Stage 4: Increasing the PLIO Bitwidth and Re-generate - 2023.2 English

Vitis Tutorials: AI Engine

Document ID
Release Date
2023.2 English

Solving this problem is fairly easy. Navigate inside the FIRchain sub-system. Get the PLIO block from AMD Toolbox / AI Engine / Interface, or just type plio in the canvas. Double-click on the new block and specify:

  • PLIO width (bits): 128

  • Check Specify PLIO frequency

  • PLIO frequency (MHz) : 250

Click OK. Place the block just after the input port, and a copy of this block just before the output port:

missing image

Re-open the Model Composer Hub block, and click Generate to re-compile and re-simulate the design.

After the AI Engine simulation, the estimated throughput is 126 MSPS. This is computed from the following timestamped (green) output data, calculated for two full frame periods:

missing image

This gives around 125 MSPS which is 1/8th of the input sample rate (1 GSPS). This means that the design meets specification.