- Use of graph neural networks provides a way to solve the matrix equation systems using GPUs
- Approximation of SIMPLE algorithm terms that disregarded in the traditional approaches lead to a considerable improvement of performance, accuracy and robustness for several canonical, benchmark and simple Industrial-typical CFD cases
- exaSIMPLE code permits all CFD practitioners to reproduce the results here obtained and transfer the major findings to any CFD code
L1_exaMLSolver contains the full codebase for the exaSOLVER GNN pipeline
L2 contains the full codebase for the pressure-velocity coupling improvements
Detailed user guides for each of these are contained in their respective repositories.