Publikation

Hardware-Software Co-Visualization: Developing Systems in the Holodeck

Rolf Drechsler, Mathias Soeken

In: IEEE Symposium on Design and Diagnostics of Electronic Circuits and Systems. IEEE Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS-13) April 8-10 Karlovy Vary Czech Republic IEEE 2013.

Abstrakt

Modern systems consisting of hardware and soft-ware are becoming more and more complex. The underlying data of next generation systems will consist of billions of entries in terms of components or lines of code. Handling this data efficiently is one of the major challenges for future EDA. In order to provide a meaningful preparation for these complex issues it is inevitable to deal with highly elaborated visualization techniques. It is unimaginable how data sets of this size could be grasped without advanced plotting methods. Although a lot of effort has been put into research for visualization of hardware and software, techniques hardly exist that consider them in combination. Besides that, in most cases visualization techniques concentrate on the illustration of the system’s structure and behavior, e.g. to ease debugging. However, far more information can be integrated. As an example, in the context of verification the accentuation of coverage metrics on top of the structural visualization of a system would immediately pinpoint the verification engineer to areas that are poorly validated. Furthermore, when considering the co-design of hardware- software systems, design exploration can be carried out much easier when the designer gets immediate visual feedback. Inspired by recent achievements in visualization methods and the invention of sophisticated machinery, in this invited paper we propose the use of Hardware-Software Co-Visualization (HSCV). The potential of current techniques as well as their limitations will be demonstrated. Furthermore, we are seeking for alternative methods in system visualization that go beyond monitors and printed pages. Techniques from 3D rendering and virtual reality are utilized for this purpose leading to a holistic environment in which complex systems can be grasped within seconds just as huge data sets in the context of plots. State-of-the-art is presented and directions for future work are outlined

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence