可配置的点数规模为M×N≤2 048。结果表明，该设计能够实现2D-FFT点数的灵活配置。所有2D-FFT运算结果的绝对误差＜2.5，相对误差＜0.5%，精度满足使用需求。与传统2D-FFT运算相比，该设计的计算效率显著提高。

关键词: 流水线, 单路径延迟反馈, 2D-FFT, 可配置点数

Abstract: To meet the demand for efficient, small-point two-dimensional fast Fourier transform (2D-FFT) in the distance and velocity dimensions of millimeter-wave radar signal processing, a pipelined architecture 2D-FFT acceleration engine based on single-path delay feedback is designed. This engine incorporates a data pick-and-pass module before each stage and supports configurable point sizes of M×N≤2 048. Results demonstrate that this design enables flexible configuration of 2D-FFT points. The absolute error of all 2D-FFT operation results is less than 2.5, and the relative error is less than 0.5%, which meets the accuracy requirements. Compared with the traditional 2D-FFT operation, the design achieves significantly improved computational efficiency.

Key words: pipeline, single-path delay feedback, 2D-FFT, configurable point

中图分类号:

TN431.2

王培富，李振涛. 一种流水线架构的2D-FFT加速引擎设计[J]. 电子与封装, 2025, 25(12): 120302 .

WANG Peifu, LI Zhentao. Design of a 2D-FFT Acceleration Engine with Pipelined Architecture[J]. Electronics & Packaging, 2025, 25(12): 120302 .

参考文献

[1] VARGAS J, ALSWEISS S, TOKER O, et al. An overview of autonomous vehicles sensors and their vulnerability to weather conditions[J]. Sensors, 2021, 21(16): 5397.
[2] GOUROVA R, KRASNOV O, YAROVOY A. Analysis of rain clutter detections in commercial 77 GHz automotive radar[C]// 2017 European Radar Conference (EURAD), Nuremberg, Germany, 2017: 25-28.
[3] HEO J, JUNG Y, LEE S, et al. FPGA implementation of an efficient FFT processor for FMCW radar signal processing[J]. Sensors, 2021, 21(19): 6443.
[4] SAPONARA S, NERI B. Real-time FPGA-based radar imaging for smart mobility systems[C]// Real-Time Image and Video Processing 2016, Brussels, Belgium, 2016: 989702.
[5] MEINL F, SCHUBERT E, KUNERT M, et al. Realtime FPGA-based processing unit for a high-resolution automotive MIMO radar platform[C]// 2015 European Radar Conference (EuRAD), Paris, France, 2015: 213-216.
[6] HAKOBYAN G, YANG B. High-performance automotive radar: a review of signal processing algorithms and modulation schemes[J]. IEEE Signal Processing Magazine, 2019, 36(5): 32-44.
[7] JIA P C, GAO S D, LI Z Y, et al. Physics-embedded neural state-space module for single-shot lens-free on-chip microscopy[J]. Optics Letters, 2025, 50(20): 6357-6360.
[8] UNDERWOOD K D, SASS R R, LIGON W B. Acceleration of a 2D-FFT on an adaptable computing cluster[C]//
The 9th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, Rohnert Park, CA, USA, 2001: 180-189.
[9] KIM Y J, LEE H S. The implementation of 2D FFT using multiple topology on 4 × 4 Torus[C]// 2009 9th International Symposium on Communications and Information Technology, Icheon, South Korea, 2009: 615-620.
[10] 才华, 陈广秋, 刘广文, 等. 基于FPGA架构的可变点FFT处理器设计与实现[J]. 吉林大学学报(理学版), 2018, 56(1): 151-158.
[11] CHEN J Y, LEI Y W, PENG Y X, et al. Configurable floating-point FFT accelerator on FPGA based multiple-rotation CORDIC[J]. Chinese Journal of Electronics, 2016, 25(6): 1063-1070.
[12] 王谛, 石嵩, 吴铁彬, 等. 一种高性能超长点数浮点FFT加速器设计[J]. 计算机研究与发展, 2021, 58(6): 1192-1203.
[13] TANG S N, LIAO C H, CHANG T Y. An area- and energy-efficient multimode FFT processor for WPAN/WLAN/WMAN systems[J]. IEEE Journal of Solid-State Circuits, 2012, 47(6): 1419-1435.
[14] 金国栋, 刘向明, 陶智, 等. 基2与混合基快速Fourier变换算法性能比较[J]. 计算机与数字工程, 2010, 38(3): 25-27.
[15] 侯晓晨, 孟骁, 陈昊. 基于FPGA的混合基FFT算法设计与实现[J]. 太赫兹科学与电子信息学报, 2021, 19(2): 303-307.
[16] MALI S K, LAKKANNAVAR M C. Parallel pipelined FFT architecture for real valued signals using radix-2[C]// 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, India, 2016: 1277-1281.
[17] 于建, 霍永华, 焦利彬, 等. 一种紧凑型1024点流水线FFT处理器设计[J]. 无线电工程, 2021, 51(11): 1326-1334.
[18] 占席春, 蔡费杨, 王伟. 多路并行FFT算法的FPGA实现技术[J]. 现代电子技术, 2015, 38(19): 33-36.
[19] 王海淼. 基于FPGA的实时FFT分析方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2021.

中国半导体行业协会封装分会会刊

中国电子学会电子制造与封装技术分会会刊

一种流水线架构的2D-FFT加速引擎设计

Design of a 2D-FFT Acceleration Engine with Pipelined Architecture

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	谌民迪,万江华. 基于泰勒级数近似的浮点开方运算器的设计[J]. 电子与封装, 2024, 24(5): 50301-.
[2]	池哲涵;黎飞;刘颖异;唐旭升;苗澎. 一种应用于高精度流水线ADC的差分参考电压电路^*[J]. 电子与封装, 2022, 22(5): 50305-.
[3]	邵杰;唐路. 应用于高精度模数转换器的乘法数模单元模块研究^*[J]. 电子与封装, 2022, 22(4): 40305-.
[4]	杨迎;黎飞;刘颖异;唐旭升;苗澎. 18 bit 20 MS/s流水线ADC架构及行为级模型设计^*[J]. 电子与封装, 2022, 22(2): 20304-.
[5]	张浩松，唐鹤. 一款14位流水线-逐次逼近型模数转换器设计[J]. 电子与封装, 2020, 20(7): 70302-.
[6]	李跃峰，唐鹤. 一种流水线-逐次逼近型ADC的异步时序控制方法[J]. 电子与封装, 2020, 20(7): 70301-.
[7]	史帅帅，唐　鹤，武　锦，王　卓，张　波. 一款12 Bit 1 GS/s射频采样的流水线模数转换器设计[J]. 电子与封装, 2018, 18(6): 17-21.
[8]	戴立新¹，冯立康¹，洪国东¹，陈珍海²，叶爱民³. 用于高速流水线ADC的低抖动多相时钟产生电路[J]. 电子与封装, 2017, 17(2): 25-27.