ARM-software/ComputeLibrary

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

3183 stars · 818 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Arm's Compute Library is a C++ collection of over 100 low-level machine learning and computer vision functions optimized for Arm Cortex-A/Neoverse CPUs and Mali GPUs using SIMD technologies like Neon, SVE2, and OpenCL. It provides multiple convolution algorithms, support for FP32/FP16/INT8/BFLOAT16 data types, and micro-architecture-tuned kernels with configurable lightweight builds.

Use cases

• run neural network inference on arm cpus
• optimize convolutions with neon or sve2
• accelerate ml kernels on mali gpus with opencl
• deploy computer vision functions on android
• run inference on raspberry pi or embedded arm boards
• build lightweight ml binaries for bare metal arm

When to choose

• you target arm cortex-a, neoverse, or mali hardware and need maximum performance
• you need immediate support for new arm technologies like sve2
• you want permissive MIT-licensed ml primitives with kernel fusion and tuning options

When to avoid

• you need x86 or nvidia cuda as your primary target
• you want a high-level framework rather than low-level primitives
• you need a license file in-repo before legal review

Facets

library · maturity active

machine-learning computer-vision image-processing llm-inference gpu-computing machine-learning computer-vision deep-learning embedded-systems cpp embedded arm-neon opencl simd sve arm-mali aarch64 kernel-fusion bare-metal linux android macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ARM-software/ComputeLibrary")