A High Performance Accelerator Design for Ultra-Long Point Floating-Point FFT
-
摘要: 快速傅里叶变换(fast Fourier transform, FFT)在数字信号处理中占据核心地位.随着高性能超长点数FFT需求的增长，数字信号处理器(digital signal processor, DSP)的计算能力越来越难以满足需求，集成FFT加速器成为重要的发展趋势.为了支持超长点数FFT，将2维分解算法推广到多维，提出一种可集成于DSP的高性能超长点数FFT加速器结构.该结构通过基于素数个存储体的无冲突体编址方法实现了3维转置运算；通过递推算法实现了高效铰链因子生成；使用单精度浮点二项融合点积运算和融合加-减运算，对FFT运算电路进行了精细化设计.实现了对4G点数单精度浮点FFT计算的支持.综合结果表明：FFT加速器运行频率能够达到1GHz以上，性能达到640Gflop/s.在支持的点数和性能方面都较已有研究成果取得大幅提升.Abstract: Fast Fourier transform (FFT) plays a key role in digital signal processing. With the increasing demand of high performance ultra-long point FFT, digital signal processor (DSP) is becoming more and more difficult to meet the demand, so integrated FFT accelerators have become an important development trend. In order to support ultra-long point FFT, this paper extends the two-dimensional decomposition algorithm of FFT to multi-dimensional, and we propose a high performance ultra-long point FFT accelerator architecture which can be integrated into DSP. In this architecture, three-dimensional transposition operation is realized by using collision-free addressing method with prime number memory banks; efficient twiddle factor generation is realized by recursive algorithm; FFT operation circuit is refined by using single precision floating-point fused dot product and fused add-subtract operation. Finally, this paper realizes the single precision floating-point FFT calculation within 4G points. The synthesis result shows that the proposed FFT accelerator can run at a frequency of more than 1GHz and its performance can reach 640Gflop/s, which has been greatly improved in terms of points and performance compared with the existing research.
-
-
期刊类型引用(11)
1. 袁子轩，张峰，许岗，魏光辉，石永强. 融合MAML和TGAT的机会网络动态链路预测模型. 小型微型计算机系统. 2024(12): 2957-2963 . 
百度学术
2. 曹志威，樊志杰，王青杨，韩伟力，李欣. 一种降噪自编码器的复杂网络链路预测算法. 小型微型计算机系统. 2023(03): 665-672 . 百度学术
3. 刘林峰，于子兴，祝贺. 基于门控循环单元的移动社会网络链路预测方法. 计算机研究与发展. 2023(03): 705-716 . 本站查看
4. 王曙燕，巩婧怡. 融合节点标签与强弱关系的链路预测算法. 计算机工程与应用. 2022(18): 71-77 . 百度学术
5. 张瑾，朱桂祥，王宇琛，郑烁佳，陈镜潞. 基于异质图表达学习的跨境电商推荐模型. 电子与信息学报. 2022(11): 4008-4017 . 百度学术
6. 唐明虎. 基于多种信息组合模式的非负矩阵分解链路预测模型. 计算机应用研究. 2021(05): 1393-1397+1408 . 百度学术
7. 顾秋阳，吴宝，池仁勇. 基于高阶路径相似度的复杂网络链路预测方法. 通信学报. 2021(07): 61-69 . 百度学术
8. 许爽，李淼磊. 基于子图特征的科学家合作网络链路预测. 大连民族大学学报. 2020(01): 51-63 . 百度学术
9. 张尚田，陈光，邱天. 基于融合特征的LSTM评分预测. 计算机与现代化. 2020(03): 49-53+59 . 百度学术
10. 顾秋阳，琚春华，吴功兴. 基于子图演化与改进蚁群优化算法的社交网络链路预测方法. 通信学报. 2020(12): 21-35 . 百度学术
11. 李琦，王智强，梁吉业. 基于PU学习的链接预测方法. 模式识别与人工智能. 2019(09): 793-799 . 百度学术
其他类型引用(18)
计量
- 文章访问数:
- HTML全文浏览量: 0
- PDF下载量:
- 被引次数: 29
下载:
