English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Power and thermal management are critical components ofHigh-Performance-Computing (HPC) systems, due to their high power density andlarge total power consumption. The assessment of thermal dissipation by meansof compact models directly from the thermal response of the final deviceenables more robust and precise thermal control strategies as well as automateddiagnosis. However, when dealing with large scale systems "in production", theaccuracy of learned thermal models depends on the dynamics of the powerexcitation, which depends also on the executed workload, and measurementnonidealities, such as quantization. In this paper we show that, using anadvanced system identification algorithm, we are able to generate very accuratethermal models (average error lower than our sensors quantization step of1{\deg}C) for a large scale HPC system on real workloads for very long timeperiods. However, we also show that: 1) not all real workloads allow for theidentification of a good model; 2) starting from the theory of systemidentification it is very difficult to evaluate if a trace of data leads to agood estimated model. We then propose and validate a set of techniques based onmachine learning and deep learning algorithms for the choice of data traces tobe used for model identification. We also show that deep learning techniquesare absolutely necessary to correctly choose such traces up to 96% of thetimes.

Robust identification of thermal models for in-production High-Performance-Computing clusters with machine learning-based data selection