Compiler und Bibliotheken

Compilers and Libraries

The following list is regularly updated and enhanced. Current available versions become visible with the command “module avail”. Currently (May 22, 2019) installed:

Compilers and programming environments

GNU Compiler Collection (GCC)

Intel Parallel Studio XE Cluster Edition (incl. Intel MKL, Intel MPI, etc.)

LLVM (clang)

CUDA

GlobalAarrays (GA) http://hpc.pnl.gov/globalarrays/

IntelMPI Part of Intel Parallel Studio

Java: Open JDK

NAG Fortran Compiler

OpenMPI Several versions for GCC and Intel Compiler https://www.open-mpi.org/

Python (incl. numpy scipy matplotlib ipython jupyter pandas h5py keras tensorflow torch)

QT

Compiler options

There are various options to achieve the best performance with a given compiler.
We recommend to set the following parameters:

Intel Compiler: '-O2 -march=sandybridge -mtune=haswell'

GNU Compiler: '-O2 -march=sandybridge -mtune=haswell'
The options '-Ofast' or '-O3' are possible, too. However, they are not suitable to all codes, and can lead to problems with some programs.

Few older compiler versions mit require the options -march=corei7-avx -mtune=core-avx2 instead.

Numerical and other libraries

Blis

Boost https://www.boost.org/

Eigen

FFTW http://fftw.org/

GNU Scientific Library (GSL) https://www.gnu.org/software/gsl/

HDF5 https://portal.hdfgroup.org/display/support

Hypre

Intel Math Kernel Library (MKL) (Part of Intel Parallel Studio)

Lapack http://performance.netlib.org/lapack/

LibFlame

LibM

NAG Libraries

Netcdfhttps://www.unidata.ucar.edu/software/netcdf/

OpenBLAS http://www.openblas.net/

PETSc with modules https://www.mcs.anl.gov/petsc/