Towards bespoke optimizations of energy efficiency in HPC environments

Abstract We present bespoke energy efficiency optimizations in high performance computing (HPC) environments using holistic approach to data collection, analysis and proactive management of resources and workloads. Our solution has three major components: (i) platform for collecting, storing and pro...

Full description

Bibliographic Details
Main Authors: Robert Tracey, Vadim Elisseev, Michalis Smyrnakis, Lan Hoang, Mark Fellows, Michael Ackers, Andrew Laughton, Stephen Hill, Phillip Folkes, John Whittle
Format: Article
Language:English
Published: Wiley 2023-12-01
Series:Applied AI Letters
Subjects:
Online Access:https://doi.org/10.1002/ail2.87
_version_ 1797369648870588416
author Robert Tracey
Vadim Elisseev
Michalis Smyrnakis
Lan Hoang
Mark Fellows
Michael Ackers
Andrew Laughton
Stephen Hill
Phillip Folkes
John Whittle
author_facet Robert Tracey
Vadim Elisseev
Michalis Smyrnakis
Lan Hoang
Mark Fellows
Michael Ackers
Andrew Laughton
Stephen Hill
Phillip Folkes
John Whittle
author_sort Robert Tracey
collection DOAJ
description Abstract We present bespoke energy efficiency optimizations in high performance computing (HPC) environments using holistic approach to data collection, analysis and proactive management of resources and workloads. Our solution has three major components: (i) platform for collecting, storing and processing data from multiple sources across hardware and software stacks, (ii) collections of regression machine learning (ML) algorithms for making workloads classifications and energy usage predictions, (iii) agent‐based decision‐making framework for delivering control decisions to middle‐ware and infrastructure thus supporting real time or near real energy efficiency optimizations. We will provide some concrete examples of using our proposed approach in HPC environment.
first_indexed 2024-03-08T17:49:58Z
format Article
id doaj.art-48e41d27bc884d10b78b5d751a3bba83
institution Directory Open Access Journal
issn 2689-5595
language English
last_indexed 2024-03-08T17:49:58Z
publishDate 2023-12-01
publisher Wiley
record_format Article
series Applied AI Letters
spelling doaj.art-48e41d27bc884d10b78b5d751a3bba832024-01-02T08:29:24ZengWileyApplied AI Letters2689-55952023-12-0144n/an/a10.1002/ail2.87Towards bespoke optimizations of energy efficiency in HPC environmentsRobert Tracey0Vadim Elisseev1Michalis Smyrnakis2Lan Hoang3Mark Fellows4Michael Ackers5Andrew Laughton6Stephen Hill7Phillip Folkes8John Whittle9Daresbury Laboratory IBM Research Warrington UKDaresbury Laboratory IBM Research Warrington UKDaresbury Laboratory, The Hartree Centre STFC Warrington UKDaresbury Laboratory IBM Research Warrington UKDaresbury Laboratory, The Hartree Centre STFC Warrington UKDaresbury Laboratory, The Hartree Centre STFC Warrington UKDaresbury Laboratory, The Hartree Centre STFC Warrington UKDaresbury Laboratory STFC Warrington UKDaresbury Laboratory STFC Warrington UKDaresbury Laboratory STFC Warrington UKAbstract We present bespoke energy efficiency optimizations in high performance computing (HPC) environments using holistic approach to data collection, analysis and proactive management of resources and workloads. Our solution has three major components: (i) platform for collecting, storing and processing data from multiple sources across hardware and software stacks, (ii) collections of regression machine learning (ML) algorithms for making workloads classifications and energy usage predictions, (iii) agent‐based decision‐making framework for delivering control decisions to middle‐ware and infrastructure thus supporting real time or near real energy efficiency optimizations. We will provide some concrete examples of using our proposed approach in HPC environment.https://doi.org/10.1002/ail2.87cloudenergy efficiencyHPCmachine learning
spellingShingle Robert Tracey
Vadim Elisseev
Michalis Smyrnakis
Lan Hoang
Mark Fellows
Michael Ackers
Andrew Laughton
Stephen Hill
Phillip Folkes
John Whittle
Towards bespoke optimizations of energy efficiency in HPC environments
Applied AI Letters
cloud
energy efficiency
HPC
machine learning
title Towards bespoke optimizations of energy efficiency in HPC environments
title_full Towards bespoke optimizations of energy efficiency in HPC environments
title_fullStr Towards bespoke optimizations of energy efficiency in HPC environments
title_full_unstemmed Towards bespoke optimizations of energy efficiency in HPC environments
title_short Towards bespoke optimizations of energy efficiency in HPC environments
title_sort towards bespoke optimizations of energy efficiency in hpc environments
topic cloud
energy efficiency
HPC
machine learning
url https://doi.org/10.1002/ail2.87
work_keys_str_mv AT roberttracey towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT vadimelisseev towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT michalissmyrnakis towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT lanhoang towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT markfellows towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT michaelackers towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT andrewlaughton towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT stephenhill towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT phillipfolkes towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments
AT johnwhittle towardsbespokeoptimizationsofenergyefficiencyinhpcenvironments