GPU Accelerated Gauss‐Jordan Elimination on the OpenPOWER platform – A case study

GPU Accelerated Gauss‐Jordan Elimination on the OpenPOWER platform – A case study The solution of linear systems is still one of the basic building blocks in scientific computing. Therefore, it needs to be adapted to each new hardware platform in order to exploit the new features of the platform in an optimal way. During the last decade many of these building blocks were accelerated by the usage of GPUs and similar accelerator devices. In our contribution we will focus on the solution of linear systems with many right hand sides, where a fast solution not only requires an optimized LU decomposition, but also needs an efficient forward and backward substitution phase. Since the triangular shape of the factors leads to a rather sequential resolution step, this is a difficult task for parallelization and optimization. (© 2017 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim) http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Proceedings in Applied Mathematics & Mechanics Wiley

GPU Accelerated Gauss‐Jordan Elimination on the OpenPOWER platform – A case study

Loading next page...
 
/lp/wiley/gpu-accelerated-gauss-jordan-elimination-on-the-openpower-platform-a-9d0e0gsk5q
Publisher
Wiley Subscription Services, Inc., A Wiley Company
Copyright
Copyright © 2017 Wiley Subscription Services
ISSN
1617-7061
eISSN
1617-7061
D.O.I.
10.1002/pamm.201710390
Publisher site
See Article on Publisher Site

Abstract

The solution of linear systems is still one of the basic building blocks in scientific computing. Therefore, it needs to be adapted to each new hardware platform in order to exploit the new features of the platform in an optimal way. During the last decade many of these building blocks were accelerated by the usage of GPUs and similar accelerator devices. In our contribution we will focus on the solution of linear systems with many right hand sides, where a fast solution not only requires an optimized LU decomposition, but also needs an efficient forward and backward substitution phase. Since the triangular shape of the factors leads to a rather sequential resolution step, this is a difficult task for parallelization and optimization. (© 2017 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim)

Journal

Proceedings in Applied Mathematics & MechanicsWiley

Published: Jan 1, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off