Multithreaded Implicitly Dealiased Pseudospectral Convolutions

Convolutions are used in data and image analysis and form the crux of the pseudospectral method for direct numerical simulations of fluids. Their calculation is a computationally expensive task that is facilitated by the use of FFTs at the expense of increased memory, which is required for the removal of aliased terms. Here, we present a multithreaded version of the method of implicit dealiasing (Bowman and Roberts, SIAM J. Sci. Comput. 33, 2011). Implicit dealiasing requires less memory than conventional explicit zero padding without increasing computational complexity or communication cost.