Imagen de Portada

Porting the Meso-NH atmospheric model on different GPU architectures for the next generation of supercomputers (version MESONH-v55-OpenACC)

Guardado en:
Publicado en:Geoscientific Model Development vol. 18, no. 9 (2025), p. 2679
Autor principal: Escobar, Juan
Otros Autores: Wautelet, Philippe, Pianezze, Joris, Pantillon, Florian, Dauhut, Thibaut, Barthe, Christelle, Chaboureau, Jean-Pierre
Publicado:
Copernicus GmbH
Materias:
France
Central processing units > CPUs
Graphics
Fourier transforms
Graphics processing units
Personal computers
Atmosphere
Microprocessors
Supercomputers
Atmospheric models
Energy efficiency
Nodes
Libraries
Storms
Reproducibility
Radiation
Memory management
Environmental
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:The advent of heterogeneous supercomputers with multi-core central processing units (CPUs) and graphics processing units (GPUs) requires geoscientific codes to be adapted to these new architectures. Here, we describe the porting of Meso-NH version 5.5 community weather research code to GPUs named MESONH-v55-OpenACC with guaranteed bit reproducibility thanks to its own MPPDB_CHECK library. This porting includes the use of OpenACC directives, specific memory management, communications optimization, development of a geometric multigrid (MG) solver and creation of an in-house preprocessor. Performance on the AMD MI250X GPU Adastra platform shows up to 6.0<inline-formula>×</inline-formula> speedup (4.6<inline-formula>×</inline-formula> on the NVIDIA A100 Leonardo platform), and achieves a gain of a factor of 2.3 in energy efficiency compared to AMD Genoa CPU Adastra platform using the same configuration with 64 nodes. The code is even 17.8<inline-formula>×</inline-formula> faster by halving the precision and quadrupling the nodes with a gain in energy efficiency of a factor of 1.3. First scientific simulations of three representative storms using 128&#xa0;GPUs nodes of Adastra show successful cascade of scales for horizontal grid spacing down to 100 m and grid size up to 2.1 billion points. For one of these storms, Meso-NH is also successfully coupled to the WAVEWATCH III wave model via the OASIS3-MCT coupler without any extra computational cost. This GPU porting paves the way for Meso-NH to be used on future European exascale machines.
ISSN:1991-962X
1991-9603
DOI:10.5194/gmd-18-2679-2025
Fuente:Engineering Database