NXP eIQ Neutron Backend

This manual page is dedicated to introduction NXP eIQ Neutron backend. NXP offers accelerated machine learning models inference on edge devices. To learn more about NXP’s machine learning acceleration platform, please refer to the official NXP website.

For up-to-date status about running ExecuTorch on Neutron backend please visit the manual page.

Features

ExecuTorch v1.2 supports running machine learning models on selected NXP chips (for now only i.MXRT700). Among currently supported machine learning models are:

• Convolution-based neutral networks

• Full support for MobileNetV2 and CifarNet

Target Requirements

• Hardware with NXP’s i.MXRT700 chip or a evaluation board like MIMXRT700-EVK.

Development Requirements

• MCUXpresso IDE or MCUXpresso Visual Studio Code extension

• MCUXpresso SDK 25.12

• eIQ Neutron SDK version 3.0.0, what you can download from eIQ PyPI:

$ pip install --index-url https://eiq.nxp.com/repository eiq_neutron_sdk==3.0.0

Instead of manually installing requirements, except MCUXpresso IDE and SDK, you can use the setup script:

$ ./examples/nxp/setup.sh

Using NXP eIQ Backend

To test the eIQ Neutron Backend, both AoT flow for model preparation and Runtime for execution, refer to the Getting started with eIQ Neutron NPU ExecuTorch backend

For a quick overview how to convert a custom PyTorch model, take a look at our example python script.

Runtime Integration

An example runtime application using the eIQ NSYS (eIQ Neutron Simulator) is available examples/nxp/executor_runner, described in the tutorial Getting started with eIQ Neutron NPU ExecuTorch backend

To learn how to run the converted model on the NXP hardware, use one of our example projects on using ExecuTorch runtime from MCUXpresso IDE example projects list. For more finegrained tutorial, visit this manual page.

For guideline how to update the eIQ Neutron Runtime on MCUXpresso SDK, follow the instructions from the eIQ Neutron SDK package docs/NeutronSDKUserGuide.md available here https://www.nxp.com/design/design-center/software/eiq-ai-development-environment/eiq-toolkit-for-end-to-end-model-development-and-deployment:EIQ-TOOLKIT.

Reference

→nxp-partitioner — Partitioner options.

→nxp-quantization — Supported quantization schemes.

→tutorials/nxp-tutorials — Tutorials.

→nxp-dim-order — Dim order support (channels last inputs).

→nxp-kernel-selection — Neutron Firmware Kernel Selection support.