Simulating MPI Applications: The SMPI Approach

Augustin Degomme; Arnaud Legrand; George S. Markomanolis; Martin Quinson; Mark Stillwell; Frederic Suter

doi:10.1109/TPDS.2017.2669305

Simulating MPI Applications: The SMPI Approach

Augustin Degomme, Arnaud Legrand, George S. Markomanolis, Martin Quinson, Mark Stillwell, Frederic Suter

Research output: Contribution to journal › Article › peer-review

39 Scopus citations

Abstract

This article summarizes our recent work and developments on SMPI, a flexible simulator of MPI applications. In this tool, we took a particular care to ensure our simulator could be used to produce fast and accurate predictions in a wide variety of situations. Although we did build SMPI on SimGrid whose speed and accuracy had already been assessed in other contexts, moving such techniques to a HPC workload required significant additional effort. Obviously, an accurate modeling of communications and network topology was one of the key to such achievements. Another less obvious key was the choice to combine in a single tool the possibility to do both offline and online simulation.

Original language	English
Article number	7855780
Pages (from-to)	2387-2400
Number of pages	14
Journal	IEEE Transactions on Parallel and Distributed Systems
Volume	28
Issue number	8
DOIs	https://doi.org/10.1109/TPDS.2017.2669305
State	Published - Aug 1 2017
Externally published	Yes

Funding

The authors would like to thank the SimGrid team members and collaborators who contributed to SMPI: P. Bedaride, H. Casanova, P.-N. Clauss, F. Desprez, S. Genaud, A. Gupta, and B. Videau. This work is partially supported by the Hac Specis Inria Project Lab, the ANR SONGS (11-ANR-INFR-13), CNRS PICS N degree 5473, and European Mont-Blanc (EC grant 288777) projects. Experiments were carried out on a PRACE (EC grants RI-261557 and RI-283493) prototype and the Grid’5000 experimental testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER, and other Universities and organizations.

Funders	Funder number
European Mont-Blanc
Hac Specis Inria	11-ANR-INFR-13
Seventh Framework Programme	288777
European Commission
Centre National de la Recherche Scientifique

Keywords

MPI runtime and applications
Simulation
performance prediction and extrapolation

Access to Document

10.1109/TPDS.2017.2669305

Cite this

@article{b4a548f3fba34393a88b0bdabe0c3cef,

title = "Simulating MPI Applications: The SMPI Approach",

abstract = "This article summarizes our recent work and developments on SMPI, a flexible simulator of MPI applications. In this tool, we took a particular care to ensure our simulator could be used to produce fast and accurate predictions in a wide variety of situations. Although we did build SMPI on SimGrid whose speed and accuracy had already been assessed in other contexts, moving such techniques to a HPC workload required significant additional effort. Obviously, an accurate modeling of communications and network topology was one of the key to such achievements. Another less obvious key was the choice to combine in a single tool the possibility to do both offline and online simulation.",

keywords = "MPI runtime and applications, Simulation, performance prediction and extrapolation",

author = "Augustin Degomme and Arnaud Legrand and Markomanolis, {George S.} and Martin Quinson and Mark Stillwell and Frederic Suter",

note = "Publisher Copyright: {\textcopyright} 1990-2012 IEEE.",

year = "2017",

month = aug,

day = "1",

doi = "10.1109/TPDS.2017.2669305",

language = "English",

volume = "28",

pages = "2387--2400",

journal = "IEEE Transactions on Parallel and Distributed Systems",

issn = "1045-9219",

publisher = "Institute of Electrical and Electronics Engineers",

number = "8",

}

TY - JOUR

T1 - Simulating MPI Applications

T2 - The SMPI Approach

AU - Degomme, Augustin

AU - Legrand, Arnaud

AU - Markomanolis, George S.

AU - Quinson, Martin

AU - Stillwell, Mark

AU - Suter, Frederic

PY - 2017/8/1

Y1 - 2017/8/1

N2 - This article summarizes our recent work and developments on SMPI, a flexible simulator of MPI applications. In this tool, we took a particular care to ensure our simulator could be used to produce fast and accurate predictions in a wide variety of situations. Although we did build SMPI on SimGrid whose speed and accuracy had already been assessed in other contexts, moving such techniques to a HPC workload required significant additional effort. Obviously, an accurate modeling of communications and network topology was one of the key to such achievements. Another less obvious key was the choice to combine in a single tool the possibility to do both offline and online simulation.

AB - This article summarizes our recent work and developments on SMPI, a flexible simulator of MPI applications. In this tool, we took a particular care to ensure our simulator could be used to produce fast and accurate predictions in a wide variety of situations. Although we did build SMPI on SimGrid whose speed and accuracy had already been assessed in other contexts, moving such techniques to a HPC workload required significant additional effort. Obviously, an accurate modeling of communications and network topology was one of the key to such achievements. Another less obvious key was the choice to combine in a single tool the possibility to do both offline and online simulation.

KW - MPI runtime and applications

KW - Simulation

KW - performance prediction and extrapolation

UR - http://www.scopus.com/inward/record.url?scp=85029049825&partnerID=8YFLogxK

U2 - 10.1109/TPDS.2017.2669305

DO - 10.1109/TPDS.2017.2669305

M3 - Article

AN - SCOPUS:85029049825

SN - 1045-9219

VL - 28

SP - 2387

EP - 2400

JO - IEEE Transactions on Parallel and Distributed Systems

JF - IEEE Transactions on Parallel and Distributed Systems

IS - 8

M1 - 7855780

ER -

Simulating MPI Applications: The SMPI Approach

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this