# Profile ExecuTorch models with SME2 on Arm

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/)
- [Explore ExecuTorch profiling with SME2](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/01-overview/)
- [Set up the ExecuTorch profiling environment](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/02-setup-and-pipeline/)
- [Export PyTorch models and analyze performance](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/03-model-onboarding-and-profiling/)
- [Automate profiling workflows with AI agents](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/04-agent-skills/)
- [Next Steps](https://learn.arm.com/learning-paths/cross-platform/sme-executorch-profiling/_next-steps/)

## About this Learning Path

|                |                    |
|----------------|--------------------|
| Skill level:   | Advanced           |
| Reading time:  | 1 hr 30 min        |
| Last updated:  | 12 Nov 2026        |

### Authors:
- Jason Zhu, Arm
- Tyler Mullenbach, Arm
- Damien Dooley

### Arm IP:
- [Cortex-A](https://support.arm.com/?tab=compute-ip&Product%20Type=Application%20Processors)
- [Arm C1](https://support.arm.com/?tab=compute-ip&Product%20Type=Application%20Processors)

### Tags:
- [AI/ML](https://learn.arm.com/tag/ai-ml/)
- [macOS](https://learn.arm.com/tag/macos)
- [Android](https://learn.arm.com/tag/android)
- [ExecuTorch](https://learn.arm.com/tag/executorch)
- [Python](https://learn.arm.com/tag/python)
- [CMake](https://learn.arm.com/tag/cmake)
- [SME2](https://learn.arm.com/tag/sme2)

### Who is this for?
This is an advanced topic for developers and performance engineers who deploy ExecuTorch models on Arm devices and want to understand and reduce inference latency.

### What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
- Understand how SME2 acceleration changes the performance profile of ExecuTorch models by reducing compute-bound bottlenecks
- Interpret operator-level and operator-category breakdowns (for example, convolution, GEMM, data movement, and other operators)
- Identify which operators benefit most from SME2 acceleration and which operators become the new performance bottlenecks
- Apply a model-agnostic profiling workflow that you reuse across different models and deployments
- Make evidence-based optimization decisions by comparing execution profiles with SME2 enabled and disabled

### Prerequisites
Before starting, you'll need the following prerequisites:
- An Apple Silicon macOS host with Python 3.9 or later and CMake 3.29 or later
- Basic familiarity with ExecuTorch or PyTorch
- Optionally, an Android device with Armv9 and SME2 support for on-device testing (if used, configure power management settings to ensure consistent performance measurements)

### Summary
You’ll profile ExecuTorch models on Arm with SME2 acceleration using a repeatable workflow. You’ll set up macOS, build SME2-enabled and SME2-disabled runner binaries, and export a model to `.pte`. You’ll run timing-only and trace-enabled passes to capture operator and category breakdowns for convolution, GEMM, and data movement. Then, you’ll compare the profiles to identify SME2 gains and new bottlenecks, and use structured agent skills to automate and validate the workflow.
