| | |
| | |
Stat |
Members: 3645 Articles: 2'503'724 Articles rated: 2609
23 April 2024 |
|
| | | |
|
Article overview
| |
|
Analysis of A Splitting Approach for the Parallel Solution of Linear Systems on GPU Cards | Ang Li
; Radu Serban
; Dan Negrut
; | Date: |
26 Sep 2015 | Abstract: | We discuss an approach for solving sparse or dense banded linear systems
${f A} {f x} = {f b}$ on a Graphics Processing Unit (GPU) card. The
matrix ${f A} in {mathbb{R}}^{N imes N}$ is possibly nonsymmetric and
moderately large; i.e., $10000 leq N leq 500000$. The ${it split and
parallelize}$ (${ t SaP}$) approach seeks to partition the matrix ${f A}$
into diagonal sub-blocks ${f A}_i$, $i=1,ldots,P$, which are independently
factored in parallel. The solution may choose to consider or to ignore the
matrices that couple the diagonal sub-blocks ${f A}_i$. This approach, along
with the Krylov subspace-based iterative method that it preconditions, are
implemented in a solver called ${ t SaP::GPU}$, which is compared in terms of
efficiency with three commonly used sparse direct solvers: ${ t PARDISO}$,
${ t SuperLU}$, and ${ t MUMPS}$. ${ t SaP::GPU}$, which runs entirely on
the GPU except several stages involved in preliminary row-column permutations,
is robust and compares well in terms of efficiency with the aforementioned
direct solvers. In a comparison against Intel’s ${ t MKL}$, ${ t SaP::GPU}$
also fares well when used to solve dense banded systems that are close to being
diagonally dominant. ${ t SaP::GPU}$ is publicly available and distributed as
open source under a permissive BSD3 license. | Source: | arXiv, 1509.7919 | Services: | Forum | Review | PDF | Favorites |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
browser Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
|
| |
|
|
|
| News, job offers and information for researchers and scientists:
| |