Design of A Low-Latency and Parallelizable SVD Dataflow Architecture on FPGA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Fangqiang, Chong, Sixuan, Huang, Zixuan, Qin, Rui, Mi, Fengnan, Hu, Caibao, Chen, Jiangang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915636343472128
author Du, Fangqiang
Chong, Sixuan
Huang, Zixuan
Qin, Rui
Mi, Fengnan
Hu, Caibao
Chen, Jiangang
author_facet Du, Fangqiang
Chong, Sixuan
Huang, Zixuan
Qin, Rui
Mi, Fengnan
Hu, Caibao
Chen, Jiangang
contents Singular value decomposition (SVD) is widely used for dimensionality reduction and noise suppression, and it plays a pivotal role in numerous scientific and engineering applications. As the dimensions of the matrix grow rapidly, the computational cost increases significantly, posing a serious challenge to the efficiency of data analysis and signal processing systems, especially in time-sensitive scenarios involving large-scale datasets. Although various dedicated hardware architectures have been proposed to accelerate the computation of intensive SVD, many of these designs suffer from limited scalability and high consumption of on-chip memory resources. Moreover, they typically overlook the computational and data transfer challenges associated with SVD, making them unsuitable for real-time processing of large-scale data stream matrices in embedded systems. In this paper, we propose a Data Stream-Based SVD processing algorithm (DSB Jacobi), which significantly reduces on-chip BRAM usage while improving computational speed, offering a practical solution for real-time SVD computation of large-scale data streams. Compared to previous works, our experimental results indicate that the proposed method reduces on-chip RAM consumption by 41.5 percent and improves computational efficiency by a factor of 23.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12461
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Design of A Low-Latency and Parallelizable SVD Dataflow Architecture on FPGA
Du, Fangqiang
Chong, Sixuan
Huang, Zixuan
Qin, Rui
Mi, Fengnan
Hu, Caibao
Chen, Jiangang
Distributed, Parallel, and Cluster Computing
Signal Processing
Singular value decomposition (SVD) is widely used for dimensionality reduction and noise suppression, and it plays a pivotal role in numerous scientific and engineering applications. As the dimensions of the matrix grow rapidly, the computational cost increases significantly, posing a serious challenge to the efficiency of data analysis and signal processing systems, especially in time-sensitive scenarios involving large-scale datasets. Although various dedicated hardware architectures have been proposed to accelerate the computation of intensive SVD, many of these designs suffer from limited scalability and high consumption of on-chip memory resources. Moreover, they typically overlook the computational and data transfer challenges associated with SVD, making them unsuitable for real-time processing of large-scale data stream matrices in embedded systems. In this paper, we propose a Data Stream-Based SVD processing algorithm (DSB Jacobi), which significantly reduces on-chip BRAM usage while improving computational speed, offering a practical solution for real-time SVD computation of large-scale data streams. Compared to previous works, our experimental results indicate that the proposed method reduces on-chip RAM consumption by 41.5 percent and improves computational efficiency by a factor of 23.
title Design of A Low-Latency and Parallelizable SVD Dataflow Architecture on FPGA
topic Distributed, Parallel, and Cluster Computing
Signal Processing
url https://arxiv.org/abs/2511.12461