This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing
Lessons Learnt Porting Parallelisation Techniques for Irregular Codes to NUMA Systems
Pisa, Italy
February 17-February 19
ISBN: 978-0-7695-3939-3
ASCII Text
x 
 
Juan Ángel Lorenzo, Juan Carlos Pichel, David LaFrance-Linden, Francisco Fernández Rivera, David Expósito Singh, "Lessons Learnt Porting Parallelisation Techniques for Irregular Codes to NUMA Systems," 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008), pp. 213-217, 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing, 2010.
 
 
BibTex
x
 
@article{ 10.1109/PDP.2010.66,
author = {Juan Ángel Lorenzo and Juan Carlos Pichel and David LaFrance-Linden and Francisco Fernández Rivera and David Expósito Singh},
title = {Lessons Learnt Porting Parallelisation Techniques for Irregular Codes to NUMA Systems},
journal ={16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008)},
volume = {0},
year = {2010},
issn = {1066-6192},
pages = {213-217},
doi = {http://doi.ieeecomputersociety.org/10.1109/PDP.2010.66},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008)
TI - Lessons Learnt Porting Parallelisation Techniques for Irregular Codes to NUMA Systems
SN - 1066-6192
SP213
EP217
A1 - Juan Ángel Lorenzo,
A1 - Juan Carlos Pichel,
A1 - David LaFrance-Linden,
A1 - Francisco Fernández Rivera,
A1 - David Expósito Singh,
PY - 2010
KW - Irregular Codes
KW - Itanium2
KW - Hardware Counters
VL - 0
JA - 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008)
ER -
 
This work presents a study undertaken to characterise the behaviour of some parallelisation techniques for irregular codes, previously developed for SMP architectures, on a several-node SMP NUMA system. The main objective is to determine the performance effect of bus contention and cache coherency in such a complex architecture. Results show that: (1) cores which share a socket can be considered as independent processors in this context; (2) for big data sizes, the effect of sharing a bus degrades the performance but masks the cache coherency effects and (3) the NUMA-ratio is a critical factor on irregular codes. These results allow us to study the effect in performance of the thread-to-core mappings and memory allocation policies.
Index Terms:
Irregular Codes, Itanium2, Hardware Counters
Citation:
Juan Ángel Lorenzo, Juan Carlos Pichel, David LaFrance-Linden, Francisco Fernández Rivera, David Expósito Singh, "Lessons Learnt Porting Parallelisation Techniques for Irregular Codes to NUMA Systems," pdp, pp.213-217, 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing, 2010
Usage of this product signifies your acceptance of the Terms of Use.