Setting Up the Host

Use the following steps to set up the host:
  1. Clone the Vitis AI repository:
    git clone https://github.com/xilinx/vitis-ai
  2. Install the Docker, and add the user to the docker group. Link the user to docker installation instructions from the following docker's website:
  3. Any GPU instructions will have to be separated from Vitis AI.
  4. Set up Vitis AI to target Alveo cards (Only for systems with Alveo cards). To target Alveo cards with Vitis AI for machine learning workloads, you must install the following software components:
    • Xilinx Runtime (XRT)
    • Alveo Deployment Shells (DSAs)
    • Xilinx Resource Manager (XRM) (xbutler)
    • Xilinx Overlaybins (Accelerators to Dynamically Load – binary programming files)

    While it is possible to install all of these software components individually, a script has been provided to automatically install them at once. To do so:

    1. Run the following commands:
      cd Vitis-AI/alveo/packages
      sudo su
      ./install.sh
    2. Power cycle the system.
  5. Start the Docker Container.
    1. Change directories to Vitis AI:
      cd Vitis-AI/
    2. Run one of the following command sets.
      • For a CPU tools container:
        ./docker_run.sh xilinx/vitis-ai:1.0.0-cpu
        
      • For a GPU-enabled tools container:
        cd Vitis-AI/docker
          ./docker_build.sh
          cd Vitis-AI
          ./docker_run.sh xilinx/vitis-ai:runtime-1.0.0-gpu
    3. Upon starting the container your current working directory will be mounted to: /workspace