High-Level Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms

Khalid Hasanov; Jean-Noël Quintin; Alexey Lastovetsky

doi:10.1007/978-3-319-14313-2_35

High-Level Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms

Khalid Hasanov, Jean-Noël Quintin, Alexey Lastovetsky

Research output: Chapter in Book/Report/Conference proceeding › Chapter

4 Scopus citations

Abstract

There has been a significant research in collective communication operations, in particular in MPI broadcast, on distributed memory platforms. Most of the research works are done to optimize the collective operations for particular architectures by taking into account either their topology or platform parameters. In this work we propose a very simple and at the same time general approach to optimize legacy MPI broadcast algorithms, which are widely used in MPICH and OpenMPI. Theoretical analysis and experimental results on IBM BlueGene/P and a cluster of Grid’5000 platform are presented.

Original language	English (US)
Title of host publication	Euro-Par 2014: Parallel Processing Workshops
Publisher	Springer Nature
Pages	412-424
Number of pages	13
ISBN (Print)	9783319143125
DOIs	https://doi.org/10.1007/978-3-319-14313-2_35
State	Published - 2014
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This work has emanated from research conducted withthe financial support of IRCSET (Irish Research Council for Science, Engineeringand Technology) and IBM, grant number EPSG/2011/188 and Science Founda-tion Ireland, grant number 08/IN.1/I2054.Some of the experiments presented in this publication were carried out us-ing the Grid’5000 experimental testbed, being developed under the INRIA AL-ADDIN development action with support from CNRS, RENATER and severalUniversities as well as other funding bodies (seehttps://www.grid5000.fr)Another part of the experiments were carried out using the resources of the Su-percomputing Laboratory at King Abdullah University of Science&Technology(KAUST) in Thuwal, Saudi Arabia.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Access to Document

10.1007/978-3-319-14313-2_35

Cite this

@inbook{b1d15aaa277a4920ad1210e862e38e7e,

title = "High-Level Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms",

abstract = "There has been a significant research in collective communication operations, in particular in MPI broadcast, on distributed memory platforms. Most of the research works are done to optimize the collective operations for particular architectures by taking into account either their topology or platform parameters. In this work we propose a very simple and at the same time general approach to optimize legacy MPI broadcast algorithms, which are widely used in MPICH and OpenMPI. Theoretical analysis and experimental results on IBM BlueGene/P and a cluster of Grid{\textquoteright}5000 platform are presented.",

author = "Khalid Hasanov and Jean-No{\"e}l Quintin and Alexey Lastovetsky",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This work has emanated from research conducted withthe financial support of IRCSET (Irish Research Council for Science, Engineeringand Technology) and IBM, grant number EPSG/2011/188 and Science Founda-tion Ireland, grant number 08/IN.1/I2054.Some of the experiments presented in this publication were carried out us-ing the Grid{\textquoteright}5000 experimental testbed, being developed under the INRIA AL-ADDIN development action with support from CNRS, RENATER and severalUniversities as well as other funding bodies (seehttps://www.grid5000.fr)Another part of the experiments were carried out using the resources of the Su-percomputing Laboratory at King Abdullah University of Science&Technology(KAUST) in Thuwal, Saudi Arabia. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2014",

doi = "10.1007/978-3-319-14313-2_35",

language = "English (US)",

isbn = "9783319143125",

pages = "412--424",

booktitle = "Euro-Par 2014: Parallel Processing Workshops",

publisher = "Springer Nature",

}

TY - CHAP

T1 - High-Level Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms

AU - Hasanov, Khalid

AU - Quintin, Jean-Noël

AU - Lastovetsky, Alexey

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This work has emanated from research conducted withthe financial support of IRCSET (Irish Research Council for Science, Engineeringand Technology) and IBM, grant number EPSG/2011/188 and Science Founda-tion Ireland, grant number 08/IN.1/I2054.Some of the experiments presented in this publication were carried out us-ing the Grid’5000 experimental testbed, being developed under the INRIA AL-ADDIN development action with support from CNRS, RENATER and severalUniversities as well as other funding bodies (seehttps://www.grid5000.fr)Another part of the experiments were carried out using the resources of the Su-percomputing Laboratory at King Abdullah University of Science&Technology(KAUST) in Thuwal, Saudi Arabia. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2014

Y1 - 2014

N2 - There has been a significant research in collective communication operations, in particular in MPI broadcast, on distributed memory platforms. Most of the research works are done to optimize the collective operations for particular architectures by taking into account either their topology or platform parameters. In this work we propose a very simple and at the same time general approach to optimize legacy MPI broadcast algorithms, which are widely used in MPICH and OpenMPI. Theoretical analysis and experimental results on IBM BlueGene/P and a cluster of Grid’5000 platform are presented.

AB - There has been a significant research in collective communication operations, in particular in MPI broadcast, on distributed memory platforms. Most of the research works are done to optimize the collective operations for particular architectures by taking into account either their topology or platform parameters. In this work we propose a very simple and at the same time general approach to optimize legacy MPI broadcast algorithms, which are widely used in MPICH and OpenMPI. Theoretical analysis and experimental results on IBM BlueGene/P and a cluster of Grid’5000 platform are presented.

UR - http://hdl.handle.net/10754/598490

UR - http://link.springer.com/10.1007/978-3-319-14313-2_35

U2 - 10.1007/978-3-319-14313-2_35

DO - 10.1007/978-3-319-14313-2_35

M3 - Chapter

SN - 9783319143125

SP - 412

EP - 424

BT - Euro-Par 2014: Parallel Processing Workshops

PB - Springer Nature

ER -

High-Level Topology-Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this