Accelerated CFD Computations on Multi-GPU Using OpenMP and OpenACC

With the demand for increased computing precision and a large-scale domain in many computational fluid dynamics (CFD) problems, the computational load on the processor is getting heavier than ever. The graphical processing units (GPU) have proven to be an excellent computing platform for carrying out high precision floating-point computational loads. There is no such direct provisioning for parallelizing code across multiple GPUs using OpenACC, a directive-based programming model. Hence, a hybrid type of programming is required to tackle this problem. In this present work, hybrid type of (CPU + GPU) parallelization of the Poisson solver on multi-GPU was demonstrated using directive-based programming models (OpenMP and OpenACC), which reduced the computational time by 61 × on multi-GPU when compared with a single CPU. We have further analyzed a turbulent 3D lid-driven cavity flow using a direct numerical simulation (DNS) using this multi-GPU solver. The numerical computations and experimental results were quite in agreement.