Small dense or sparse matrix multiplications and convolutions for x86_64
LIBXSMM is a library for small dense and small sparse matrix-matrix multiplications, as well as for deep learning primitives such as small convolutions targeting Intel Architecture (x86). The library generates code for the following instruction set extensions: Intel SSE, Intel AVX, Intel AVX2, IMCI (KNCni) for Intel Xeon Phi coprocessors ("KNC"), and Intel AVX‑512 as found in the Intel Xeon Phi processor family ("KNL") and future Intel Xeon processors. Small convolutions are currently only optimized for Intel AVX‑512. Historically the library was solely targeting the Intel Many Integrated Core Architecture "MIC") using intrinsic functions. Currently, optimized assembly code targets all aforementioned instruction set extensions (static code generation), and Just‑In‑Time (JIT) code generation targets Intel AVX and beyond.
Release | Stable | Testing |
---|---|---|
Fedora Rawhide | 1.17-4.fc41 | - |
Fedora 41 | 1.17-4.fc41 | - |
Fedora 40 | 1.17-3.fc40 | - |
Fedora EPEL 9 | 1.17-1.el9 | - |
Fedora EPEL 8 | 1.17-1.el8 | - |
You can contact the maintainers of this package via email at
libxsmm dash maintainers at fedoraproject dot org
.