Skip to content

LIBXSMM: library for specialized dense and sparse matrix operations

Overview of package

Package: LIBXSMM
Description: library for specialized dense and sparse matrix operations
For more information: https://github.com/hfp/libxsmm
Categories: SoftwareDevelopment
MachineLearning
License: OpenSource (BSD-3clause)

General Usage

LIBXSMM is a library for specialized dense and sparse matrix operations as well as for deep learning primitives such as small convolutions.

This module will add the libxsmm_gemm_generator code to your PATH.

The following environmental variables have been defined:

  • $LIBXSMM_ROOT has been set to the root of the libxsmm installation
  • $LIBXSMM_LIBDIR points to the directory containing the libraries
  • $LIBXSMM_INCDIR points to the directory containing the header files

You will probably wish to use these by adding the following flags to your compilation command (e.g. to CFLAGS in your Makefile):

  • -I$LIBXSMM_INCDIR

and the following flags to your link command (e.g. LDFLAGS in your Makefile):

  • -L$LIBXSMM_LIBDIR -Wl,-rpath,$LIBXSMM_LIBDIR

Available versions by cluster

This section lists the available versions of the package LIBXSMMon the UMD HPC clusters.

Versions available on the Zaratan cluster

Version Module tags CPU(s) optimized for GPU ready?
1.16.3 1.16.3 zen2 Yes
1.15 1.15 zen Yes
1.17 1.17 icelake, x86_64, zen2 Yes