RAMSES-yOMP: Performance Optimizations for the Astrophysical Hydrodynamic Simulation Code RAMSES

Developing an efficient code for large, multiscale astrophysical simulations is crucial in preparing for the upcoming era of exascale computing. RAMSES is an astrophysical simulation code that employs parallel processing based on the message-passing interface (MPI). However, it has limitations in co...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:The Astrophysical journal Ročník 978; číslo 1; s. 96 - 105
Hlavní autori: Han, San, Dubois, Yohan, Lee, Jaehyun, Kim, Juhan, Cadiou, Corentin, Yi, Sukyoung K.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Philadelphia The American Astronomical Society 01.01.2025
IOP Publishing
American Astronomical Society
Predmet:
Annan fysik
Astronomy software
Computational astronomy
Computational methods
Computer and Information Sciences
Computer graphics and computer vision
Data- och informationsvetenskap (Datateknik)
Datorgrafik och datorseende
Distributed memory
Fusion, Plasma and Space Physics
Fusion, plasma och rymdfysik
Fysik
Galaxy evolution
Memory management
Message passing
Multiprocessing
Natural Sciences
Naturvetenskap
Other Physics Topics
Parallel processing
Physical Sciences
Processors
Sciences of the Universe
Simulation
Galaxy evolution
Astrophysics - Astrophysics of Galaxies
Computational methods
Computational astronomy
Astrophysics - Instrumentation and Methods for Astrophysics
Astronomy software
ISSN:0004-637X, 1538-4357, 1538-4357
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Developing an efficient code for large, multiscale astrophysical simulations is crucial in preparing for the upcoming era of exascale computing. RAMSES is an astrophysical simulation code that employs parallel processing based on the message-passing interface (MPI). However, it has limitations in computational and memory efficiency when using a large number of CPU cores. The problem stems from inefficiencies in workload distribution and memory allocation that inevitably occur when a volume is simply decomposed into domains equal to the number of working processors. We present RAMSES-yOMP, which is a modified version of RAMSES designed to improve parallel scalability. Major updates include the incorporation of open multiprocessing into the MPI parallelization to take advantage of both the shared and distributed memory models. Utilizing this hybrid parallelism in high-resolution benchmark simulations with full prescriptions for baryonic physics, we achieved an increase in performance by a factor of 2 in the total run-time, while using 75% less memory and 30% less storage than the original code, when using the same number of processors. These improvements allow us to perform larger or higher-resolution simulations than what was feasible previously.
Bibliografia:AAS57878
Laboratory Astrophysics, Instrumentation, Software, and Data
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0004-637X
1538-4357
1538-4357
DOI:10.3847/1538-4357/ad98f4