Homepage of Technische Universität Dresden
Personal tools
|
|
Systems Engineering GroupWelcome to the Systems Engineering Group The Systems Engineering Group's main research focus is on dependable systems. We follow a divide and conquer approach to address various kinds of faults and failures that can occur in computers and in distributed systems. We are designing and evaluating mechanisms to deal with individual fault types to facilitate developers to choose and match mechanisms depending on a system's dependability requirements. For example, we have developed an encoding tool (SIListra) to detect execution failures of programs: it not only detects wrong executions caused by the CPU failures but also those caused by compiler failures. We also investigate dependability issues in the context of cloud computing (SRT-15), stream processing (STREAM) and transactional memory (VELOX). Our focus in transactional memory is not only on concurrency control but in particular, its use for failure isolation.
SRT-15 The goal of the SRT-15 research project is to build a
scalable platform for connecting business applications and
services. SRT-15 relies on technologies that support rapid
change: cloud computing, content-based routing, and complex
event processing. Software Transactional Memory Transactional Memory (TM) provides transactions for main
memory. TM is supposed to make parallel/concurrent programming
a lot easier for developers. With Software Transactional
Memory (STM), transactions are entirely implemented in
software. We maintain open-source tools (STM runtime, static
and dynamic STM compilers) for research and experimental
development. SIListra The SIListra technology developed in the Systems
Engineering research group uses arithmetic codes to recognize
erroneous program executions. For detecting errors, processed
data is encoded using an arithmetic code. These codes
facilitate detection of errors during data storage, transport,
and processing. 
The goal of the StreamMine project is to investigate the
challenges involved in building scalable event stream
processing. Further, an implementation of a such a system is
also being carried out in the context of the Framework
Programmes for Research and Technological Development
(FP7).
The courses offered by the Systems Engineering group include lectures (with exercises), seminars and computer labs in the field of distributed and parallel computing, software-fault tolerance and dependability.
 
|
Contact
Consultation:
|
