Compute Resources
GPU Hybrid (@Piz Daint)

Computing node-hours on a CPU/GPU hybrid partition (Cray XC50) of the Piz Daint supercomputer. This service includes access to the high-performance Lustre scratch file system.

MultiCore (@Piz Daint)

Computing node-hours on the multicore partition (Cray XC40) of the Piz Daint supercomputer. This service includes access to the high-performance Lustre scratch file system.

Manycore (@Grand Tavé)

Compute node hours on the manycore nodes (Cray XC40 with KNL) of the Grand Tavè supercomputer.

OpenStack (@Pollux)

OpenStack installation at CSCS offering classical Infrastructure-as-a-Service interfaces.

Storage Resources
Home Directory

Every user is assigned their own home directory with sufficient storage space to store codes and documents (/home)

Online Storage

A shared parallel file system to store project data (/store or /project)

Interaction Models / Service Layers
Job Queue

Access to compute nodes is provided with the use of an integrated workload manager (Slurm).  This provides traditional batch processing services through a pre-defined queue structure


The user can “containerize” the Operating System of choice (must be a Linux-based OS) plus all the libraries and applications that are needed on his/her own, and then launch it inside a job. This gives the user the flexibility of “almost” an Infrastructure Service.

Serial Meta-Scheduler

GREASY is a meta scheduler to simplify the execution of embarrassingly parallel simulations in any environment.


This service enables users to define, create and manage their own infrastructure. This mostly consists of raw resources like Compute (e.g. virtual cores), Storage (e.g. block devices) or Network (e.g. routers) – among others – that users can control via a REST-ful API. Users are then enabled to create their own services on top of it like web services or databases, among others.

Data Mover

Bidirectional data transfer services between /scratch and /store and between /store and any external location

Scientific Applications

Amber (Assisted Model Building with Energy Refinement) is a collective name for a suite of programs that allow users to carry out molecular dynamics simulations, particularly on biomolecules


CP2K is a program to perform atomistic and molecular simulations of solid state, liquid, molecular and biological systems


The CPMD code is a plane wave/pseudopotential implementation of Density Functional Theory, particularly designed for ab initio molecular dynamics. Please note that a license has to be acquired from CPMD separately


GROMACS is a versatile package for performing molecular dynamics, i.e. to simulate the Newtonian equations of motion for systems with hundreds to millions of particles


LAMMPS is a classical molecular dynamics code that models an ensemble of particles in a liquid, solid, or gaseous state


NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems


Python is an interpreted high-level programming language for general-purpose programming


Quantum ESPRESSO is an integrated suite of open-source computer codes for nanoscale electronic structure calculations and materials modelling


The Vienna Ab initio Simulation Package (VASP) is a code for atomic scale materials modelling, e.g. electronic structure calculations and quantum-mechanical molecular dynamics, from first principles. Please note that a license has to be acquired from VASP separately

Scientific Libraries

Typical libraries for HPC applications such as HDF5, Trilinos, FFTW, BLAS or NetCDF. These are found in our systems but specific help on how to use them is not provided by CSCS.

Data Science & Machine Learning Applications

Apache Spark is a fast general engine for large-scale data processing


TensorFlow is an open-source software library for numerical computation using data flow


Theano is a Python library that allows efficient definition, optimisation and evaluation of mathematical expressions involving multi-dimensional arrays

Jupyter Notebook

Notebook documents are both human-readable documents containing the analysis description and the results (figures, tables, etc..) as well as executable documents which can be run to perform data analysis.

Cray Graph Engine

CGE is a highly optimized and scalable graph analytics application software, designed for high-speed processing of interconnected data

Anaconda Python and R

Anaconda is a distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing. It aims at simplifying package management and deployment.

Intel BigDL

BigDL is a distributed deep learning library for Spark that can run directly on top of existing Spark or Apache Hadoop clusters. Deep learning applications can be written as Scala or Python programs


Dask is a parallel programming library that combines with the Numeric Python ecosystem to provide parallel arrays, data-frames, machine learning, and custom algorithms


ABCpy is a highly modular, scientific library for Approximate Bayesian Computation (ABC) written in Python.

Programming Environment
Cray Compiler

The Cray Compiling Environment (CCE) is a release of the Cray Fortran and Cray C compilers for use on x86-based Cray systems

Intel Compiler

Intel compilers produce optimised code that can run significantly faster by taking advantage of the ever-increasing core count and vector register width of Intel processors

GNU Compiler

The GNU Compiler Collection (GCC) includes the GNU Fortran compiler (gfortran), C (gcc) and C++ (g++) compilers

PGI Compiler

The PGI compiler suite includes Fortran 77, Fortran 90/95, C and C++ compilers.

CUDA Toolkit

The NVIDIA CUDA Toolkit provides a development environment for creating high performance GPU-accelerated applications

DDT Debugger

DDT provides source-level debugging of Fortran, C and C++ codes

CrayPat Performance Tool

CrayPat is a performance analysis tool developed by Cray for CSCS production systems

VI-HPS Performance Tool

The mission of the Virtual Institute - High Productivity Supercomputing (VI-HPS) is to improve the quality and accelerate the development process of complex simulation codes in science and engineering that are being designed to run on highly-parallel computer systems

NVIDIA SDK Performance Tool

NVIDIA profiling tools and APIs for understanding and optimising the performance of CUDA and OpenACC applications

Easy Build Framework

EasyBuild is a software installation framework in Python that allows you to install software in a structured and robust way

Visualisation Applications

ParaView is an open-source, multi-platform data analysis and visualisation application


VisIt is an open-source, interactive, scalable, visualisation, animation and analysis tool


VMD is a molecular visualisation program for displaying, animating, and analysing large biomolecular systems using 3-D graphics and built-in scripting

Customer / Support Services
Help Desk

All questions and service requests should be addressed by email to An FAQ section is also available.


Every year there are several tutorials and courses for CSCS users