NumPEx
The national network for reproducible research days 2024
From March 26 to 28, the national network for reproducible research days 2024 will be held in Grenoble and online. It's the perfect place to discuss reproducibility issues, which affect all scientific fields, and to share best practices and recommendations.
NumPEx supports Guix as a software reproducibility solution and invites you to attend the presentation by Ludovic Courtès, Inria research engineer at Inria Bordeaux Sud-Ouest, and Pierre-Antoine Bouttier, CNRS - Centre national de la recherche scientifique research engineer at Gricad, on Wednesday 27/03 at 1:30 pm, either on site or by videoconference!
GAP 2024
The Grenoble Artificial Intelligence for Physical Sciences (GAP 2024) workshop, supported by NumPEx, will explore the intersections between machine learning research and the study of physical systems described by systems of differential equations. We expect to gather researchers from machine learning, computational physics and diverse application fields, in order to foster collaborations and strengthen connections within the scientific community, and in particular across the alpine region. Application fields will include climate science, geophysics, solid state physics, and neuroscience.
The program is based on an impressive line-up of keynote speakers from the emerging domain of AI4Science.
2024 Teratec Forum
The TERATEC Forum is a major event in Europe that brings together the best international experts in high-performance computing (HPC) in digital simulation, high-performance computing (HPC), massive data processing, artificial intelligence and quantum computing. And NumPEx members are excited to be part of this community: one of the main drivers of the NumPEx program is the current paradigm shift in HPC system architectures with the rapid emergence of new technologies and applications (such as the digital continuum and AI), which necessitates the development and adaptation of HPC software stacks for forthcoming Exascale supercomputers.
NumPEx will be present and will have his own stand at Teratec.
Journées Programmation GPU
The NumPEx Accelerator Working Group is organizing two days dedicated on GPU programming.
This event will be adress an overview of the various approaches currently available for an effective use of GPUs, including direct programming, libraries, frameworks, and task-based methods. You will benefit from insights and experiences with different codes across these approaches.
While it is not a full training on each tool, the aim is to leave with a clear understanding of the advantages and disadvantages of each approach.
Program:
🔸June 12 from 11 AM: General presentation and introduction
🔸 June 12 early afternoon: Overview of approaches: CUDA, Frameworks, specialized and generic libraries, languages, task-based programming
🔸 June 12 late afternoon: Experience sharing part 1
🔸 June 13 morning: Experience sharing part 2
🔸 June 13 early afternoon: Integration with the PEPR NumPEx, discussion of identified needs for the call for projects
2024 InPEx Workshop
Following the previous first InPEx meeting and the InPEx workshop held in Reims in 2023, the InPEx community will meet in June 2024 in Sitges (Spain). The workshop will gather around 100 experts in the HPC fields from the European Union, Japan and the United States.
SciML Workshop
This event is an opportunity for scientists and researchers to gather, discuss, and collaborate on the latest advancements in scientific machine learning.
SciML is a relatively new research field that combines machine learning (ML) and scientific computing to develop robust, reliable, and interpretable methods for solving complex problems like multidimensional partial differential equations, parameter identification, and inverse problems.
Highlights of the event:
🔸Introduction to the mathematical concepts lying at the foundation of machine learning as used in scientific computing;
🔸Overview of the different approaches developed to address these problems;
🔸Insight on the latest numerical tools in scientific machine learning and data inclusion for the solution of PDEs.