A Scalable Parallel Computing Framework for Large-Scale Astrophysical Fluid Dynamics Numerical Simulation

The numerical simulation of complex astrophysical problems requires high-performance computing due to the large size of the problems and variety of simulated physical processes. In this paper, we present a new framework for the numerical simulation of astrophysical fluid dynamics. It is based on the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) S. 328 - 333
Hauptverfasser: Kulikov, Igor, Chernykh, Igor, Tchernykh, Andrei
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.12.2019
Schlagworte:
ISSN:2640-6721
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The numerical simulation of complex astrophysical problems requires high-performance computing due to the large size of the problems and variety of simulated physical processes. In this paper, we present a new framework for the numerical simulation of astrophysical fluid dynamics. It is based on the mechanisms of combining distributed and parallel computing techniques, advanced vectorization for KNL, and Skylake-SP CPU architectures. Our new HydroBox3D framework uses large 3D meshes to solve problems such as the dynamics of stars or galaxies. In our framework, we use computational nodes with a large amount of memory (RAM or Intel Optane in memory mode) for mesh processing and typical computational nodes for the numerical simulation of astrophysical problems. We use MPI both for send/receive operations between computational nodes and for sending processed data for calculations from data nodes. For optimization of calculations, memory, and CPU usage, we use data vectorization, FMA3, and AVX-512 instructions for Intel Xeon Phi 72XX and Intel Xeon Scalable processors. Benchmark results on different CPU and MIC devices show the effectiveness of the proposed solution.
AbstractList The numerical simulation of complex astrophysical problems requires high-performance computing due to the large size of the problems and variety of simulated physical processes. In this paper, we present a new framework for the numerical simulation of astrophysical fluid dynamics. It is based on the mechanisms of combining distributed and parallel computing techniques, advanced vectorization for KNL, and Skylake-SP CPU architectures. Our new HydroBox3D framework uses large 3D meshes to solve problems such as the dynamics of stars or galaxies. In our framework, we use computational nodes with a large amount of memory (RAM or Intel Optane in memory mode) for mesh processing and typical computational nodes for the numerical simulation of astrophysical problems. We use MPI both for send/receive operations between computational nodes and for sending processed data for calculations from data nodes. For optimization of calculations, memory, and CPU usage, we use data vectorization, FMA3, and AVX-512 instructions for Intel Xeon Phi 72XX and Intel Xeon Scalable processors. Benchmark results on different CPU and MIC devices show the effectiveness of the proposed solution.
Author Kulikov, Igor
Chernykh, Igor
Tchernykh, Andrei
Author_xml – sequence: 1
  givenname: Igor
  surname: Kulikov
  fullname: Kulikov, Igor
  organization: ICMMG SB RAS
– sequence: 2
  givenname: Igor
  surname: Chernykh
  fullname: Chernykh, Igor
  organization: ICMMG SB RAS
– sequence: 3
  givenname: Andrei
  surname: Tchernykh
  fullname: Tchernykh, Andrei
  organization: CICESE Research Center
BookMark eNotj99KwzAYxaMoOOeeQIS8QGfyNU2ay9I5FYYONq_HlzaZwbQdaYvs7Tf_XB0O53cOnFty1XatJeSBsznnTD-uF2WxFVIxmAPjes4Yk_KCzLTKuYKcg-RSXpIJSMESqYDfkFnfe8MEiHNJ6wnxBd1UGNAES9cYMQQbaNk1h3Hw7Z4uIzb2u4tf1HWRrjDubfLDW1r0Q-wOn8feny1dhtHXdHFssfFVT9_GxsbfYOObMeDgu_aOXDsMvZ3965R8LJ-25Uuyen9-LYtV4jnPhwSFxAzQuTpTlUNnZM0graWzqUaTZTXwzLhaVUKBFhqE48w6A8K43HCAdEru_3a9tXZ3iL7BeNzp810udHoCOKhc1A
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PDCAT46702.2019.00066
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781728126166
1728126169
EISSN 2640-6721
EndPage 333
ExternalDocumentID 9029149
Genre orig-research
GroupedDBID 6IE
6IL
ABLEC
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-a46a52affd57cfafb6d023d6fe39ab55d215bfd7c47294924f10efb24bf8b1223
IEDL.DBID RIE
IngestDate Wed Jun 26 19:27:03 EDT 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-a46a52affd57cfafb6d023d6fe39ab55d215bfd7c47294924f10efb24bf8b1223
PageCount 6
ParticipantIDs ieee_primary_9029149
PublicationCentury 2000
PublicationDate 2019-Dec.
PublicationDateYYYYMMDD 2019-12-01
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-Dec.
PublicationDecade 2010
PublicationTitle 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)
PublicationTitleAbbrev PDCAT
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib042470299
ssib048504810
Score 1.707059
Snippet The numerical simulation of complex astrophysical problems requires high-performance computing due to the large size of the problems and variety of simulated...
SourceID ieee
SourceType Publisher
StartPage 328
SubjectTerms Carbon
computational astrophysics
Explosions
high performance scientific computing
Hydrodynamics
Mathematical model
Numerical simulation
parallel/distributed algorithms
Poisson equations
Three-dimensional displays
Title A Scalable Parallel Computing Framework for Large-Scale Astrophysical Fluid Dynamics Numerical Simulation
URI https://ieeexplore.ieee.org/document/9029149
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27asMwFBVJ6NCpLUnpGw0dq8ay9bBHk9R0CMGQFLIFPcGQJsGx-_2VbCft0KWbkTWYe4XPlXTPOQA8W5VIi-MAUa4lIiFmSGCukdWGh0yIkIpGZ3bG5_N4tUryHng5cWGMMU3zmXn1j81dvt6p2h-VjZMgTFxF3wd9zlnL1TquHRIS7t6eoJnE1CuhBB1pBwfJOJ9O0qX7LzT8K-xlKgOvjfjLVKXBlOzif19zCUY_5DyYn2DnCvTMdgiKFC5ctD0PCuai9AYpG9g6NrhJMDu2YEFXo8KZ7_5Gfr6B6aEqd_suWTDb1IWG09al_gDndXufs4GL4rPz-RqBj-xtOXlHnYsCKtzmoUKCMEFDYa2mXFlhJdMOpzWzJkqEpFQ70JdWc0VcnU3cdsziwFgZEmljiV31cA0G293W3ADIlIqIFcx74RIaqNhGOjKGJBJjE0XiFgx9mNb7Vihj3UXo7u_he3Du89D2hjyAQVXW5hGcqa-qOJRPTXa_ASDMpuM
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA5zCnpS2cRvc_BoXNMm_TiOzTKxlsIm7DbyCYW5ja7195u03fTgxVtJcyjvG_q8Sd7neQB41CLiGocOooHkiLjYRwwHEmmpAtdnzKWs1plNgjQN5_Mo64CnPRdGKVU3n6ln-1jf5cu1qOxR2SBy3MhU9Afg0DpntWyt3eohLgnM-z04k5BaLRSnpe1gJxpk49FwZv4MNQMLW6FKx6oj_rJVqVElPv3f95yB_g89D2Z74DkHHbXqgXwIpybelgkFM1ZYi5QlbDwbzCQY75qwoKlSYWL7v5Gdr-BwWxbrTZsuGC-rXMJx41O_hWnV3Ogs4TT_bJ2--uAjfpmNJqj1UUC52T6UiBGfUZdpLWkgNNPclwappa-VFzFOqTSwz7UMBDGVNjEbMo0dpblLuA45NvXDBeiu1it1CaAvhEc0860bLqGOCLUnPaVIxDFWnseuQM-GabFppDIWbYSu_x5-AMeT2XuySF7TtxtwYnPSdIrcgm5ZVOoOHImvMt8W93WmvwEAWKos
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2019+20th+International+Conference+on+Parallel+and+Distributed+Computing%2C+Applications+and+Technologies+%28PDCAT%29&rft.atitle=A+Scalable+Parallel+Computing+Framework+for+Large-Scale+Astrophysical+Fluid+Dynamics+Numerical+Simulation&rft.au=Kulikov%2C+Igor&rft.au=Chernykh%2C+Igor&rft.au=Tchernykh%2C+Andrei&rft.date=2019-12-01&rft.pub=IEEE&rft.eissn=2640-6721&rft.spage=328&rft.epage=333&rft_id=info:doi/10.1109%2FPDCAT46702.2019.00066&rft.externalDocID=9029149