Howto: Bringing up ExecuTorch on a Bare Metal Microcontroller

Legal Notice

Copyright © 2026 Embecosm Limited

The document entitled Howto: Bringing up ExecuTorch on a Bare Metal Microcontroller by Jeremy Bennett, Pietra Ferreira, William Jones and Shane Slattery of Embecosm is licensed under a Creative Commons Attribution ShareAlike 4.0 International License.

You are free to copy, distribute and adapt this work, provided you attribute the work in the manner specified by the author or licensor. If you alter, transform, or build upon this work, you may distribute the resulting work only under the same or similar license to this one.

Full license text: https://creativecommons.org/licenses/by-sa/4.0/

• 1. Introduction
  • 1.1. Target audience
  • 1.2. Further information
  • 1.3. Structure of the document
  • 1.4. Acknowledgements
  • 1.5. Licensing and legal notices
• 2. ExecuTorch Overview
  • 2.1. About PyTorch and ExecuTorch
  • 2.2. The ExecuTorch architecture
  • 2.3. Structure of the ExecuTorch repository
  • 2.4. The target: CV32E40Pv2
• 3. Setting up to run the examples
  • 3.1. Prerequisites
  • 3.2. File hierarchy
  • 3.3. The Python virtual environment
  • 3.4. Getting the source code
  • 3.5. Building and running the target model
• 4. Bringing up ExecuTorch AoT for the CV32E40Pv2
  • 4.1. Files to be changed
  • 4.2. Modifying the build system for CORE-V
  • 4.3. The CORE-V AoT backend implementation
  • 4.4. The CORE-V AoT backend driver
  • 4.5. An example AI model
  • 4.6. Building and running ExecuTorch AoT for CORE-V
• 5. Implementing an ExecuTorch runtime for the CV32E40Pv2
  • 5.1. Files to be changed
  • 5.2. Modifying the build system for CORE-V
  • 5.3. The CORE-V runtime backend implementation
  • 5.4. The CORE-V runtime backend driver
  • 5.5. Building and running ExecuTorch runtime for CORE-V
• 6. Optimizing ExecuTorch by using delegation
  • 6.1. Overview of how delegation works
  • 6.2. Files to be changed
  • 6.3. Adding a new test model
  • 6.4. Modifying the ExecuTorch AoT for delegation
  • 6.5. Modifying the ExecuTorch runtime for delegation
• 7. Benchmarking ExecuTorch
  • 7.1. Overview of how to benchmark ExecuTorch
  • 7.2. Files to be changed
  • 7.3. Modifying the ExecuTorch runtime for benchmarking
  • 7.4. Benchmarking ExecuTorch
• 8. Further optimization of ExecuTorch
  • 8.1. Overview of optimization
  • 8.2. Optimizing for a memory hierarchy
  • 8.3. Optimizing for multi-core operation
  • 8.4. Optimization for custom accelerators
  • 8.5. Optimization by quantization
  • 8.6. Operator fusion
  • 8.7. Customized runtime for deeply embedded edge inference
• 9. Appendix: An introduction to neural networks with PyTorch
  • 9.1. Key features of neural networks
  • 9.2. Installing PyTorch and associated tools
  • 9.3. An example model: a 7 segment display recognizer
  • 9.4. Inspecting models
• 10. Glossary
• 11. References
• Index