Adaptive Power monitoring for self-aware embedded systems

Mohamad El Ahmad (1) , Mohamad Najem (1) , Pascal Benoit (1) , Gilles Sassatelli (1) , Lionel Torres (1)

1 ADAC - ADAptive Computing

Dynamic Thermal and Power Management methods require efficient monitoring techniques. Based on a set of data collected by sensors, embedded models estimate online the power consumption: this task is a real challenge, since models must be both accurate and low cost, but they also have to be robust to variations. In this paper, we investigate a self-aware approach using the performance events and the external temperature. We present a solution (PESel) for the selection of the relevant information. This method is two times faster than existing solutions and provides better results compared to related works. The power models achieve a 96% accuracy with a temporal resolution of 100 ms, and negligible performance/energy overheads (less than 1%). Moreover, we show that our estimations are not sensitive to external temperature variations.

Mots clés: Power Monitoring; Thermal Modeling; Performance Ponitoring Counter selection; Power Modeling; Adaptive systems; Self-Aware

Domaines: Informatique [cs]; Micro et nanotechnologies/Microélectronique

Mohamad El Ahmad, Mohamad Najem, Pascal Benoit, Gilles Sassatelli, Lionel Torres. Adaptive Power monitoring for self-aware embedded systems. NORCAS 2015 - 1st Nordic Circuits and Systems Conference, Oct 2015, Oslo, Norway. ⟨10.1109/NORCHIP.2015.7364364⟩. ⟨lirmm-01257519⟩