34.6.3. Using and Managing GPGPUs

In order to use GPGPUs, you must specify in the Fluent Launcher or with the -gpgpu= ngpgpus command line option how many GPGPUs are to be used per machine (note that when launching in serial, the command line option is the only available way to specify the GPGPUS). For details, refer to the following sections:

Starting Parallel ANSYS Fluent Using Fluent Launcher
Starting Parallel ANSYS Fluent on a Windows System Using Command Line Options
Starting Parallel ANSYS Fluent on a Linux System

Once the Fluent session is running, you can view and/or select the available GPGPUs on the system using the following TUI commands:

parallel/gpgpu/show

display the available GPGPUs on the system.

parallel/gpgpu/select

select the GPGPUs to use. Note that you can only select up to the number of GPGPUs that you specified on the command line or in the Fluent Launcher when starting the session.

By default, GPGPU acceleration is applied automatically to coupled systems and not to scalar systems because scalar systems typically are not as computationally expensive. However, if desired you can enable/disable GPGPU acceleration of the AMG solver for coupled and scalar systems in the following TUI menu:

solve/set/amg-options/amg-gpgpu-options/

The menu contains commands for each supported equation type allowing you to enable/disable GPGPU acceleration, choose between AMG and FGMRES solvers, and specify various solver options.


Release 18.2 - © ANSYS, Inc. All rights reserved.