Model-Integrated Environment for Adaptive Computing

Many high-performance, embedded applications must function in rapidly changing environments. Power/size constraints limit hardware size, while performance requirements demand algorithm-specific architectures. Reconfigurable computing devices allow the architecture to change in response to the changing environment. A model-integrated approach is used for the synthesis of these systems. The target systems are built on a heterogeneous computing platform: including configurable hardware, ASIC and general-purpose processors and DSPs. The model interpretation process will generate hardware/software architecture specifications and a run-time Configuration Manger allowing dynamic adaptation to changing environments while the synthesized system is online. The synthesis process will optimize hardware/software architectures for user-definable cost functions such as weight, power, algorithmic accuracy and flexibility.