Efficiency analysis of hydrodynamic calculations on GPU and CPU clusters

Speedup of parallel hydrodynamic calculations on clusters with CPUs and GPUs is considered. The CFD SigmaFlow code developed by the authors and ported for GPU by means of CUDA is used in test calculations. The incompressible flow simulation is based on a SIMPLE-like procedure and on a discretization by the control volume method on unstructured hexahedral meshes. The performance evaluation shows a high efficiency of the new generation of GPUs for GPGPU calculations.