Trends in multimedia consumer electronics, digital video and audio, aim to reach users through low-cost mobile devices connected to data broadcasting networks with limited bandwidth. An emergent broadcasting network is the digital audio broadcasting network (DAB) which provides CD quality audio transmission together with robustness and efficiency techniques to allow good quality reception in motion conditions. This paper focuses on the system-level evaluation of different architectural options to allow low bandwidth digital video reception over DAB, based on video compression techniques. Profiling and design space exploration techniques are applied over the ASP MPEG-4 decoder in order to find out the best HW/SW partition given the application and platform constraints. An innovative SystemC-based system-level design tool, called CASSE, is being used for modelling, exploration and evaluation of different ASP MPEG-4 decoder HW/SW partitions. System-level trade offs and quantitative data derived from this analysis are also presented in this work.
This paper discusses and compares solutions for the issue of signalling and synchronization in the heterogeneous architecture multiprocessor paradigm. The on-chip interconnect infrastructure is split conceptually into a data transport network and a signalling network. This paper presents a SystemC based technique for modelling the communication architecture, with different topologies for the synchronization or signalling network. Each topology is parameterised for several communication requirements that define a point in the communication space. A high abstraction model leads to an experimental set-up that eases the analysis of the quantitative and qualitative behaviour of the networks for representative points in the communication space of the system design. The SystemC simulation models developed allow us to obtain information about total simulation time, processing time spent by the coprocessors, data transport time (read/write) used by the coprocessors (including arbitration time), and synchronization time spent by the coprocessors and the network. Another important metric is the coprocessor usage percentage. Results show that splitting data and signalling networks bring additional improvement to the performance of the system. The model applies well when mapping to architectural platforms the application processes expressed by abstract computational models such as Kahn process networks (KPN), synchronous data flow models (SDF), and generalized communicating sequential processes models (CSP).