@inproceedings{65e050fe5a554b6d9f4e49a2a6c8a634,
title = "Novel GPU implementation of Jacobi algorithm for Karhunen-Lo{\`e}ve transform of dense matrices",
abstract = "Jacobi algorithm for Karhunen-Lo{\`e}ve transform of a symmetric real matrix, and its parallel implementation using chess tournament algorithm are revisited in this paper. Impact of memory access patterns and significance of memory coalescing on the performance of the GPU implementation for the parallel Jacobi algorithm are emphasized. Two novel memory access methods for the Jacobi algorithm are proposed. It is shown with simulation results that one of the proposed methods achieves 77.3% computational performance improvement over the traditional GPU methods, and it runs 73.5 times faster than CPU for a dense symmetric square matrix of size 1,024.",
keywords = "CUDA, Eigendecomposition, GPU Computing, Jacobi Algorithm, KLT",
author = "Torun, {Mustafa U.} and Onur Yilmaz and Akansu, {Ali N.}",
year = "2012",
doi = "10.1109/CISS.2012.6310720",
language = "English (US)",
isbn = "9781467331401",
series = "2012 46th Annual Conference on Information Sciences and Systems, CISS 2012",
booktitle = "2012 46th Annual Conference on Information Sciences and Systems, CISS 2012",
note = "2012 46th Annual Conference on Information Sciences and Systems, CISS 2012 ; Conference date: 21-03-2012 Through 23-03-2012",
}