Vacancy No. IPE 05-20

IPE 05-20 Internship: Optimizing imaging algorithms for the latest CPU and GPU Architectures

Job description

Parallel programming technologies are extremely important in the domain of scientific computing. Standard servers include CPUs with up to 64 cores. Modern GPUs are able to execute thousands of floating point operations in parallel and have become an invaluable tool in almost any scientific field with high computational throughput. In order to make use of the computational power it becomes more and more important to parallelize existing algorithms and tune the implementations to the recent hardware

architectures. For optimal performance, it is crucial to take the details of hardware architectures into account.

The student will perform optimization of selected image-processing algorithms for recent parallel architectures in one of our currently running projects.

  • advanced image reconstruction and segmentation algorithms in cooperation with the ANKA synchrotron at  KIT,
  • digital image tracking algorithms done in cooperation with the Institute for Thermal Process Engineering,
  • simulation codes for the international KATRIN and Edelweiss collaborations.
Personal qualification

Required Skills

Good knowledge of C programming language, knowledge of

OpenCL or/and CUDA is a plus.

Experience Gained

Image processing in scientific applications, high performance

computing, hardware-aware software development, parallel and GPU programming, benchmarking and profiling.

Organizational unit

Institute for Data Processing and Electronics (IPE)

Starting date

On appointment

Contract Duration

limited, according to the study regulations

Contact person in line-management

Suren Chilingaryan IPE

Phone: +49 721 / 608 26579

Andreas Kopmann IPE


Please apply online using the button below for this vacancy number IPE 05-20.
Personnel support is provided by 

Ms Schaber
phone: +49 721 608-25184,

Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany

If qualified, severely disabled persons will be preferred.