Methods and features of parallel algorithms for numerical simulation of optical waves propagation are considered. The scalar parabolic equation for a complex amplitude of monochromatic waves was solved numerically, using the Fourier transform method for homogeneous media and split-step Fourier method for inhomogeneous media. Two parallel algorithms, using OpenMP technology with MKL library for Intel multicore processors and CUDA technology for NVIDIA graphic accelerators have been created. The comparison of two approaches with each other and with a common sequential algorithm, using FFTW library, was performed by calculation of average number of test task solutions per second. It is shown that parallel algorithms have a considerable advantage in speed (by tens times) to the common sequential algorithm in accordance with the grid size in computational task. When comparing the performance of the above two parallel techniques with each other the results were as follows: for grids up to1024 ґ1024 the approach, using OpenMP technology, holds the lead, while for the large grids (from 1024 ґ1024 and more) the approach, using CUDA technology, was faster. The obtained results are discussed and recommendations about transition from sequential algorithms to the parallel ones are given.
OpenMP, CUDA, parallel programming, wave propagation simulation, computational optics