Scalable many-core algorithms for tridiagonal solvers

[thumbnail of WRAP-Scalable-many-core-algorithms-tridiagonal-solvers-2021.pdf]
Preview
PDF
WRAP-Scalable-many-core-algorithms-tridiagonal-solvers-2021.pdf - Accepted Version - Requires a PDF viewer.

Download (503kB) | Preview

Request Changes to record.

Abstract

We present a novel distributed memory Tridiagonal solver library, targeting large-scale systems based on modern multi-core and many-core processor architectures. The library uses methods based on both approximate and exact algorithms. Performance comparisons with the state-of-the-art, using both a large Cray EX system and a GPU cluster show the algorithmic trade-offs required at increasing machine scale to achieve good performance, particularly considering the advent of exascale systems.

Item Type: Journal Article
Subjects: Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Divisions: Faculty of Science, Engineering and Medicine > Science > Computer Science
Library of Congress Subject Headings (LCSH): Parallel processing (Electronic computers), High performance computing, Differential equations, Linear -- Data processing, Computer algorithms, Linear systems
Journal or Publication Title: Computing in Science and Engineering
Publisher: IEEE
ISSN: 1521-9615
Official Date: January 2022
Dates:
Date
Event
January 2022
Published
24 November 2021
Available
21 November 2021
Accepted
Volume: 24
Number: 1
Page Range: pp. 26-35
DOI: 10.1109/MCSE.2021.3130544
Status: Peer Reviewed
Publication Status: Published
Re-use Statement: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Access rights to Published version: Restricted or Subscription Access
Date of first compliant deposit: 25 November 2021
Date of first compliant Open Access: 25 November 2021
RIOXX Funder/Project Grant:
Project/Grant ID
RIOXX Funder Name
Funder ID
INF/R1/1800 12
Royal Society
EP/R029326/1
[EPSRC] Engineering and Physical Sciences Research Council
UNSPECIFIED
Narodowe Centrum Nauki
Related URLs:
URI: https://wrap.warwick.ac.uk/160567/

Export / Share Citation


Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item