Introduction

The Compute Library is a collection of low-level machine learning functions optimized for both Arm CPUs and GPUs using SIMD technologies.

Several builds of the library are available using various configurations:

• OS: Linux®, Android™, macOS or bare metal.
• Architecture: armv7a (32bit) or armv8a (64bit).
• Technology: Arm® Neon™ / OpenCL / Arm® Neon™ and OpenCL.
• Debug / Asserts / Release: Use a build with asserts enabled to debug your application and enable extra validation. Once you are sure your application works as expected you can switch to a release build of the library for maximum performance.

Warning

Depecation Notice from 24.01: NCHW data format specific optimizations will gradually be removed from the code base in future releases. The implication of this is that the user is expected to translate NCHW models into NHWC in order to benefit from the optimizations.

Minimum toolchains requirements are shown below:

Operating System	Architecture	Minimum Toolchain
Linux®	armv7a	gcc-linaro-6.3.1-2017.05-x86_64_arm-linux-gnueabihf
	armv8a	gcc-linaro-6.3.1-2017.05-x86_64_aarch64-linux-gnu
	armv8.2-a
	armv8.2-a-sve	gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu
Android™	armv8a	NDK r20b
	armv8.2-a
	armv8.2-a-sve	NDK r23b
macOS	armv8.2-a	Monterey (OS version): clang 13 (native)

Contact / Support

Please create an issue on Github.

In order to facilitate the work of the support team please provide the build information of the library you are using. To get the version of the library you are using simply run:

$ strings android-armv8a-cl-asserts/libarm_compute.so | grep arm_compute_version
arm_compute_version=v16.12 Build options: {'embed_kernels': '1', 'opencl': '1', 'arch': 'armv8a', 'neon': '0', 'asserts': '1', 'debug': '0', 'os': 'android', 'Werror': '1'} Git hash=f51a545d4ea12a9059fe4e598a092f1fd06dc858

Pre-built binaries

For each release we provide some pre-built binaries of the library here.

These binaries have been built using the following toolchains:

• Linux® armv7a: gcc-linaro-7.2.1-2017.11-x86_64_arm-linux-gnueabihf
• Linux® armv8a: gcc-linaro-7.2.1-2017.11-x86_64_aarch64-linux-gnu
• Linux® armv8.2-a: gcc-linaro-7.2.1-2017.11-x86_64_aarch64-linux-gnu
• Linux® armv8.2-a (multi-ISA binary): gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu
• Linux® armv8.2-a-sve: gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu
• Android™ armv8a: clang++ / libc++ NDK r20b
• Android™ armv8.2-a: clang++ / libc++ NDK r20b
• Android™ armv8.2-a-sve: clang++ / libc++ NDK r23b

Warning

Make sure to use a compatible toolchain to build your application or you will get some std::bad_alloc errors at runtime.

File organisation

This archive contains:

• The arm_compute header and source files
• The latest Khronos OpenCL 1.2 C headers from the Khronos OpenCL registry
• The latest Khronos cl2.hpp from the Khronos OpenCL registry (API version 2.1 when this document was written)
• The latest Khronos EGL 1.5 C headers from the Khronos EGL registry
• The sources for a stub version of libOpenCL.so, libGLESv1_CM.so, libGLESv2.so and libEGL.so to help you build your application.
• An examples folder containing a few examples to compile and link against the library.
• A utils folder containing headers with some boiler plate code used by the examples.
• This documentation.

For detailed information about file organization, please refer to Files -> File List section of this documentation.