MPI+OpenMP tasking scalability for the simulation of the human brain

Pedro Valero-Lara; Raül Sirvent; Antonio J. Peña; Xavier Martorell; Jesús Labarta

doi:10.1145/3236367.3236373

MPI+OpenMP tasking scalability for the simulation of the human brain

Pedro Valero-Lara
, Raül Sirvent
, Antonio J. Peña
, Xavier Martorell
, Jesús Labarta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Scopus citations

Abstract

The simulation of the behavior of the Human Brain is one of the most ambitious challenges today with a non-end of important applications. We can find many different initiatives in the USA, Europe and Japan which attempt to achieve such a challenging target. In this work we focus on the most important European initiative (Human Brain Project) and on one of the tools (Arbor). This tool simulates the spikes triggered in a neuronal network by computing the voltage capacitance on the neurons' morphology, being one of the most precise simulators today. In the present work, we have evaluated the use of MPI+OpenMP tasking on top of the Arbor simulator. In this paper, we present the main characteristics of the Arbor tool and how these can be efficiently managed by using MPI+OpenMP tasking. We prove that this approach is able to achieve a good scaling even when computing a relatively low workload (number of neurons) per node using up to 32 nodes. Our target consists of achieving not only a highly scalable implementation based on MPI, but also to develop a tool with a high degree of abstraction without losing control and performance by using MPI+OpenMP tasking.

Original language	English
Title of host publication	EuroMPI 2018 - Proceedings of the 25th European MPI Users' Group Meeting
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450364928
DOIs	https://doi.org/10.1145/3236367.3236373
State	Published - Sep 23 2018
Externally published	Yes
Event	25th European MPI Users' Group Meeting, EuroMPI 2018 - Barcelona, Spain Duration: Sep 23 2018 → Sep 26 2018

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	25th European MPI Users' Group Meeting, EuroMPI 2018
Country/Territory	Spain
City	Barcelona
Period	09/23/18 → 09/26/18

Funding

We would like to apreciate the valuable feedback and help provided by Benjamin Cumming and Alexander Peyser. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 720270 (HBP SGA1 and HBP SGA2), from the Spanish Ministry of Economy and Competitiveness under the project Computación de Altas Presta-ciones VII (TIN2015-65316-P) and the Departament d’Innovació, Universitats i Empresa de la Generalitat de Catalunya, under project MPEXPAR: Models de Programació i Entorns d’Execució Paral·lels (2014-SGR-1051). This project has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska Curie grand agreement No. 749516. We would like to apreciate the valuable feedback and help provided by Benjamin Cumming and Alexander Peyser. This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 720270 (HBP SGA1 and HBP SGA2), from the Spanish Ministry of Economy and Competitiveness under the project Computación de Altas Presta-ciones VII (TIN2015-65316-P) and the Departament d'Innovació, Universitats i Empresa de la Generalitat de Catalunya, under project MPEXPAR: Models de Programació i Entorns d'Execució Paral·lels (2014-SGR-1051). This project has received funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska Curie grand agreement No. 749516.

Keywords

Arbor
Human Brain
MPI
OpenMP
Simulation
Tasking

Access to Document

10.1145/3236367.3236373

Cite this

@inproceedings{de23220c9a4f465f80a28017113049c0,

title = "MPI+OpenMP tasking scalability for the simulation of the human brain",

abstract = "The simulation of the behavior of the Human Brain is one of the most ambitious challenges today with a non-end of important applications. We can find many different initiatives in the USA, Europe and Japan which attempt to achieve such a challenging target. In this work we focus on the most important European initiative (Human Brain Project) and on one of the tools (Arbor). This tool simulates the spikes triggered in a neuronal network by computing the voltage capacitance on the neurons' morphology, being one of the most precise simulators today. In the present work, we have evaluated the use of MPI+OpenMP tasking on top of the Arbor simulator. In this paper, we present the main characteristics of the Arbor tool and how these can be efficiently managed by using MPI+OpenMP tasking. We prove that this approach is able to achieve a good scaling even when computing a relatively low workload (number of neurons) per node using up to 32 nodes. Our target consists of achieving not only a highly scalable implementation based on MPI, but also to develop a tool with a high degree of abstraction without losing control and performance by using MPI+OpenMP tasking.",

keywords = "Arbor, Human Brain, MPI, OpenMP, Simulation, Tasking",

author = "Pedro Valero-Lara and Ra{\"u}l Sirvent and Pe{\~n}a, \{Antonio J.\} and Xavier Martorell and Jes{\'u}s Labarta",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 25th European MPI Users' Group Meeting, EuroMPI 2018 ; Conference date: 23-09-2018 Through 26-09-2018",

year = "2018",

month = sep,

day = "23",

doi = "10.1145/3236367.3236373",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "EuroMPI 2018 - Proceedings of the 25th European MPI Users' Group Meeting",

}

Valero-Lara, P, Sirvent, R, Peña, AJ, Martorell, X & Labarta, J 2018, MPI+OpenMP tasking scalability for the simulation of the human brain. in EuroMPI 2018 - Proceedings of the 25th European MPI Users' Group Meeting., a5, ACM International Conference Proceeding Series, Association for Computing Machinery, 25th European MPI Users' Group Meeting, EuroMPI 2018, Barcelona, Spain, 09/23/18. https://doi.org/10.1145/3236367.3236373

MPI+OpenMP tasking scalability for the simulation of the human brain. / Valero-Lara, Pedro; Sirvent, Raül; Peña, Antonio J. et al.
EuroMPI 2018 - Proceedings of the 25th European MPI Users' Group Meeting. Association for Computing Machinery, 2018. a5 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MPI+OpenMP tasking scalability for the simulation of the human brain

AU - Valero-Lara, Pedro

AU - Sirvent, Raül

AU - Peña, Antonio J.

AU - Martorell, Xavier

AU - Labarta, Jesús

PY - 2018/9/23

Y1 - 2018/9/23

N2 - The simulation of the behavior of the Human Brain is one of the most ambitious challenges today with a non-end of important applications. We can find many different initiatives in the USA, Europe and Japan which attempt to achieve such a challenging target. In this work we focus on the most important European initiative (Human Brain Project) and on one of the tools (Arbor). This tool simulates the spikes triggered in a neuronal network by computing the voltage capacitance on the neurons' morphology, being one of the most precise simulators today. In the present work, we have evaluated the use of MPI+OpenMP tasking on top of the Arbor simulator. In this paper, we present the main characteristics of the Arbor tool and how these can be efficiently managed by using MPI+OpenMP tasking. We prove that this approach is able to achieve a good scaling even when computing a relatively low workload (number of neurons) per node using up to 32 nodes. Our target consists of achieving not only a highly scalable implementation based on MPI, but also to develop a tool with a high degree of abstraction without losing control and performance by using MPI+OpenMP tasking.

AB - The simulation of the behavior of the Human Brain is one of the most ambitious challenges today with a non-end of important applications. We can find many different initiatives in the USA, Europe and Japan which attempt to achieve such a challenging target. In this work we focus on the most important European initiative (Human Brain Project) and on one of the tools (Arbor). This tool simulates the spikes triggered in a neuronal network by computing the voltage capacitance on the neurons' morphology, being one of the most precise simulators today. In the present work, we have evaluated the use of MPI+OpenMP tasking on top of the Arbor simulator. In this paper, we present the main characteristics of the Arbor tool and how these can be efficiently managed by using MPI+OpenMP tasking. We prove that this approach is able to achieve a good scaling even when computing a relatively low workload (number of neurons) per node using up to 32 nodes. Our target consists of achieving not only a highly scalable implementation based on MPI, but also to develop a tool with a high degree of abstraction without losing control and performance by using MPI+OpenMP tasking.

KW - Arbor

KW - Human Brain

KW - MPI

KW - OpenMP

KW - Simulation

KW - Tasking

UR - https://www.scopus.com/pages/publications/85055443464

U2 - 10.1145/3236367.3236373

DO - 10.1145/3236367.3236373

M3 - Conference contribution

AN - SCOPUS:85055443464

T3 - ACM International Conference Proceeding Series

BT - EuroMPI 2018 - Proceedings of the 25th European MPI Users' Group Meeting

PB - Association for Computing Machinery

T2 - 25th European MPI Users' Group Meeting, EuroMPI 2018

Y2 - 23 September 2018 through 26 September 2018

ER -

MPI+OpenMP tasking scalability for the simulation of the human brain

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this