High-fidelity markovian power model for protocols

We formally define a high-level power-aware protocol model based on a Markov chain, and consider 2 aspects of power consumption: the general switching activity, and the cost of data transfers. A state-assignment algorithm is devised that results in a state encoding that is near the theoretical lower bound (in the protocols we have studied). We have analyzed a set of protocol `converters' that have been synthesised for the AMBA protocol, and compared the (high-level) predicted power consumption with the power actually used during (low-level) simulation of these converters. We observe high fidelity.