Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 

README.md

AMD logo

AMD Vitis™ AI Engine Tutorials

See Vitis™ Development Environment on amd.com
See Vitis™ AI Development Environment on amd.com

GMIO Tutorial

Version: Vitis 2025.2

Introduction

This tutorial targets AIE-ML devices, but shares test cases and description files with AIE 02-using-gmio.

IMPORTANT: Before beginning the tutorial, install the AMD Vitis™ unified software platform 2025.2. This Vitis release includes all the embedded base platforms including the VCK190 base platform that this tutorial uses. Also, download the Common Images for Embedded Vitis Platforms from this link.

The ‘common image’ package contains a prebuilt Linux kernel and root file system that you can use with AMD Versal™ boards for embedded design development using the Vitis software platform.

Before starting this tutorial, run the following steps:

  1. Go to the directory where you have unzipped the Versal Common Image package.
  2. In a Bash shell, run the /Common Images Dir/xilinx-versal-common-v2025.2/environment-setup-cortexa72-cortexa53-amd-linux script. This script sets up the SDKTARGETSYSROOT and CXX variables. If the script is not present, you must run the /Common Images Dir/xilinx-versal-common-v2025.2/sdk.sh.
  3. Set up your ROOTFS and IMAGE to point to the rootfs.ext4 and Image files located in the /Common Images Dir/xilinx-versal-common-v2025.2 directory.
  4. Set up your PLATFORM_REPO_PATHS environment variable to $XILINX_VITIS/base_platforms.

This tutorial targets VEK280 board for 2025.2 version.

Objectives

After completing this tutorial, you can:

  • Understand the programming model and software programmability of the AI Engine GMIO
  • Profile GMIO design in AI Engine simulator and improve performance
  • Profile GMIO performance by event trace API or Linux system timer
  • Measure the NOC bandwidth and make trade offs between GMIO and PLIO

Steps

Step 1 - AI Engine GMIO: Copy test case from Single AIE test cases.

Follow instructions in AIE GMIO Programming Model. But, run all make commands with ARCH=aie-ml. For example:

To build AIE graph, run:

make aie ARCH=aie-ml

To run aiesimulator, run:

make aiesim ARCH=aie-ml

To run HW emulation, run:

make run_hw_emu ARCH=aie-ml

After Linux has booted, run the following commands at the Linux prompt. To exit QEMU press Ctrl+A and then press x. (this is only for HW cosim):

./host.exe a.xclbin

To build system design targeting HW flow, run:

make package TARGET=hw ARCH=aie-ml

To run in hardware, run the following commands at the Linux prompt after booting Linux. Login with username:petalinux, password:petalinux, then run sudo su with password:petalinux before running following commands:

cd /run/media/mm*1
./host.exe a.xclbin

Step 2 - AI Engine GMIO Performance Profile: Copy test case from Performance profile test cases.

Follow instructions in AIE GMIO Performance Profile. But, run all make commands with ARCH=aie-ml. See run commands in step 1.

Copyright © 2020–2026 Advanced Micro Devices, Inc.

Terms and Conditions