#120 · Primary category: Computer Vision

Simd

amx arm avx avx512 c-plus-plus haar-cascade hexagon hvx image-processing lbp machine-learning neon neural-network simd simd-library sse sve

C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON, SVE for ARM, HVX for Hexagon

Project last updated:08/27/26

GitHub Stars

2.3K

Forks

453

Contributors

54

License

MIT

Why we included this project

Simd is a C++ library for image processing and machine learning that earns its keep through SIMD tuning: it ships optimized paths for SSE through AVX-512 and AMX on x86, NEON and SVE on ARM, and HVX on Qualcomm Hexagon DSPs. Beyond the everyday operations, pixel format conversion, scaling, filtering, and statistics extraction, it also handles motion detection, object detection and classification, and neural network inference. The C API comes with C++ wrappers and a Python binding, so teams working in different languages can call the same tuned kernels. For embedded vision systems, video pipelines, and desktop apps where a heavier framework is too much overhead, this is a practical, low-dependency option.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category