Digital Signal Processing: The Impact of Convergence on Hardware Design Flow

By:
Mr Kofi Appiah,
Andrew Hunter
To add a paper, Login.

Design and development of real-time, memory and processor hungry digital signal processing systems have for decades been accomplished on general-purpose microprocessors. Various attempts to improve the performance of these systems resulted in the use of dedicated digital signal processing devices like DSP processors and the former heavyweight champion of electronics design — Application Specific Integrated Circuits.

The advent of RAM-based Field Programmable Gate Arrays has changed the DSP design flow. Software algorithmic designers can now take their DSP algorithms right from inception to hardware implementation, thanks to the increasing number of C/C++ hardware design flow. This has led to a demand in the industry for graduates with good skills in both electrical engineering and computer science. This paper evaluates the impact of technology on DSP-based designs, hardware design languages, and how graduate/undergraduate courses have changed to suit this transition.


Keywords: Digital Signal Processing, Application Specific Integrated Circuits, Field Programmable Gate Array, Augmented C/C++ design-flow
Stream: Technology in Community, Technology in Education
Presentation Type: Paper Presentation in
Paper: Digital Signal Processing


Mr Kofi Appiah

Research Student, Department of Computing and Informatics, Faculty of Applied Computing Sciences, University of Lincoln
UK

Mr Kofi Appiah graduated with BSc Computer Science in 2000 at the University of Science and Technology in Ghana. He has an MSc in Electrical Engineering from Royal Institute of Technology (KTH) in Sweden and an MSc in Computer Science from University of Oxford in England. He is now a PhD candidate at the University of Lincoln in UK.

Andrew Hunter

Head of Department, Dept. Computing and Informatics, University of Lincoln
UK

I am the leader of the Vision and Intelligence group at Lincoln, which is currently active in a number of areas, including: automated diagnosis of diabetic retinopathy, the leading cause of blindness in the developed world; security surveillance and monitoring of the vulnerable; automated dosing of Warfarin; the inference of comprehensible models for medical practitioners; and satellite imaging. These projects exploit a range of technologies, including: active contour models, neural networks and genetic programming.


Ref: T05P0038