Monday July 21, 2003
Noon - 1:30 pm
Intel Seminar (417 S. Craig Street - 3rd Floor)
EVENTS PAGE: http://www.intel-research.net/pittsburgh/events.htm
Dresden University of Technology, Germany
Micro-Kernels - Will they ever deliver?
In the days of the MACH project, many expectations were placed on micro-kernel
technology. Later, many of them were disappointed (such as operating system
architectures based on multiple generalized servers) or delivered by other
technologies(such as multiple os-personalities on single machines). However,
combining legacy OSes with other system software that has radically different
requirements seems the killer application for micro-kernels. In Dresden,
two such areas are investigated: small trusted systems with high assurance
requirements and real-time applications, both running besides and reusing
L4Linux, a user-level variant of Linux as a legacy OS. We present architectures
and some performance results that deny the long-held perception that micro-kernel-based
architectures are too expensive for any useful application.
Hermann Härtig is a professor since 1994 at Dresden University of
Technology, Germany. His research interests include operating system support
for multimedia systems, µ-kernel-based operating systems, real-time
operating systems, and security in operating systems. He graduated from
the University of Karlsruhe (PhD 1984). From 1984 until 1994 he was the
principle developer of the BirliX Operating System at GMD(German National
Research Center for Information Technology). He has had extended visits
at the International Computer Science Institute in Berkeley, UNSW in Sydney,
Hebrew University in Jerusalem, MIT in Boston, and the University of Hildesheim.
Contact Kim Kaan, 412-605-1203,
or visit http://www.intel-research.net.
SDI Home: http://www.pdl.cmu.edu/SDI/