Getting started with AI on NXP i.MX8M Plus - Development - Developing software for the board - Building the SDK

Getting started with AI on NXP i.MX8M Plus
Introduction
Overview i.MX8M Plus hardware specifications Development tools Development kit DART-MX8M-PLUS Development kit Quick getting started Yocto minimal image Flashing SD card First steps on the board
Development
Gatesgarth and Hardknott Yocto versions Downloading Yocto images for NXP based BSP Building an imx-core-image Flashing SD card Integrating multimedia software stack Installing GStreamer Installing OpenCV Integrating Artificial Intelligence software stack Installing TensorFlow Lite for NXP based images Installing R2Inference Installing GstInference Developing software for the board Building the SDK Crosscompiling apps for GStreamer, TensorFlow Lite, and OpenCV Exploring TensorFlow Lite delegates for prototyping
Neural Processing Unit
Introduction Profiling the NPU Installing gputop Setting the board on debug mode Use Case experiments: Smart Parking Introduction to the use case License Plate Detection TinyYOLO version 3 Training a model compatible with GstInference License Plate Recognition Rosetta Getting the model prototyping Bash scripts for CPU usage and time estimation Serial experiments Parallel Experiments Results
GStreamer
Exploring Rosetta element for character recognition Example pipelines Smart Parking Video inferences Image inferences Video streaming
Contact Us

Building the toolchain

First of all, we need to set the environment for bitbaking the Software Development Kit from the imx-image-core:

cd $HOME/<your image folder>

If you have not built the image in the previous steps please execute the following commands, otherwise skip these commands:

# Create a build folder
mkdir build_xwayland_imx_image_core

# Creating the configuration files, but you will need to add the modules to local.conf and bblayers.conf
source var-setup-release.sh -b build_xwayland_imx_image_core

# Compiling the SDK
bitbake imx-image-core -c populate_sdk

If you have followed the entire building process until here, just set the environment by:

source setup-environment build_xwayland_imx_image_core

bitbake imx-image-core -c populate_sdk

Installing the SDK

After the bitbake command has finished, then an sdk folder is created at

cd $HOME/<your image folder>/build_xwayland_imx_image_core/tmp/deploy/sdk

At this path, then execute the bash script that looks like something like the following, in order to install the toolchain at an specific folder:

./fsl-imx-xwayland-glibc-x86_64-imx-image-core-cortexa53-crypto-imx8mp-var-dart-toolchain-5.10-gatesgarth.sh

After the installation a message like the following will appear:

SDK has been successfully set up and is ready to be used.
Each time you wish to use the SDK in a new shell session, you need to source the environment setup script e.g.
 $ . /opt/fsl-imx-xwayland/<your Yocto version>/environment-setup-cortexa53-crypto-poky-linux

Using the SDK

As shown in the last message from the previous section, you can configure your crosscompilation environment by executing the following command:

. /opt/fsl-imx-xwayland/<your Yocto version>/environment-setup-cortexa53-crypto-poky-linux

To ensure that your environment is configured properly, examine the $CC variable:

echo $CC

Simple example

Suppose you have a folder at your root directory($HOME) called test_toolcahin. Go there, configure the crosscompilation environment and write the following code in a file called test.cpp:

#include <stdio.h>

int main () {
  printf("Hello from arm\n");
  return 0;
}

Once you have this code, open up a terminal and execute the following commands:

cd $HOME/test_toolcahin

# Configuring the toolchain:
source /opt/fsl-imx-xwayland/<your Yocto version>/environment-setup-cortexa53-crypto-poky-linux

# Crosscompiling the test.cpp code:
$CC -O test test.cpp