The BLAS library

⚠ INFORMATION
This page was translated by an AI (LLM) with a cursory human check and is awaiting full review.

---

Description

BLAS (Basic Linear Algebra Subprograms) is a set of functions performing basic linear algebra operations such as vector additions, scalar products or matrix multiplications.

BLAS is available in free versions (Netlib and OpenBLAS) or via the Intel MKL (Math Kernel Libraries) that we recommend because they offer better performance.

Installed Versions

The versions installed on Jean Zay can be found using the following commands:

• Intel MKL versions (recommended versions)

  module avail intel-mkl

• Netlib-Lapack versions

  module avail netlib-lapack

• OpenBLAS versions

  module avail openblas

Environment

The BLAS versions are available in different environments.

• Intel Environments

For Intel environments, please refer to our documentation on the Intel MKL library.

• Free Versions

For free versions, this information can be found using the module show command. For example:

module show netlib-lapack
module-whatis    {LAPACK version 3.X is a comprehensive FORTRAN library that does linear algebra operations including matrix inversions, least squared solutions to linear sets of equations, eigenvector analysis, singular value decomposition, etc. It is a very comprehensive and reputable package that has found extensive use in the scientific community.}prereq            gcc/11.4.1 gcc/10.1.0conflict          netlib-lapack
Available software environment(s):- gcc/11.4.1- gcc/10.1.0

module show openblas

To use this library in other environments, please contact the User Support team.

Remarks

• To obtain information on the library access paths for the free version, it will be necessary to first load the chosen environment (gcc in this example):

module load gcc/11.4.1module show netlib-lapack

• With the module show command, you can also obtain information on the library access paths for OpenBLAS:

module show openblas

Usage

The library is accessible via the module command.

Using BLAS via MKL

For the use of MKL, please refer to the page concerning the Intel MKL library.

Using BLAS via LAPACK

For the use of the LAPACK library, please refer to our documentation concerning the LAPACK libraries.

Using BLAS via OpenBLAS

To load the default version in the current environment (or in the default environment if no environment is previously loaded):

module load openblas

or to load a specific version in a specific environment (gcc in this example):

module load gcc/8.2.0module load openblas/0.3.6

Link Editing

Link Editing with MKL

Please refer to the page concerning the Intel MKL library.

Link editing for the use of MKL can vary depending on several parameters such as the operating system, the type of compiler and the architecture. It is recommended to use the Intel® MKL Link Line Advisor to find the appropriate options.

Here is an example for the BLAS library:

module load intel-mklifort appel_blas.f90 -L${MKLROOT}/lib/intel64 -lmkl_intel_lp64 \ 
 -lmkl_sequential -lmkl_core -lpthread -lm -ldl

Link Editing with Free LAPACK Version

For link editing with the free LAPACK library, please refer to our documentation concerning the LAPACK libraries.

When link editing, it is necessary to add the -lblas options:

module load gcc/11.4.1module load netlib-lapackgfortran appel_blas.f90 -lblas

Link Editing with Free BLAS Version

When link editing, it is necessary to add the -lopenblas option:

module load gcc/9.1.0module load openblasgfortran appel_blas.f90 -lopenblas

Documentation

📝 Reference Site (Netlib)
📝 Reference Site (OpenBLAS)
📝 Intel MKL documentation
📝 Intel MKL Link Line Advisor