Abstract
Abstract Numerically solving time-fractional diffusion equations, especially in three space dimensions, is a daunting computational task. This is due to the huge requirements of both computation time and memory storage. Compared with solving integer-ordered diffusion equations, the costs for time and storage both increase by a factor that equals the number of time steps involved. Aiming to overcome these two obstacles, we study in this paper three programming techniques: loop unrolling, vectorization and parallelization. For a representative numerical scheme that adopts finite differencing and explicit time integration, the performance-enhancing techniques are indeed shown to dramatically reduce the computation time, while allowing the use of many CPU cores and thereby a large amount of memory storage. Moreover, we have developed simple-to-use performance models that support our empirical findings, which are based on using up to 8192 CPU cores and 12.2 terabytes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have