Parallelization of Direct-Forcing Immersed Boundary Method Using OpenACC

A parallelization of Poisson equation solver is developed by using the parallel algorithm of red-black SOR method performed on GPU by OpenACC. We use the parallel computing solver to solve the fluid-structure interaction problem with direct-forcing immersed boundary method. The speedup for the parallel computing solver is up to 8.62 times. In addition, we present that the optimization of the red-black SOR (RBSOR) algorithm for the problem with the complex-geometry objects is to allocate the same memory on two variables which is to take advantages of accessing data by random indexes and formatted indexes. The implementation of parallel computing RBSOR with OpenACC is efficient to delegate the simulation of fluid-structure interaction problem on the GPU.