Docs Backend Snapdragon Readme

Unlock the Power of Snapdragon for Your European SME

Are you an innovative European small-to-medium-sized enterprise (SME) looking to harness the power of Snapdragon processors? Look no further! In this article, we’ll guide you through the process of building and deploying your application on these high-performance devices.

Getting Started with Android

The easiest way to get started is by using the toolchain Docker image from the Snapdragon Toolchain GitHub repository. This image includes all the necessary tools for building llama.cpp on a Snapdragon-based Android device, including Android NDK, OpenCL SDK, Hexagon SDK, and CMake.

Let’s dive into an example of how to set up your environment:

~/src/llama.cpp$ docker run -it -u $(id -u):$(id -g) --volume $(pwd):/workspace --platform linux/amd64 ghcr.io/snapdragon-toolchain/arm64-android:v0.3
[d]/> cd /workspace

Building for Windows On Snapdragon

For native Windows 11 arm64 builds, you’ll need to have the following tools installed:

• MS Visual Studio 2026 (Community Edition or Pro)
  • MSVC arm64 standard and runtime libraries
  • UCRT and Driver Kit
• LLVM core libraries and Clang compiler (winget)
• CMake, Git, Python (winget)
• Hexagon SDK Community Edition 6.4 or later (see windows.md)
• OpenCL SDK 2.3 or later (see windows.md)

Here’s an example of how to build llama.cpp with CPU, OpenCL, and Hexagon backends:

[d]/workspace> cp docs/backend/snapdragon/CMakeUserPresets.json .

[d]/workspace> cmake --preset arm64-android-snapdragon-release -B build-snapdragon
...
-- Including OpenCL backend
-- Including Hexagon backend
...

[d]/workspace> cmake --build build-snapdragon
...
[144/356] Performing build step for 'htp-v73'
...

Key Takeaways

• Use the toolchain Docker image to simplify the building process on Android devices.
• Ensure you have the necessary tools installed for native Windows 11 arm64 builds.
• Use CMake presets to easily switch between different backends, such as CPU, OpenCL, and Hexagon.

By following these steps and leveraging the power of Snapdragon processors, your European SME can unlock new levels of performance and efficiency in your applications. Don’t wait – start building today!

Get Ahead with VORLUX AI

Ready to take your application development to the next level? Our team at VORLUX AI is here to help you optimize your code for maximum performance on Snapdragon devices. Contact us today to learn more about our expert services and how we can support your European SME’s success.

Happy building!