Benchmark a KleidiAI micro-kernel in ExecuTorch
Introduction
Set up your environment
Cross-Compile ExecuTorch for the AArch64 platform
Accelerate ExecuTorch operators with KleidiAI micro-kernels
Create and quantize linear layer benchmark model
Create and quantize convolution layer benchmark model
Create matrix multiply layer benchmark model
Run model and generate the ETDump
Analyze ETRecord and ETDump
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Advanced
Reading time:  30 min
Last updated:  25 Nov 2025
Skill level:
  Advanced
Reading time:
  30 min
Last updated:
  25 Nov 2025
Author:Qixiang Xu, Arm
Arm IP:Cortex-A
Tags: ML Linux Python ExecuTorch XNNPACK KleidiAI
Author:
  • Qixiang Xu, Arm
Arm IP:
Cortex-A
Tags:
ML Linux Python ExecuTorch XNNPACK KleidiAI

Who is this for?

This is an advanced topic for developers, performance engineers, and ML framework contributors who want to benchmark and optimize KleidiAI micro-kernels within ExecuTorch to accelerate model inference on Arm64 platforms supporting SME/SME2 instructions.

What will you learn?

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

  • Cross-compile ExecuTorch for Arm64 with XNNPACK and KleidiAI enabled, including SME/SME2 instructions
  • Build and export ExecuTorch models that can be accelerated by KleidiAI using SME/SME2 instructions
  • Use the executor_runner tool to run kernel workloads and collect ETDump profiling data.
  • Inspect and analyze ETRecord and ETDump files using the ExecuTorch Inspector API to understand kernel-level performance behavior.

Prerequisites

Before starting, you will need the following:

  • An x86_64 Linux host machine running Ubuntu, with at least 15 GB of free disk space
  • An Arm64 target system with support for SME or SME2 - see the Learning Path Devices with native SME2 support
Next