HPC software

This section gives a summary of the applications installed on the HPC cluster, which is available to all users of the cluster (to become one fill in the form) connected to the cluster interface (the instruction is available here). If you cannot find the necessary application in the catalogue, contact us and we will consider the technical possibilities of installing it. Users can also install (compile) applications in their user area themselves.

Catalogue

Open source software

bcl2fastq (ver. 1.8.4)

Blender (ver. 2.7)

GROMACS (ver.2016-1)

OpenFoam (ver. 2.4, 5)

Peridigm (ver. 1.5)

R (ver. 3.4.0)

SalomeMeca (ver. 2015)

Scilab  (ver. 5.4)

Commercial vendors software 

COMSOL Multiphysics (ver. 5.3a)

Matlab (ver. 2017b)

Development tools 

Conda/Anaconda (ver. 4.4)

CUDA Toolkit (ver. 8.0)

GCC (ver. 4.8.5)

Intel MPI (ver. 4.0.3)

OpenMPI (ver. 1.10.5a)

Perl (ver. 5)

Python (ver. 2.7, 3.6)

R (ver. 3.4.0)

The cluster uses Environment Modules. To prepare user’s working environment for using a particular application, follow this procedure.

module load module_name

To obtain the full list of available modules:

module avail

Boot script examples for the cluster are available in the directory:

/opt/exp_soft/user_info

To receive individual assistance in creating a script, email the HPC Centre at hpc@rtu.lv.

MATLAB Distributed Computing Server

MATLAB Distributed Computing Server (MDCS) virtually expands the computing resources (number of CPU, storage capacity, disc space) available to MATLAB by providing access to workers (MATLAB computational engines) that run on the computer cluster.

Intel Parallel Studio

Intel Parallel Studio is mainly used for the development of parallel programs for high-performance computing (HPC) systems. The tools can be used for developing not only HPC programs but also high-speed programs for personal computers. For example, Intel C++, Fortran compilers and Intel MKL math libraries are widely used for developing not only parallel but also serial programs and are all tuned for Intel processors.

CUDA

CUDA is a programming model for Nvidia graphical processing units (GPU). HPC cluster has six Tesla M2070 and eight Tesla K40 GPU. CUDA C++/Fortran programming libraries are available upon logging into the RTU HPC cluster server (instruction is available here).