Enabling AI Engine Pipeline - Enabling AI Engine Pipeline - 2026.1 English - UG1702

The AI Engine Pipeline view can provide instruction pipeline details. To view AI Engine Pipeline view contents for a core, follow the instructions below.

1. In the Component Explorer, right-click on the AI Engine component to expand the Settings folder.
2. Select the launch.json to open the Launch Configurations view.
3. In the Launch Configurations view, open or create an AI Engine AIESIM launch configuration. To create one, click the + command in the toolbar menu.
   
   
4. Select the Enable Pipeline View checkbox to enable the feature.

When you run the AI Engine simulator (AIESIM), Vitis opens the Pipeline view.

The Pipeline view displays the program counter vertically and the kernel cycle count horizontally. The ID represents instruction decode, and E1-E7 are execution stages. Besides non-linear operations, most operations in the scalar unit schedule in E1 stage of the pipeline. The vector unit scheduling spans from the ID stage to the E6 stage. Address Generation Units (AGUs) spans over two pipeline stages. The address is ready in the E2 stage of the pipeline.

For load units, the data is available in the AI Engine from the memory module in the E7 stage. For the store unit, the AI Engine sends the data to the memory module in the E5 or E6 stage of the pipeline depending on the type of instruction.