EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond

Mario Heene; Alfredo Parra Hinojosa; Michael Obersteiner; Hans Joachim Bungartz; Dirk Pflüger

doi:10.1007/978-3-319-68394-2_31

EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond

Mario Heene, Alfredo Parra Hinojosa, Michael Obersteiner, Hans Joachim Bungartz, Dirk Pflüger

Informatik 5 - Lehrstuhl für Scientific Computing

Publikation: Beitrag in Buch/Bericht/Konferenzband › Kapitel › Begutachtung

6 Zitate (Scopus)

Abstract

Within the current reporting period (04/2016-04/2017) of our HLRS project we have developed a scalable implementation of the fault-tolerant combination technique. Fault-tolerance is one of the key topics in the ongoing research of algorithms for future exascale systems. Our algorithms enable fault-tolerance for both hard and soft faults, for the efficient and massively parallel computation of high-dimensional PDEs without the need of checkpointing or process replication. The research project EXAHD is part of DFG’s priority program “Software for Exascale Computing” (SPPEXA). The project’s target application is the large-scale simulation of plasma turbulence with the code GENE. The report combines parts of three publications.

Originalsprache	Englisch
Titel	High Performance Computing in Science and Engineering' 17
Untertitel	Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2017
Herausgeber (Verlag)	Springer International Publishing
Seiten	513-529
Seitenumfang	17
ISBN (elektronisch)	9783319683942
ISBN (Print)	9783319683935
DOIs	https://doi.org/10.1007/978-3-319-68394-2_31
Publikationsstatus	Veröffentlicht - 1 Jan. 2018

Zugriff auf Dokument

10.1007/978-3-319-68394-2_31

Andere Dateien und Links

Verknüpfung zur Publikation in Scopus

Dieses zitieren

Heene, M., Hinojosa, A. P., Obersteiner, M., Bungartz, H. J., & Pflüger, D. (2018). EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond. in High Performance Computing in Science and Engineering' 17: Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2017 (S. 513-529). Springer International Publishing. https://doi.org/10.1007/978-3-319-68394-2_31

Heene, Mario ; Hinojosa, Alfredo Parra ; Obersteiner, Michael et al. / EXAHD : An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond. High Performance Computing in Science and Engineering' 17: Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2017. Springer International Publishing, 2018. S. 513-529

@inbook{c2a8e68c884b4845a8cef5a0eab672eb,

title = "EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond",

abstract = "Within the current reporting period (04/2016-04/2017) of our HLRS project we have developed a scalable implementation of the fault-tolerant combination technique. Fault-tolerance is one of the key topics in the ongoing research of algorithms for future exascale systems. Our algorithms enable fault-tolerance for both hard and soft faults, for the efficient and massively parallel computation of high-dimensional PDEs without the need of checkpointing or process replication. The research project EXAHD is part of DFG{\textquoteright}s priority program “Software for Exascale Computing” (SPPEXA). The project{\textquoteright}s target application is the large-scale simulation of plasma turbulence with the code GENE. The report combines parts of three publications.",

author = "Mario Heene and Hinojosa, {Alfredo Parra} and Michael Obersteiner and Bungartz, {Hans Joachim} and Dirk Pfl{\"u}ger",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2018.",

year = "2018",

month = jan,

day = "1",

doi = "10.1007/978-3-319-68394-2_31",

language = "English",

isbn = "9783319683935",

pages = "513--529",

booktitle = "High Performance Computing in Science and Engineering' 17",

publisher = "Springer International Publishing",

}

Heene, M, Hinojosa, AP, Obersteiner, M , Bungartz, HJ & Pflüger, D 2018, EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond. in High Performance Computing in Science and Engineering' 17: Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2017. Springer International Publishing, S. 513-529. https://doi.org/10.1007/978-3-319-68394-2_31

EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond. / Heene, Mario; Hinojosa, Alfredo Parra; Obersteiner, Michael et al.
High Performance Computing in Science and Engineering' 17: Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2017. Springer International Publishing, 2018. S. 513-529.

Publikation: Beitrag in Buch/Bericht/Konferenzband › Kapitel › Begutachtung

TY - CHAP

T1 - EXAHD

T2 - An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond

AU - Heene, Mario

AU - Hinojosa, Alfredo Parra

AU - Obersteiner, Michael

AU - Bungartz, Hans Joachim

AU - Pflüger, Dirk

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Within the current reporting period (04/2016-04/2017) of our HLRS project we have developed a scalable implementation of the fault-tolerant combination technique. Fault-tolerance is one of the key topics in the ongoing research of algorithms for future exascale systems. Our algorithms enable fault-tolerance for both hard and soft faults, for the efficient and massively parallel computation of high-dimensional PDEs without the need of checkpointing or process replication. The research project EXAHD is part of DFG’s priority program “Software for Exascale Computing” (SPPEXA). The project’s target application is the large-scale simulation of plasma turbulence with the code GENE. The report combines parts of three publications.

AB - Within the current reporting period (04/2016-04/2017) of our HLRS project we have developed a scalable implementation of the fault-tolerant combination technique. Fault-tolerance is one of the key topics in the ongoing research of algorithms for future exascale systems. Our algorithms enable fault-tolerance for both hard and soft faults, for the efficient and massively parallel computation of high-dimensional PDEs without the need of checkpointing or process replication. The research project EXAHD is part of DFG’s priority program “Software for Exascale Computing” (SPPEXA). The project’s target application is the large-scale simulation of plasma turbulence with the code GENE. The report combines parts of three publications.

UR - http://www.scopus.com/inward/record.url?scp=85046408093&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-68394-2_31

DO - 10.1007/978-3-319-68394-2_31

M3 - Chapter

AN - SCOPUS:85046408093

SN - 9783319683935

SP - 513

EP - 529

BT - High Performance Computing in Science and Engineering' 17

PB - Springer International Publishing

ER -

Heene M, Hinojosa AP, Obersteiner M , Bungartz HJ, Pflüger D. EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond. in High Performance Computing in Science and Engineering' 17: Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2017. Springer International Publishing. 2018. S. 513-529 doi: 10.1007/978-3-319-68394-2_31

EXAHD: An exa-scalable two-level sparse grid approach for higher-dimensional problems in plasma physics and beyond

Abstract

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Dieses zitieren