Slot 4

Reconfigurable Multiprocessor Systems-on-Chip: Hardware Architectures, Design Tools and Runtime Support
Diana Göhringer, TU Dresden

Abstract

The increasing complexity and adaptive dynamic behaviour of cyber-physical systems, such as advanced driver assistance systems (ADAS) or service robotics, require novel embedded hardware/software solutions. In particular, the dynamic behaviour at runtime needs an approach providing adaptation to changing demands in terms of real-time requirements, data throughput, safety and security. One representative example can be found in robotic systems, where changing situations are handled with image processing algorithms for object detection and tracking. Here, besides the change of algorithm, it would also be recommended to change the hardware architecture, e.g. the reconfiguration of accelerators for specific algorithms, in response to changing situations. This feature can be provided by reconfigurable multiprocessor systems-on-chip (MPSoCs), which can adapt the hardware as well as the software to the application requirements and therefore achieve high computational efficiency as well as high flexibility. However, the development, the programming and the operation of such flexible and heterogeneous systems is very complex as the many criteria (performance, power consumption, costs, development time, runtime adaptations, etc.) open a huge design space.

This course is split in three parts. First, basic principles of Multiprocessor Systems-on-Chip including processing elements, communication infrastructure and memory systems are introduced. The second part covers Field Programmable Gate Arrays (FPGAs) and dynamic partial reconfiguration as the basis for reconfigurable computing systems. The third part gives an overview of existing methods and tools for designing and programming such reconfigurable systems and operating system support for managing the runtime adaptations. Throughout the course, several examples of modern reconfigurable systems are presented.

Bio

Since April 2017, Diana Göhringer has been professor for adaptive dynamic systems at TU Dresden, Germany. From 2013 to 2017 she was an assistant professor and head of the MCA (application-specific Multi-Core Architectures) research group at the Ruhr-University Bochum (RUB), Germany. She received her PhD and her master degree in Electrical Engineering and Information Technology from the Karlsruhe Institute of Technology (KIT), Germany in 2011 and 2006, respectively. She is author and co-author of over 100 publications in international journals, conferences and workshops. Additionally, she serves as technical programme committee member in several international conferences and workshops. She is reviewer and guest editor of several international journals. Furthermore, she is a member of IEEE, ACM and HIPEAC. Her research interests include Reconfigurable Computing, Multiprocessor Systems-on-Chip (MPSoCs), Networks-on-Chip, Simulators / Virtual Platforms, Hardware-Software-Codesign and Runtime Systems.


  Back to course info