An Implicit GNN Solver for Poisson-like problems

Autor: Nastorg, Matthieu, Bucci, Michele Alessandro, Faney, Thibault, Gratien, Jean-Marc, Charpiat, Guillaume, Schoenauer, Marc

This paper presents $\Psi$-GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions. By leveraging the Implicit Layer Theory, $\Psi$-GNN models an "infinitely" deep network, thus

Externí odkaz: http://arxiv.org/abs/2302.10891

Machine Learning model for gas-liquid interface reconstruction in CFD numerical simulations

Autor: Nakano, Tamon, Bucci, Alessandro Michele, Gratien, Jean-Marc, Faney, Thibault, Charpiat, Guillaume

The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids. A major bottleneck of the VoF method is the interface reconstruction step due to its high computational c

Externí odkaz: http://arxiv.org/abs/2207.05684

DS-GPS : A Deep Statistical Graph Poisson Solver

Autor: Nastorg, Matthieu, Schoenauer, Marc, Charpiat, Guillaume, Faney, Thibault, Gratien, Jean-Marc, Bucci, Michele Alessandro

Publikováno v: NeurIPS 2022-Machine Learning and the Physical Sciences, workshop
NeurIPS 2022-Machine Learning and the Physical Sciences, workshop, Dec 2022, New-Orleans, United States

International audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______165::1ee1520f0f6d1056f9a0aac13cb2797e
https://inria.hal.science/hal-03864015

Evaluation of the performance portability layer of different linear solver packages with alien, an open generic and extensible linear algebra framework

Autor: Anciaux-Sedrakian, Ani, Chevalier, Cédric, de Chaisemartin, Stéphane, Gratien, Jean-Marc, Guignon, Thomas, Havé, Pascal, Möller, Nathalie, Tunc, Xavier

Publikováno v: ECCOMAS 2022 : 8th European Congress on Computational Methods in Applied Sciences and Engineering
ECCOMAS 2022 : 8th European Congress on Computational Methods in Applied Sciences and Engineering, Jun 2022, Oslo, Norway

International audience; Applications to solve large and complex partial derivative equation systems often rely nowadays on frameworks like Arcane, Dune, Feel++. Linear solver packages like PETSc or Trilinos are used to manage linear systems and provi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3515::0619c637e26e1b85bb062177be8f1afb
https://hal.science/hal-03790551/document

ArcFVDSL, a DSEL Combined to HARTS, a Runtime System Layer to Implement Efficient Numerical Methods to Solve Diffusive Problems on New Heterogeneous Hardware Architecture

Autor: Gratien Jean-Marc

Publikováno v: Oil & Gas Science and Technology, Vol 72, Iss 2, p 12 (2017)

Nowadays, some frameworks like Arcane and Dune offer a number of advanced tools to deal with the complexity related to parallelism, meshes and linear solvers. However, they do not handle the high level complexity related to discretization methods and

Externí odkaz: https://doaj.org/article/53496564502845dda49099a74b04c8d4