A datapath synthesis system for the reconfigurable datapath architecture
ASP-DAC '95 Proceedings of the 1995 Asia and South Pacific Design Automation Conference
Combining structural and procedural programming by parallelizing compilation
SAC '95 Proceedings of the 1995 ACM symposium on Applied computing
A decade of reconfigurable computing: a visionary retrospective
Proceedings of the conference on Design, automation and test in Europe
KressArray Xplorer: a new CAD environment to optimize reconfigurable datapath array
ASP-DAC '00 Proceedings of the 2000 Asia and South Pacific Design Automation Conference
Coarse grain reconfigurable architecture (embedded tutorial)
Proceedings of the 2001 Asia and South Pacific Design Automation Conference
Are We Really Ready for the Breakthrough ?
IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Configware and morphware going mainstream
Journal of Systems Architecture: the EUROMICRO Journal - Special issue: Reconfigurable systems
The digital divide of computing
Proceedings of the 1st conference on Computing frontiers
Reconfigurable HPC: Torpedoed by Deficits in Education?
HPCASIA '04 Proceedings of the High Performance Computing and Grid in Asia Pacific Region, Seventh International Conference
New challenges in computer science education
ITiCSE '05 Proceedings of the 10th annual SIGCSE conference on Innovation and technology in computer science education
Diverse hardware platforms in embedded systems lab courses: a way to teach the differences
ACM SIGBED Review - Special issue: The first workshop on embedded system education (WESE)
Hardware platform design decisions in embedded systems: a systematic teaching approach
ACM SIGBED Review - Special issues on the second workshop on embedded system education (WESE)
| Hi-index | 0.00 |
More than 98% of all microprocessors are found within embedded systems. The British Department of Trade and Industry predicts, that by the year 2010 more than 90% of all program code will be implemented for embedded applications. But the qualification of our "typical" CS (and CIT) graduates is torpedoed by deficits of our current computer architecture education limiting the horizon to procedural programming in the time domain. However, meanwhile the fundamental machine model is no more just the "von Neumann" paradigm merely supporting an instruction-stream-based mind set. For embedded systems the basic model is a symbiosis between CPU and primarily data-stream-based accelerator co-processors. Implementing applications for embedded systems also requires hardware / software partitioning decisions. Since meanwhile morphware [1] [2] and Reconfigurable Computing (RC) has become mainstream, also the accelerators are programmable by loading configware code downto their hidden RAM [3]. What is urgently needed is the qualification for programming in time (programming software) and programming in space (programming configware). But currently the software for the CPU is mainly implemented by software people, whereas the accelerators are implemented by EEs or other hardware people.