Shypd.aiThe largest open index of AI toolslibxsmm is an open-source library for specialized dense and sparse matrix operations, and deep learning primitives. It targets Intel Architecture for optimized performance through Just-In-Time (JIT) code specialization.
Trending
About
LIBXSMM is an open-source library designed to accelerate specialized dense and sparse matrix operations, as well as deep learning primitives like small convolutions. It specifically targets Intel Architecture, including Intel SSE, AVX, AVX2, AVX-512 (with VNNI and Bfloat16), and Intel AMX. The library achieves high performance through Just-In-Time (JIT) code specialization, making it compiler-independent and suitable for a "build once and deploy everywhere" approach. It supports various GEMM datatypes including FP64, FP32, bfloat16, int16, and int8. LIBXSMM provides interfaces for Matrix Multiplication (MM), Tensor Processing Primitives (TPP), Deep Neural Networks (DNN), and auxiliary service functions, offering both C/C++ and Fortran interfaces for integration into diverse projects.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
