Performance of 3D Wave Field Modeling Using the Staggered Grid Finite Difference Method with General-Purpose Processors

This paper aims to provide a quantitative understanding of the performance of numerical modeling of a wave field equation using general-purpose processors. In particular, this article presents the most important aspects related to the memory workloads and execution time of the numerical modeling of both acoustic and fully elastic waves in isotropic and anisotropic mediums. The results presented in this article were calculated for the staggered grid finite difference method. Our results show that the more realistic the seismic wave simulations that are performed, the more the demand for memory and the computational capacity of the computing environment increases. The results presented in this article allow the estimation of the memory requirements and computational time of wavefield modeling for the considered model (acoustic, elastic or anisotropic) so that their feasibility can be assessed in a given computing environment and within an acceptable time. Understanding the numerical modeling performance is especially important when graphical processing units (GPU) are utilized to satisfy the intensive calculations of three-dimensional seismic forward modeling.