Skip to content

Instantly share code, notes, and snippets.

What would you like to do?

Power Estimate


Complete System Power Estimation using Processor Performance Events


Power estimate wiki (before 2012)

We have presented a systematic study on the use of performance counters to estimate power online. We found a subset of counters (# Fetched instructions, L1 hit and Dispatch Stalls) that are suitable for estimating power across multiple architecture types within an error of 5%. This was illustrated using an OOO high performance (HPerf) and an in-order low power (LP) core. At 5% average error, the proposed estimator improves upon prior estimators with error of 9% [3] and 11.5% [4].


Leakage power and dynamic energy per access for an SRAM and DRAM memory. The values base on confidential industry predictions and have been anonymised, maintaining the right relations and orders of magnitude. To visualise the meaning of the values, the 2018's predictions have been translated into Watts per MB for leakage and Watts per 100MHz operation speed (under burst access).

Per task memory energy consumption;jsessionid=B733068B3269875E9C59F7588029395A?sequence=1

DDR4 power calculation (activation vs standby)


VM Level Power Estimate

Energy Efficiency

CPU RAPL and temperature

CPU utilization and energy consumption

Run-time Energy Consumption Estimation Based on Workload in Server System

K8s energy aware scheduler


Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment