Build and test KleidiCV on macOS
Introduction
Download and build KleidiCV software
Test KleidiCV and verify SME backend support
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Introductory
Reading time:  30 min
Last updated:  28 Jul 2026
Skill level:
  Introductory
Reading time:
  30 min
Last updated:
  28 Jul 2026
Author:Jett Zhou
Arm IP:Cortex-A
Tags: Performance and Architecture macOS KleidiCV C
Author:
  • Jett Zhou
Arm IP:
Cortex-A
Tags:
Performance and Architecture macOS KleidiCV C

Who is this for?

This is an introductory topic for software developers who want to build and test KleidiCV on macOS.

What will you learn?

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

  • Install and compile KleidiCV on macOS
  • Run KleidiCV example tests
  • Enable Scalable Matrix Extensions (SME) and verify increased SME performance

Prerequisites

Before starting, you will need the following:

  • A Mac with Apple Silicon (M4 generation or newer)
  • Xcode command line tools installed
  • Basic familiarity with using the Terminal and command-line tools

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 build Arm KleidiCV from source on macOS and run its bundled tests. You’ll compile the library, execute the API test, and inspect vector-length and test-count output. KleidiCV selects Neon, SVE2, or SME2 implementations based on Apple silicon, so you can validate hardware-specific backends without changing application code.

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
?
Where do I find and run the KleidiCV API test after the build?
Run the test binary at ./build-kleidicv-benchmark-SME/test/api/kleidicv-api-test. It prints the number of tests executed and their results to confirm the build works.
What result should I expect from the API test to confirm success?
Expect output similar to a vector length report and a summary of tests run and passed. A clean pass indicates the build and public API are functioning.
How do I verify that the SME backend is being used?
KleidiCV auto-detects your CPU and selects the fastest path: Neon, SVE2, or SME2. Review the test output in the SME verification step. On supported Apple silicon, SME support is exercised during the tests.
Do I need to change my application code to target Neon, SVE2, or SME2?
No. KleidiCV automatically detects the hardware and chooses the optimal implementation, so your code doesn’t need to change.
What should I check if the tests fail to run or report errors?
Confirm the build finished without errors and run the binary from the path shown. If issues persist, confirm that you installed the required tools, then rebuild and rerun the tests.
Next