In this paper we present CUDA kernels that compute an interval matrix product. Starting from a naive implementation we investigate possible speedups using commonly known techniques from standard matrix multiplication. We also evaluate the achieved speedup when our kernels are used to accelerate a variant of an existing algorithm that finds an enclosure for the solution of a linear system. Moreover the quality of our enclosure is discussed.
Описание
Finding Enclosures for Linear Systems Using Interval Matrix Multiplication in CUDA - Springer
%0 Book Section
%1 noKey
%A Dallmann, Alexander
%A Beck, Philip-Daniel
%A von Gudenberg, JürgenWolff
%B Parallel Processing and Applied Mathematics
%D 2014
%E Wyrzykowski, Roman
%E Dongarra, Jack
%E Karczewski, Konrad
%E Waśniewski, Jerzy
%I Springer Berlin Heidelberg
%K cuda enclosures from:dallmann linear_systems myown
%P 582-590
%R 10.1007/978-3-642-55195-6_55
%T Finding Enclosures for Linear Systems Using Interval Matrix Multiplication in CUDA
%U http://dx.doi.org/10.1007/978-3-642-55195-6_55
%V 8385
%X In this paper we present CUDA kernels that compute an interval matrix product. Starting from a naive implementation we investigate possible speedups using commonly known techniques from standard matrix multiplication. We also evaluate the achieved speedup when our kernels are used to accelerate a variant of an existing algorithm that finds an enclosure for the solution of a linear system. Moreover the quality of our enclosure is discussed.
%@ 978-3-642-55194-9
@incollection{noKey,
abstract = {In this paper we present CUDA kernels that compute an interval matrix product. Starting from a naive implementation we investigate possible speedups using commonly known techniques from standard matrix multiplication. We also evaluate the achieved speedup when our kernels are used to accelerate a variant of an existing algorithm that finds an enclosure for the solution of a linear system. Moreover the quality of our enclosure is discussed.},
added-at = {2016-11-04T03:10:05.000+0100},
author = {Dallmann, Alexander and Beck, Philip-Daniel and von Gudenberg, JürgenWolff},
biburl = {https://www.bibsonomy.org/bibtex/248e8ffa701bf1fa52475f779f0f2e700/dmir},
booktitle = {Parallel Processing and Applied Mathematics},
description = {Finding Enclosures for Linear Systems Using Interval Matrix Multiplication in CUDA - Springer},
doi = {10.1007/978-3-642-55195-6_55},
editor = {Wyrzykowski, Roman and Dongarra, Jack and Karczewski, Konrad and Waśniewski, Jerzy},
interhash = {eb00db33535254ae6cc32872eb3f8ed2},
intrahash = {48e8ffa701bf1fa52475f779f0f2e700},
isbn = {978-3-642-55194-9},
keywords = {cuda enclosures from:dallmann linear_systems myown},
language = {English},
pages = {582-590},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes in Computer Science},
timestamp = {2024-01-18T10:31:52.000+0100},
title = {Finding Enclosures for Linear Systems Using Interval Matrix Multiplication in CUDA},
url = {http://dx.doi.org/10.1007/978-3-642-55195-6_55},
volume = 8385,
year = 2014
}