Andrew Bernat

Learn More
Dynamic binary instrumentation for performance analysis on new, large scale architectures such as the IBM Blue Gene/L system (BG/L) poses new challenges. Their scale---with potentially hundreds of thousands of compute nodes---requires new, more scalable mechanisms to deploy and to organize binary instrumentation and to collect the resulting data gathered by(More)
The benefits of working in a research group are clear: students develop domain expertise, gain an understanding and appreciation of the research process and its practice, and acquire team, communication , problem-solving, and higher-level thinking skills. Students with this experience are better equipped to make informed judgements about technical matters(More)
We describe simulation-type methods that solve (in reasonable time) the following problems of intelligent information processing: estimate the result's precision; estimate the result's reliability; and, decision-making in case of a conflict. We also propose a special architecture that enables to parallelize these algorithms efficiently (without wasting time(More)
The affiniy research group model provides strategies that will make them effective leaders. As a result, students with opportunities to learn, use, and integrate the students grow personally and academically. Figure 1 depicts knowledge and skills that are required for research with the the major goals of the non-hierarchical, scaleable affinity knowledge(More)
This paper describes the afinity group concept and model as an alternative to traditional research groups in university computer science programs. The afinity research groups provide a physical setting an a cooperative environment in which undergraduate and graduate college students engage in research. Afinity groups involve students with a wade range of(More)
This panel focuses on computer science research and educational activities involving minorities. In addition to highlighting various research in progress, this panel will emphasize how research at a given institution has impacted the corresponding computer curriculum. Specific information to be discussed by the panel will include: 1) a brief overview of(More)
An important area of application of computer vision is the detection of object motion. We are currently developing a computer vision system to automatically detect and track human motion across the international border between the United States and Mexico. Because of the wide range of environmental conditions, this application represents a stringent test of(More)
  • 1