Multi-Level GNN Preconditioner for Solving Large Scale Problems
This addresses the problem of efficient and scalable solving of large-scale simulations for researchers and engineers in computational fields, offering a hybrid approach that combines machine learning with traditional methods, though it appears incremental by integrating existing techniques.
The paper tackles the challenge of solving large-scale numerical simulations by introducing a GNN-based preconditioner within a multi-level Domain Decomposition framework, which enhances a Krylov method to converge with any desired accuracy and is adaptable to meshes of any size and shape, executed on GPUs.
Large-scale numerical simulations often come at the expense of daunting computations. High-Performance Computing has enhanced the process, but adapting legacy codes to leverage parallel GPU computations remains challenging. Meanwhile, Machine Learning models can harness GPU computations effectively but often struggle with generalization and accuracy. Graph Neural Networks (GNNs), in particular, are great for learning from unstructured data like meshes but are often limited to small-scale problems. Moreover, the capabilities of the trained model usually restrict the accuracy of the data-driven solution. To benefit from both worlds, this paper introduces a novel preconditioner integrating a GNN model within a multi-level Domain Decomposition framework. The proposed GNN-based preconditioner is used to enhance the efficiency of a Krylov method, resulting in a hybrid solver that can converge with any desired level of accuracy. The efficiency of the Krylov method greatly benefits from the GNN preconditioner, which is adaptable to meshes of any size and shape, is executed on GPUs, and features a multi-level approach to enforce the scalability of the entire process. Several experiments are conducted to validate the numerical behavior of the hybrid solver, and an in-depth analysis of its performance is proposed to assess its competitiveness against a C++ legacy solver.