Power Measurement Techniques for Energy-Efficient Computing: Reconciling Scalability, Resolution, and Accuracy

Research output: Contribution to journalResearch articleContributedpeer-review

Abstract

The rising concern for power consumption of large-scale computer systems puts a research focus on the respective measurement methods. Varying workload patterns and energy efficiency optimizations cause highly dynamic power consumption on today’s compute nodes—a challenge for every measurement infrastructure. We identify five partly contradictory requirements that characterize such infrastructures: temporal granularity, spatial granularity, well-defined accuracy, scalability, and cost. In two projects we push the boundaries for these criteria: a scalable measurement solution for hundreds of nodes at millisecond granularity that is tightly integrated into the HPC system, and a sophisticated single-node instrumentation to measure the power consumption of application events in the microsecond range. Both measurement solutions are calibrated and their accuracy is carefully studied. We discuss scalable processing of the measurements for global monitoring in large-scale systems and use this data for energy efficiency analyses in combination with contextual information such as application performance trace data.

Details

Original languageEnglish
Pages (from-to)45-52
JournalSoftware-Intensive Cyber-Physical Systems
Publication statusPublished - 2018
Peer-reviewedYes

External IDs

Scopus 85067680465
ORCID /0000-0002-8491-770X/work/141543282
ORCID /0009-0003-0666-4166/work/151475575
ORCID /0000-0002-5437-3887/work/154740503

Keywords

Sustainable Development Goals

Keywords

  • 2018, HAEC, Power measurement, Energy efficiency