Publication: How to scale Nested OpenMP Applications on the ScaleMP vSMP Architecture
Introduction
Applications
Tools
Research Groups
Workshops
Publications
   List Publications
   Advanced Search
   Info
   Add Publications
My Account
About

How to scale Nested OpenMP Applications on the ScaleMP vSMP Architecture

- Part of a collection -
 

Area
Geophysics

Author(s)
D. Schmidl , C. Terboven , A. Wolf , D. an Mey , C. H. Bischof

Published in
Proceedings of the IEEE International Conference on Cluster Computing (CLUSTER 2010), Heraklion, Greece, September 20--24, 2010

Year
2010

Publisher
IEEE Computer Society

Abstract
The novel ScaleMP vSMP architecture employs commodity x86-based servers with an InfiniBand network to assemble a large shared memory system at an attractive price point. We examine this combined hardware- and softwareapproach of a DSM system using both system-level kernel benchmarks as well as real-world application codes. We compare this architecture with traditional shared memory machines and elaborate on strategies to tune application codes parallelized with OpenMP on multiple levels. Finally we summarize the necessary conditions which a scalable application has to fulfill in order to profit from the full potential of the ScaleMP approach.

AD Tools
ADIFOR

AD Theory and Techniques
Parallelism

BibTeX
@INPROCEEDINGS{
         Schmidl2010Hts,
       author = "D. Schmidl and C. Terboven and A. Wolf and D. an~Mey and C. H. Bischof",
       title = "How to scale Nested {OpenMP} Applications on the {ScaleMP} {vSMP} Architecture",
       booktitle = "Proceedings of the {IEEE} International Conference on Cluster Computing
         ({CLUSTER}~2010), Heraklion, Greece, September~20--24, 2010",
       publisher = "IEEE Computer Society",
       address = "Los Alamitos, California",
       pages = "29--37",
       doi = "10.1109/CLUSTER.2010.38",
       isbn = "978-0-7695-4220-1",
       abstract = "The novel ScaleMP vSMP architecture employs commodity x86-based servers with an
         InfiniBand network to assemble a large shared memory system at an attractive price point. We examine
         this combined hardware- and softwareapproach of a DSM system using both system-level kernel
         benchmarks as well as real-world application codes. We compare this architecture with traditional
         shared memory machines and elaborate on strategies to tune application codes parallelized with
         OpenMP on multiple levels. Finally we summarize the necessary conditions which a scalable
         application has to fulfill in order to profit from the full potential of the ScaleMP approach.",
       year = "2010",
       ad_area = "Geophysics",
       ad_tools = "ADIFOR",
       ad_theotech = "Parallelism"
}


back
  

Contact:
autodiff.org
Username:
Password:
(lost password)