UnifaSVD: A Unified and Fast Framework of Singular Value Decomposition on GPU Architectures

Singular value decomposition (SVD) is a fundamental matrix factorization in scientific computing and data analysis, but computing it efficiently on modern GPUs remains challenging. Full SVD provides strong numerical robustness but is often expensive for large matrices, whereas randomized SVD (RSVD) improves performance but may exhibit accuracy variability, especially when the target rank is unknown or the singular spectrum decays slowly. To address this challenge, we propose UnifaSVD, a unified and adaptive framework for high-performance and numerically reliable SVD on GPUs. UnifaSVD combines a numerically stable Householder QB (HQB) factorization for numerical rank estimation with a unified EVD-based SVD backend for efficient computation of the required singular values and vectors. Its adaptive architecture supports full-rank, low-rank, and unknown-rank matrices by dynamically selecting an appropriate computational path according to matrix characteristics and user-specified numerical requirements. Rather than relying on a fixed decomposition strategy, UnifaSVD integrates efficient factorization, adaptive rank handling, and lightweight refinement within a single framework. Experimental results show that UnifaSVD achieves numerical accuracy close to full SVD while delivering substantially higher performance across a wide range of tested cases. By automating algorithm selection based on matrix properties and numerical requirements, UnifaSVD provides a robust and efficient solution for SVD on modern GPU architectures.

Authors

Institutions

Publication Details

Journal
ACM Transactions on Architecture and Code Optimization
Published
2026-11-19
DOI
https://doi.org/10.1145/3856309
Primary Topic
Matrix Theory and Algorithms
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

UnifaSVD: A Unified and Fast Framework of Singular Value Decomposition on GPU Architectures

Weiwei Xu, Lu Shi, Shaoshuai Zhang, Dajun Huang et al.
2 links
ACM Transactions on Architecture and Code Optimization
Matrix Theory and Algorithms
article

UnifaSVD: A Unified and Fast Framework of Singular Value Decomposition on GPU Architectures

Weiwei Xu, Lu Shi, Shaoshuai Zhang, Dajun Huang, Ruiyi Zhan
article en

Abstract

Singular value decomposition (SVD) is a fundamental matrix factorization in scientific computing and data analysis, but computing it efficiently on modern GPUs remains challenging. Full SVD provides strong numerical robustness but is often expensive for large matrices, whereas randomized SVD (RSVD) improves performance but may exhibit accuracy variability, especially when the target rank is unknown or the singular spectrum decays slowly. To address this challenge, we propose UnifaSVD, a unified and adaptive framework for high-performance and numerically reliable SVD on GPUs. UnifaSVD combines a numerically stable Householder QB (HQB) factorization for numerical rank estimation with a unified EVD-based SVD backend for efficient computation of the required singular values and vectors. Its adaptive architecture supports full-rank, low-rank, and unknown-rank matrices by dynamically selecting an appropriate computational path according to matrix characteristics and user-specified numerical requirements. Rather than relying on a fixed decomposition strategy, UnifaSVD integrates efficient factorization, adaptive rank handling, and lightweight refinement within a single framework. Experimental results show that UnifaSVD achieves numerical accuracy close to full SVD while delivering substantially higher performance across a wide range of tested cases. By automating algorithm selection based on matrix properties and numerical requirements, UnifaSVD provides a robust and efficient solution for SVD on modern GPU architectures.

ACM Transactions on Architecture and Code OptimizationVol. 24(1)
University of Electronic Science and Technology of China (CN), Nanjing University of Information Science and Technology (CN)
Matrix Theory and Algorithms
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon