A26 - Dataflow Analysis for Real-Time Multiprocessor Systems

From: November 23 to 26, 2017 Postponed to February 2018

Dataflow Analysis for Real-Time Multiprocessor Systems (4 days)
An introduction to real-time analysis techniques for multiprocessor systems

A PhD course given off-site, at the conference center Kontakt der Kontinenten which is located in Soesterberg.

Prof. Marco Bekooij, University of Twente/NXP Semiconductors Marc Geilen, Eindhoven University of Technology Joost Hausmans, University of Twente
ir. Robert de Groote, University of Twente

Duration: 4 full days

Lectures (half of each day)

Computer laboratories (other half of the day) using dataflow analysis tools and real-time multiprocessor systems to exercise the course material and tasks.

Registration & Costs:

Register through the ASCI website.

PhD students of research schools ASCI, DISC, ImagO, IPA, OzsL and SIKS can take part of the regular ASCI courses free of charge. The course fee for other PhD students amounts to €500. The course fee for non-PhD students amounts to €1200.



In this course we present dataflow analysis methods that have shown to be useful for the analysis and optimization of real-time stream processing applications. We explain the basics of the dataflow analysis theory as well as state-of-the-art analysis techniques will be explained.

We furthermore present software and hardware techniques that improve the system's analysability and the accuracy of the analysis results. Practical examples will be used to demonstrate the effectiveness of the presented theory. Small exercises and hands-on sessions with tools and practical multiprocessor systems after each lecture help the participant to evaluate and master the presented methods. Examples of safety-critical real-time stream-processing applications are software-defined radios for car-to-car communication, and car-radars for automatic emergency breaking. These applications are executed on embedded multiprocessor systems. Programming of these systems is challenging because despite that these applications are concurrent, dynamic and share the system's resources, they must deliver the correct information at predefined points in time. Dataflow models and tools simplify the design, analysis, and optimization of these applications.

The course is intended for computer scientists, electrical engineers and PhD students or researchers in the related disciplines, that are interested in the design and programming of real-time multiprocessor systems.

After successful completion of the course, participants are able to apply the presented dataflow analysis methods. They are also aware of ongoing research on dataflow analysis and have a good starting point for making their own scientific contributions to this research field. To allow for sufficient interaction of the teachers with the participants, at most 20 students will be allowed to participate in this course.



 ASCI Tweets