A GPU-based singular value decomposition algorithm

• Veröffentlicht in: PROBLEMS IN PROGRAMMING
• Datum: 2023
• Heft: 1
• Сторінки: 30-37
• ISSN: 1727-4907
• Автори та афіліації: S.S. Sukharskyi — Institute of Software Systems NAS of Ukraine
• Ключові слова: алгоритм хаусхолдера, сингулярний розклад, алгоритм ґівенса, обчислення на gpu, jcuda, обчислення на графічному процесорі, обчислювальний алгоритм, cuda, сингулярні числа, обчислення загального призначення на графічних процесорах
• 1. Verfasser: Sukharskyi, S.S.
• Format: Artikel
• Sprache: Ukrainisch
• Veröffentlicht: PROBLEMS IN PROGRAMMING 2023
• Schlagworte: singular value decomposition; Householder algorithm; Givens algorithm; GPU computations; jCUDA; UDC 004.415.2
• Online Zugang: https://pp.isofts.kiev.ua/index.php/ojs1/article/view/556
• Назва журналу: Problems in programming

In this research paper we present an implementation of a singular value decomposition algorithm designed specifically for the graphics processing unit. It consists of two parts: orthogonal matrix decomposition and matrix diagonalization. Presented an implementation of bidiagonalization algorithm where we calculate the main bidiagonal matrix and two orthogonal multipliers using a series of House- holder transformations, as well as diagonalization algorithm with the help of Givens rotation matrices. Bothe these parts are implemented in jCUDA environment. Experiments have been conducted, the results of which have been thoroughly investigated on the matter of time consumption and calculations error. We’ve also compared our implementation with alternatives both on central and graphic processors.Prombles in programming 2023; 1: 30-37