Visualize Ethos-U NPU performance with ExecuTorch on Arm FVPs
Introduction
Overview
Understand the ExecuTorch workflow
Set up your ExecuTorch environment
Set up the Corstone-320 Fixed Virtual Platform
Deploy and run Mobilenet V2 on the Corstone-320 FVP
Enable GUI and deploy a model on Corstone-320 FVP
Evaluate Ethos-U Performance
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Introductory
Reading time:  2 hrs
Last updated:  13 Aug 2026
Skill level:
  Introductory
Reading time:
  2 hrs
Last updated:
  13 Aug 2026
Author:Waheed Brown, Arm
Arm IP:Cortex-A Cortex-M Ethos-U
Tags: ML Linux macOS Arm Virtual Hardware FVP Python PyTorch ExecuTorch Arm Compute Library GCC Docker
Author:
  • Waheed Brown, Arm
Arm IP:
Cortex-A Cortex-M Ethos-U
Tags:
ML Linux macOS Arm Virtual Hardware FVP Python PyTorch ExecuTorch Arm Compute Library GCC Docker

Who is this for?

This is an introductory topic for developers and data scientists who are new to TinyML and want to visualize ExecuTorch model performance on virtual Arm hardware.

What will you learn?

Upon completion of this Learning Path, you will be able to:

  • Identify Arm-based targets suitable for TinyML workloads
  • Install and configure Fixed Virtual Platforms (FVPs)
  • Deploy a TinyML model using ExecuTorch on a Corstone-320 FVP
  • Visualize model execution using the FVP graphical interface

Prerequisites

Before starting, you will need the following:

  • Familiarity with basic machine learning concepts
  • A Linux or macOS computer with Python 3 installed

Summary

AI-assisted

This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
You’ll use ExecuTorch and the Corstone-320 FVP to explore TinyML execution with Ethos-U. First, you’ll set up ExecuTorch, install the FVP, and export a model with the ahead-of-time workflow. Then, you’ll run MobileNet V2 and use the FVP graphical interface to visualize CPU and NPU activity without physical hardware.

Frequently asked questions

AI-assisted

These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
What additional setup do I need before running the FV on macOS?
Follow the guidance in the FVPs-on-Mac GitHub repository before launching the Corstone-320 FVP.
Where is the MobileNet V2 example located in the ExecuTorch repository?
The Python code for MobileNet V2 is in executorch/examples/models/mobilenet_v2/model.py. Use this example when deploying the model to the Corstone-320 FVP.
How do I run the MobileNet V2 example on the Corstone-320 FVP?
Use the provided run.sh script with the additional parameters shown in the steps after completing the environment and FVP setup. Run the script from the executorch repository.
How do I know the Corstone-320 FVP installed and started correctly?
The FVP should launch without errors and present its graphical interface.
How do I verify that execution uses the simulated Ethos-U NPU?
Use the FVP graphical interface to visualize model execution and look for activity corresponding to CPU and NPU components.
Next