Prof. Michael Goesele

Modern single processors are becoming only marginally faster over time due to various, hard to overcome bottlenecks. They do, however, become steadily "more parallel" due to the multi-core and many-core (r)evolution that we have seen in the last years and that is still in progress. Any research project that depends on significant amounts of computation must not only be aware of those developments but needs to actively use the inherent parallelism of modern processors.

The main research focus of the group related to the graduate school of computational engineering is massively parallel computation. We develop new methods and algorithms for high performance computing and visualization using graphics processing units (GPUs) or other accelerator cards as main platform. In addition, we work with clusters of GPU enabled nodes, yielding one to two orders of magnitude more computational power but also adding layers of complexity. Besides further development of these foundations, we are actively interested in application-oriented projects that build on the technology developed in our group.

The research group's second focus - the intersection of computer graphics and computer vision - is also partially related to the graduate school and can be explored for specific projects. More information can be found at Michael Goesele's web page.

Prof. Dr. M. Goesele


Technische Universität Darmstadt

Graduate School CE
Dolivostraße 15
D-64293 Darmstadt

Phone+49 6151/16-24401    or
Fax+49 6151/16-24404

to assistants' office

Open BSc/MSc Theses

Show a list of open BSc/MSc topics at GSC CE.

 Print |  Impressum |  Sitemap |  Search |  Contact |  Privacy Policy
zum Seitenanfangzum Seitenanfang