Analysis of impact of general-purpose graphics processor units in supersonic flow modeling

Abstract

Computational methods are widely used in prediction of complex flowfields associated with off-normal situations in aerospace engineering. Modern graphics processing units (GPU) provide architectures and new programming models that enable to harness their large processing power and to design computational fluid dynamics (CFD) simulations at both high performance and low cost. Possibilities of the use of GPUs for the simulation of external and internal flows on unstructured meshes are discussed. The finite volume method is applied to solve three-dimensional unsteady compressible Euler and Navier-Stokes equations on unstructured meshes with high resolution numerical schemes. CUDA technology is used for programming implementation of parallel computational algorithms. Solutions of some benchmark test cases on GPUs are reported, and the results computed are compared with experimental and computational data. Approaches to optimization of the CFD code related to the use of different types of memory are considered. Speedup of solution on GPUs with respect to the solution on central processor unit (CPU) is compared. Performance measurements show that numerical schemes developed achieve 20 to 50 speedup on GPU hardware compared to CPU reference implementation. The results obtained provide promising perspective for designing a GPU-based software framework for applications in CFD.

Aero-optical effects in free and wall-bounded turbulent compressible flows

“…The computational procedure is implemented in C/C++ programming language. Parallelization of the computational procedure is performed by a message passing interface (MPI) and general-purpose graphics processing units (GPU) [23].…”

A Multi‐GPU Parallel Algorithm in Hypersonic Flow Computations

“…The GPU architecture contains different types of memory to access data, such as global, constant, texture, shared, and local memories and registers [12,21]. Figure 4 shows the memory hierarchy of a GPU.…”

“…Wang et al [20] discussed DNS and Large Eddy Simulation (LES) on a turbulent wall-bounded flow using Lattice Boltzmann method and multiple GPUs, and the acceleration performance has been discussed. Emelyanov et al [21] discussed the popular CFD benchmark solution of the flow over a smooth flat plate on a GPU with various meshes, and the speedup reached more than 46 times. Zhang et al [22] performed an implicit meshless method for compressible flow on an NVIDIA GTX TITAN GPU, and the solution agrees well with experimental results.…”

The effect of the cone rotation in the supersonic gas flow on the velocity propagation of perturbations in the boundary layer

“…Aerodynamics of bodies in high-speed flight in the atmosphere was always on the top of research needs of aerospace science and technology [1,2,3]. Effective estimates of aero-dynamical loads are necessary for precise evaluation of deorbiting time for satellites [4].…”