+++ At DLR, we are always looking for bright minds – even during the current exceptional circumstances. Our current vacancies can be found here. +++

My knowledge is shaping the future.

Bookmark
Course paper / final thesis

Parallel and Distributed Generation of Streamlines on a Cluster

Starting date

immediately

Duration of contract

up to 6 months

Type of employment

Full-time

Goal of this thesis is to develop an algorithm to generate streamlines from a given dataset on a high-performance computation cluster.

In DLR’s Institute for Software Technology, an application stack is being developed to visualize scientific data from nearly any domain. Most domains are confronted with extremely large data sets. These sets can range from a few gigabytes to terabytes of data. Visualizing these data sets is not trivial and requires a distributed and parallel approach. The data is processed on a cluster, where each node works only on a subset of data. The results from the cluster nodes are merged and send to the client for visualization.

In the scope of this thesis a streamline algorithm needs to be developed, that can run in parallel on a cluster. Streamlines come with the unfortunate property, that they can move through the whole data set and are not locally contained. This requires some complex communication between nodes that work on different parts of the data set. When a streamline switches from the boundary of one nodes work package to the boundary of another nodes work package, data has to be exchanged. With a lot of streamlines this may lead to a large overhead in communication. The thesis should develop an algorithm that minimizes network communication and file access to achieve maximum performance. It requires analyzing existing approaches and adapting them to DLRs software system, as well as coming up with new ideas. The results should be evaluated and compared to other implementations.

Your qualifications:

  • Computer Science student or similar
  • good programming skills with C++
  • preferably experience with MPI, OpenMP or parallel/distributed computing
  • preferably experience with VTK and ParaView

Your benefits:

Look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development. Our unique infrastructure offers you a working environment in which you have unparalleled scope to develop your creative ideas and accomplish your professional objectives. Our human resources policy places great value on a healthy family and work-life-balance as well as equal opportunities for persons of all genders (f/m/x). Individuals with disabilities will be given preferential consideration in the event their qualifications are equivalent to those of other candidates.

  • Apply online now
  • You can send this job advertisement via e-mail and complete your application on a personal computer or laptop.

    We need your digital application documents (PDF). The document upload function is not supported by all mobile devices. Please complete your application on a PC/laptop.

    Complete application on PC

Technical contact

Jonas Gilg
Institute for Software Technology

Phone: +49 531 295-2221

Send message

Vacancy 56123

HR department Braunschweig

Send message

DLR site Braunschweig

To location

DLR Institute for Software Technology

To institute