Using Dependent Types to Define Energy Augmented Semantics of Programs

Energy is becoming a key resource for IT systems. Hence, it can be essential for the success of a system under development to be able to derive and optimise its resource consumption. For large IT systems, compositionality is a key property in order to be applicable in practice. If such a method is hardware parametric, the effect of using different algorithms or running the same software on different hardware configurations can be studied. This article presents a hardware-parametric, compositional and precise type system to derive energy consumption functions. These energy functions describe the energy consumption behaviour of hardware controlled by the software. This type system has the potential to predict energy consumptions of algorithms and hardware configurations, which can be used on design level or for optimisation