Advances in GPU hardware and dedicated programming languages have enabled the use of GPUs to accelerate CFD simulations. Ansys Fluent has recently developed a native multi-GPU solver in Ansys Fluent, which has proven to be a game-changer in terms of reducing solution time. By running the solver code entirely on GPUs, the full potential of the GPUs is unlocked, resulting in improved performance, reduced hardware costs, and lower power consumption in comparison to a CPU driven solver. In this video, through a simulation example of heat transfer in a louvered fin heat exchanger, we will demonstrate the capability of the GPU solver in Ansys Fluent 2023 R1 to solve a steady-state conjugate heat transfer problem. Along the way, we will also highlight some of the solver features supported by the GPU solver in Ansys Fluent 2023 R1 and discuss the performance differences between GPU- and CPU-driven solvers.
jQuery(function(){
var url = jQuery("#Video").attr('src');
jQuery("#myModal").on('hide.bs.modal', function(){
jQuery("#Video").attr('src', '');
});
jQuery("#myModal").on('show.bs.modal', function(){
jQuery("#Video").attr('src', url);
}); });
Simulation Files
Download the files here to follow the video step-by-step.