My paper, GPU-centric resolved-particle disperse two-phase flow simulation using the Physalis method, has recently been published in the Journal Computer Physics Communications. The sibling to my previous paper, Resolved-particle simulation by the Physalis method: Enhancements and new capabilities, the current work more thoroughly details the algorithmic advancements I developed to improve the computational throughput of the Physalis method itself. As can be seen in the figure below, the largest simulations run more than 60 times faster when using an Nvidia Titan GPU than an Intel CPU alone.
We present work on a new implementation of the Physalis method for resolved-particle disperse two-phase flow simulations. We discuss specifically our GPU-centric programming model that avoids all device-host data communication during the simulation. Summarizing the details underlying the implementation of the Physalis method, we illustrate the application of two GPU-centric parallelization paradigms and record insights on how to best leverage the GPU’s prioritization of bandwidth over latency. We perform a comparison of the computational efficiency between the current GPU-centric implementation and a legacy serial-CPU-optimized code and conclude that the GPU hardware accounts for run time improvements up to a factor of 60 by carefully normalizing the run times of both codes.