loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2008 11th IEEE International Conference on Computational Science and Engineering
Application Performance Tuning for Clusters with ccNUMA Nodes
July 16-July 18
ISBN: 978-0-7695-3193-9
ASCII Text
x 
 
Abdullah Kayi, Edward Kornkven, Tarek El-Ghazawi, Greg Newby, "Application Performance Tuning for Clusters with ccNUMA Nodes," Computational Science and Engineering, IEEE International Conference on, pp. 245-252, 2008 11th IEEE International Conference on Computational Science and Engineering, 2008.
 
 
BibTex
x
 
@article{ 10.1109/CSE.2008.46,
author = {Abdullah Kayi and Edward Kornkven and Tarek El-Ghazawi and Greg Newby},
title = {Application Performance Tuning for Clusters with ccNUMA Nodes},
journal ={Computational Science and Engineering, IEEE International Conference on},
volume = {0},
year = {2008},
isbn = {978-0-7695-3193-9},
pages = {245-252},
doi = {http://doi.ieeecomputersociety.org/10.1109/CSE.2008.46},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computational Science and Engineering, IEEE International Conference on
TI - Application Performance Tuning for Clusters with ccNUMA Nodes
SN - 978-0-7695-3193-9
SP245
EP252
A1 - Abdullah Kayi,
A1 - Edward Kornkven,
A1 - Tarek El-Ghazawi,
A1 - Greg Newby,
PY - 2008
KW - ccNUMA
KW - application performance
KW - cpu affinity
KW - high-performance computing
VL - 0
JA - Computational Science and Engineering, IEEE International Conference on
ER -
 
With the increasing trend of putting more cores inside a single chip, more clusters adapt multicore multiprocessor nodes for high-performance computing (HPC). Cache coherent non-uniform memory access architectures (ccNUMA) are becoming an increasingly popular choice for such systems. In this paper, application performance analysis is provided using a 2312 Opteron cores system based on Sun Fire servers. Performance bottlenecks are identified and some potential solutions are proposed. With the proposed performance tunings, up to 30% application performance improvement was observed. In addition, provided experimental analysis can be utilized by HPC application developers in order to better understand clusters with ccNUMA nodes and also as a guideline for the usage of such architectures for scientific computing.
Index Terms:
ccNUMA, application performance, cpu affinity, high-performance computing
Citation:
Abdullah Kayi, Edward Kornkven, Tarek El-Ghazawi, Greg Newby, "Application Performance Tuning for Clusters with ccNUMA Nodes," cse, pp.245-252, 2008 11th IEEE International Conference on Computational Science and Engineering, 2008
Usage of this product signifies your acceptance of the Terms of Use.