Andreas Nowatzyk
| Contact Information | |
|---|---|
| Office | 4117 Newell-Simon Hall |
| Telephone | (412)-268-4846 |
| agn@acm.org | |
| Website | http://www.cs.cmu.edu/~agn/ |
Research Interests
My primary area of research is computer architecture, in particular scalable systems and their interconnect structures (switching fabrics, system area networks, network interfaces and protocol engines). Advancing technology and changing requirements continue to pose new problems for multiprocessor systems, particularly concerning reliability, availability and serviceability (RAS).
I like to work at boundaries between computing systems and their implementation technologies, drawing on my background in physics, electronics and optics. In the past, this included projects ranging from high speed interconnect links (optical and electronic), over computer chess machines (Deep Thought) to chasing RF interference problems in avionics packages for computer controlled, small scale airplanes. Currently, I'm focussed on developing a special purpose microscope to trace the neuronal structures of small biological specimens. The long term goal of this research is to "reverse engineer" these biological computing structures.
I believe that research in computer architecture is best driven by concrete, real applications. In this context, the microscope mentioned above poses a tough challenge in the areas of image processing and scientific signal processing. To be able to scan an object as large as a laboratory mouse, nearly 20 Peta-Byte of raw data must be processed in real time. This is a very interdisciplinary research projects that includes VLSI circuit design, fiber optics, sensor development, holography, lasers, RF electronics, micro-robotics, and applied computer science. The beauty (to me) of this project is that number of very different technologies have to come together to sole one concrete, easy to fathom purpose.
As a "hardware" person, I like to think about future technologies and their implications for computing architectures. For example, it is clear that the current paradigm of {super-scalar, out-of-order, VLIW, SMT, etc.} processors is increasingly running into a complexity and verification wall. While the technology is steadily advancing to integrate 10^8, 10^9, ... transistors onto one chip, it is becoming exceedingly difficult to effectively use these transistors with traditional designs. I'm interested in the new computing structures that will overcome these problems. I think that in the long term, the challenge to computer science at large is to find a more physical paradigm than von Neumann's architecture with separate processors and memory. In my opinion, such system's may very well be based on von Neumann's other great idea, the cellular arrays.
In the News
Keywords
High performance computer architecture and parallel processing
Education
PhD, 1989
Computer Science
CMU
Diplom, 1982
Computer Science
University of Hamburg
Diplom, 1982
Physics
University of Hamburg
Vordiplom, 1978
Computer Science
University of Hamburg
Vordiplom, 1976
Physics
JLU