An accurate instruction-level energy consumption model for embedded RISC processors

Energy consumption of software is becoming an increasingly important issue in designing mobile embedded systems where batteries are used as the main power source. As a consequence, recently, a number of promising techniques have been proposed to optimize software for reduced energy consumption. Such low-power software techniques require an energy consumption model that can be used to estimate or predict the energy consumed by software. We propose a technique to derive an accurate energy consumption model at the instruction level, combining an empirical method and a statistical analysis technique. The result of the proposed approach is given by a model equation that characterizes energy behavior of software based on the properties of the instructions. Experimental results show that the model equation can accurately estimate the energy consumption of random instruction sequences, with an average error of 2.5 %.