• Zielgruppen
  • Suche


Most of our ongoing work can be found on our Projects page. The current research topics include:

Energy Efficiency in HPC

The operating costs of High Performance Computing systems are considerable. The energy costs take up a notable proportion. There are different approaches to improve energy efficiency in HPC. The main focus of our research is in the area of ​​system software and applications. With the help of the development system of the HLRN III (Cray XC40), we are able to compare and to optimize the energy efficiency of different algorithms. In addition, we use a lab of ODROID-XU3 single chip computers. These small systems have next to 8 cores and a GPU in particular sensors for measuring the power consumption in real time. With respect to these systems, we have direct knowledge sharing with the Barcelona Supercomputing Center (BSC). The BSC is currently the world leader in the construction of HPC prototypes that allow to go new ways in the field of energy efficiency.


Performance Engineering

Management of Complex IT Infrastructures

We are working in the e-Infrastructure Reflection Group (e-IRG). At the EU e-IRGSP3 project we have worked as a participant and for the EU project e-IRGSP4 we took over the role of the coordinator.

Homomorphic Cryptography (hcrypt.com)

The main aspect of our HCRYPT project for homomorphic encryption is to research practical technologies and architectures for operating on privacy related data. This means, that confidential data can remain in an encrypted state while being processed. One research branch is the development of homomorphically encrypted circuitry like memory and CPUs, where working software prototypes are currently translated into hardware designs. This helps to secure cloud services or electronic devices in industry and consumer market. In parallel we research hybrid systems in which most parts of the computation is carried out unencrypted and only privacy-related portions are actually enciphered. An interesting prototype in this field is the privacy-preserving search of encrypted sequences in a genome database with secret search terms.