Hybrid CPU/GPU implementation for the FE2 multi-scale method for composite problems
This thesis aims to develop a High-Performance Computing implementation to solve large composite materials problems through the use of the FE2 multi-scale method. Previous works have not been able to scale the FE2 strategy to real size problems with mesh resolutions of more than 10K elements at the...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis doctoral |
| Fecha de publicación: | 2020 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/180785 |
| Acceso en línea: | https://hdl.handle.net/2117/180785 https://dx.doi.org/10.5821/dissertation-2117-180785 |
| Access Level: | acceso abierto |
| Palabra clave: | HPC Composite materials FE2 Multi-scale CPU GPU Àrees temàtiques de la UPC::Informàtica |
| Sumario: | This thesis aims to develop a High-Performance Computing implementation to solve large composite materials problems through the use of the FE2 multi-scale method. Previous works have not been able to scale the FE2 strategy to real size problems with mesh resolutions of more than 10K elements at the macro-scale and 100^3 elements at the micro-scale. The latter is due to the computational requirements needed to carry out these calculations. This works identifies the most computationally intensive parts of the FE2 algorithm and ports several parts of the micro-scale computations to GPUs. The cases considered assume small deformations and steady-state equilibrium conditions. The work provides a feasible parallel strategy that can be used in real engineering cases to optimize the design of composite material structures. For this, it presents a coupling scheme between the MPI multi-physics code Alya (macro-scale) and the CPU/GPU-accelerated code Micropp (micro-scale). The coupled system is designed to work on multi-GPU architectures and to exploit the GPU overloading. Also, a Multi-Zone coupling methodology combined with weighted partitioning is proposed to reduce the computational cost and to solve the load balance problem. The thesis demonstrates that the method proposed scales notably well for the target problems, especially in hybrid architectures with distributed CPU nodes and communicated with multiple GPUs. Moreover, it clarifies the advantages achieved with the CPU/GPU accelerated version respect to the pure CPU approach. |
|---|