This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
10th Euromicro Workshop on Parallel, Distributed and Network-based Processing (EUROMICRO-PDP 2002)
Efficient Implementation of Reduce-Scatter in MPI
Canary Islands, Spain
January 09-January 11
ISBN: 0-7695-1444-8
ASCII Text
x 
 
Massimo Bernaschi, Giulio Iannello, Mario Lauria, "Efficient Implementation of Reduce-Scatter in MPI," 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008), pp. 0301, 10th Euromicro Workshop on Parallel, Distributed and Network-based Processing (EUROMICRO-PDP 2002), 2002.
 
 
BibTex
x
 
@article{ 10.1109/EMPDP.2002.994296,
author = {Massimo Bernaschi and Giulio Iannello and Mario Lauria},
title = {Efficient Implementation of Reduce-Scatter in MPI},
journal ={16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008)},
volume = {0},
year = {2002},
issn = {1066-6192},
pages = {0301},
doi = {http://doi.ieeecomputersociety.org/10.1109/EMPDP.2002.994296},
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 - Efficient Implementation of Reduce-Scatter in MPI
SN - 1066-6192
SP
EP
A1 - Massimo Bernaschi,
A1 - Giulio Iannello,
A1 - Mario Lauria,
PY - 2002
KW - MPI
KW - Collective Communication
KW - LogGP model
VL - 0
JA - 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008)
ER -
 
Massimo Bernaschi, Italian National Research Council
Giulio Iannello, University of Naples
Mario Lauria, Ohio State University
We discuss the efficient implementation of the MPI collective operation called reduce-scatter. We describe the implementation issues and the performance characterization of two algorithms for the reduce-scatter that have been proven to be highly efficient in theory under the assumption of fully connected parallel system. A performance comparison with existing mainstream implementations of the operation is presented which confirms the practical advantage of the new algorithms. Experiments show that the two algorithms have different characteristics which make them complementary in providing a performance gain over standard algorithms.
Index Terms:
MPI, Collective Communication, LogGP model
Citation:
Massimo Bernaschi, Giulio Iannello, Mario Lauria, "Efficient Implementation of Reduce-Scatter in MPI," pdp, pp.0301, 10th Euromicro Workshop on Parallel, Distributed and Network-based Processing (EUROMICRO-PDP 2002), 2002
Usage of this product signifies your acceptance of the Terms of Use.