Centre Researchers to Present at Arm Summit 2018

Arm-ECS Researchers to Present at Arm Summit 2018

Researchers from the Arm-ECS Centre have been accepted to present their work at the Arm Research Summit 2018. Dr Geoff Merrett will be giving a talk titled “Run-time Power and Energy Management of Many-Core Systems” (abstract below).

Abstract: Energy-efficiency is important at all scales of computing system, from microcontrollers through to HPC. Established mechanisms like DPM and DVFS provide controls to affect power consumption, but careful management is required for effective use. In this talk, I provide an overview of the different run-time power management (RTM) approaches that we have developed, explored and practically validated through the EPSRC PRiME programme grant (www.prime-project.org), and discuss key findings and lessons learnt. I also refer to a range of open-source tools that we have released as a result of the project, from multi-core power modelling to a cross-platform framework for RTM.

Related Projects

Power and Reliability in Many-core Embedded systems (PRiME)
See Project +

Related Technologies

GemStone: Hardware-Validated CPU Performance and Energy Modelling

GemStone is a suite of five software tools that, together, identify and evaluate the sources of error in gem5 models against a reference hardware (HW) platform by utilising statistical and machine learning approaches. Independently, the tools serve many purposes: Automating the running of experiments and collection of Performance Monitoring Counters (and temperature and power on supported platforms) on Arm-based devices (ARMv7 and ARMv8); Automating the running of gem5 simulations and aggregating the results; Applying Powmon power models to the hardware results; Applying Powmon power models to gem5 simulation data; Combining the HW and gem5 model characterisations and applying statistical and…

Read Article +

PowMon: Accurate and Stable CPU Power Estimation

Being able to accurately estimate CPU power consumption is a key requirement for both controlling online CPU energy-saving techniques and design-space exploration. Models built and validated using measured data from an actual device are extremely valuable as their accuracy is known and trusted. PowMon produces power models that are both accurate and stable. The open source PowMon software tools consists of a number of distinct parts: Software tools which allow researchers to implement our automated model building methodology, and produce power models of a platform that are both accurate and stable. Downloadable power models for existing mobile CPUs (quad-core Cortex-A7 and quad-core…

Read Article +