Gabriel Hautreux

Gabriel Hautreux

Auto-generated profile, based on publicly available information

Gabriel Hautreux

CINES, France

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

12 November 2023
Verified
Conference Paper
Open access
NINaima Alaoui Ismaili
Naima Alaoui Ismaili
PWPhilippe Wautelet
Philippe Wautelet
JMJuan Escobar Munoz
Juan Escobar Munoz
GHGabriel Hautreux
Gabriel Hautreux
This paper presents the results of our efforts to port Meso-NH, an atmospheric non-hydrostatic research model, to AMD MI250X GPUs using OpenACC on the ADASTRA Machine, a technology similar to the Frontier system [1]. Meso-NH is a versatile model that covers a wide range of resolutions from synoptic to turbulent scales, and is designed for studies of physics and chemistry. It can be used in 3D for storms and thunderstorms simulation, 2D or 1D for the simulation of academic studies. Numerical simulation of the atmosphere is crucial for understanding and predicting weather and climate extremes. Current numerical weather prediction codes are limited to specibic resolutions on global and regional scales. The Meso- NH code, however, tackles scales and complexities beyond what is typically used in operational forecasting. We collaborated with GENCI, CINES, HPE, and AMD on the "progress contract," for ADASTRA machine aiming to achieve simulations at hectometric resolution for recent storms in the Atlantic and Mediterranean regions, characterized by extreme wind gusts. This higher resolution allows us to explicitly represent a cascade of scales, from the storm core (>100 km) to the deep and shallow convective circulations behind the gusts (<1 km). The successful porting of Meso-NH to AMD MI250X GPUs made this numerical achievement possible. The paper focuses on the challenges faced during the porting process, optimization strategies, and the lessons learned throughout the project. Additionally, we share the current performance results from relevant benchmark problems. A comparative study highlights the performance and energy consumption aspects of a fraction of the code that dominates the computation time. Notably, we achieved a speed-up of 3.5 times compared to computation on AMD- Genoa processors. The results of this porting effort open up new possibilities for atmospheric simulations at hectometric resolutions, enhancing the accuracy and sophistication of weather phenomena representation. The collaboration between different institutions has paved the way for advanced meteorological research, contributing to the ongoing progress in the bield.

15 November 2025
Verified
Conference Paper
Open access
GHGabriel Hautreux
Gabriel Hautreux
AGAbdoulaye Gamatié
Abdoulaye Gamatié
GSGilles Sassatelli
Gilles Sassatelli