GPUs and LandingEdge

If you have a graphics processing unit (GPU), LandingEdge will use it to run faster. In LandingEdge v2.6.45 and later, you can also assign an Inspection Point to run on one or more specific GPUs. If you allow the Inspection Point to use multiple GPUs, the system will balance the load between the processors.

For more information about supported GPUs, go to GPU Support.

Assign Specific GPUs to an Inspection Point

To assign specific GPUs to an Inspection Point:

1. Create an Inspection Point.
2. If LandingEdge detects a supported GPU, the Accelerator drop-down menu displays in the Model section. Select one of the following:
   • None (CPU): Select if you don't want the Inspection Point to use a GPU. LandingEdge will use your computer's CPU (central processing unit) instead.
   • NVIDIA GPU: Select if you have a want to assign GPUs to the Inspection Point. If LandingLens doesn't detect a GPU, it will use your computer's CPU instead.Choose if You Want to Use a GPU or Not
   Note:

   The Accelerator drop-down menu only displays if LandingEdge detects one or more supported GPUs. If it doesn't, this drop-down menu doesn't display.
3. If LandingEdge detects multiple GPUs, select the checkbox for the GPUs you want the Inspection Point to use. If you don't select any GPUs, LandingEdge will pick the first one in the list.
   Select the GPUs You Want to Use
   Note:

   Hover over a GPU to see a tooltip with the GPU identifiers. This is helpful if you have multiple GPUs that are the same model and you want to tell them apart.

   Hover Over a GPU to See More Information
4. Finish setting up the Inspection Point.

If You Change the GPU Selection

When you select a GPU, the model you selected is loaded onto that GPU. If you change the selected GPU, click Reload Model so that the model is loaded onto the new GPU.