Accurately estimating CPU power consumption is a key requirement for controlling CPUs – e.g. for implementing energy saving techniques – and for exploring the CPU design space.
ARM-ECS researchers have developed a tool that uses models built and validated from real, measured data from an actual device. This means that the tool accuracy is known and therefore the power figures can be trusted.
Obtaining accurate data from mobile devices can be challenging and more time-consuming than using a simulator or desktop/server devices. For this reason, we are making available our experimental platform software tools which allow workloads to be automatically run on a mobile device. Metrics such as Performance Monitoring Counters (PMCs), temperature, CPU utilisation, CPU power and CPU voltage are collected and analysed to produce accurate power models.
The power modelling software had two main features:
Further details on the tool methodology will be published shortly (currently under review).
Further information and the tool software download is available at: