Energy-efficient SCalable Algorithms for weather Prediction at Exascale

Informations projet

ESCAPE

N° de convention de subvention: 671627

DOI

10.3030/671627

Projet clôturé

Date de signature de la CE 24 Juin 2015

Date de début 1 Octobre 2015

Date de fin 30 Septembre 2018

Financé au titre de

• EXCELLENT SCIENCE - Future and Emerging Technologies (FET)

Coût total

€ 3 977 952,50

Contribution de l’UE

€ 3 977 952,50

Coordonné par

EUROPEAN CENTRE FOR MEDIUM-RANGE WEATHER FORECASTS
United Kingdom

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Websites, patent fillings, videos etc. (6)

Summer school
Dissemination final assembly
Dissemination workshop II
Undergraduate training facility
Dissemination workshop I
Web portal

Documents, reports (9)

Recommendations and specifications for data scope analysis tools
Final report

Final report: Report compiling ESCAPE results for all work packages

Report on energy-efficiency evaluation of several NWP model configurations
Exploitation Plan after closure

Exploitation Plan after closure: Strategy for defining measures for exploitation “after the project” phase, providing evidence of best practices in capturing and assessing IPR

Performance report and optimized implementation of Weather & Climate Dwarfs on GPU, MIC

Performance report and optimized implementation of Weather & Climate Dwarfs on GPU, MIC and Optalysys Optical Processor

Projections of achievable performance for Weather & Climate Dwarfs

Projections of achievable performance for Weather & Climate Dwarfs, and for entire NWP applications, on hybrid architectures

Report summarizing additional key features required for different directives based porting

Report summarizing additional key features required for different directives based porting approaches disseminated to standard bodies and vendors

Report on workflow analysis for specific LAM applications
Report on the performance portability demonstrated for the relevant Weather & Climate Dwarfs

Other (4)

Batch 2: Definition of novel Weather & Climate Dwarfs

Batch 2: Definition of novel Weather & Climate Dwarfs, provision of prototype implementations and dissemination to other WPs

Atlas library version under an open source license

Atlas library version under an open source license which is accelerator-enabled and has improved interoperability features

Batch 1: Definition of several Weather & Climate Dwarfs

Batch 1: Definition of several Weather & Climate Dwarfs based on established algorithms and motifs relevant to NWP, provision of prototype implementations and dissemination to other WPs

Development of the flexible data structure framework Atlas

Publications

Peer reviewed articles (9)

A finite-volume module for simulating global all-scale atmospheric flows

Auteurs: Piotr K. Smolarkiewicz, Willem Deconinck, Mats Hamrud, Christian Kühnlein, George Mozdzynski, Joanna Szmelter, Nils P. Wedi
Publié dans: Journal of Computational Physics, Numéro 314, 2016, Page(s) 287-304, ISSN 0021-9991
Éditeur: Academic Press
DOI: 10.1016/j.jcp.2016.03.015

FVM 1.0: A nonhydrostatic finite-volume dynamical core formulation for IFS

Auteurs: Christian Kühnlein, Willem Deconinck, Rupert Klein, Sylvie Malardel, Zbigniew P. Piotrowski, Piotr K. Smolarkiewicz, Joanna Szmelter, Nils P. Wedi
Publié dans: Geoscientific Model Development Discussions, 2018, Page(s) 1-37, ISSN 1991-962X
Éditeur: EGU Publications
DOI: 10.5194/gmd-2018-237

An optical Fourier transform coprocessor with direct phase determination

Auteurs: Alexander J. Macfaden, George S. D. Gordon, Timothy D. Wilkinson
Publié dans: Scientific Reports, Numéro 7/1, 2017, ISSN 2045-2322
Éditeur: Nature Publishing Group
DOI: 10.1038/s41598-017-13733-1

Current and Emerging Time-Integration Strategies in Global Numerical Weather and Climate Prediction

Auteurs: Gianmarco Mengaldo, Andrzej Wyszogrodzki, Michail Diamantakis, Sarah-Jane Lock, Francis X. Giraldo, Nils P. Wedi
Publié dans: Archives of Computational Methods in Engineering, 2018, ISSN 1134-3060
Éditeur: International Center for Numerical Methods in Engineering
DOI: 10.1007/s11831-018-9261-8

Atlas : A library for numerical weather prediction and climate modelling

Auteurs: Willem Deconinck, Peter Bauer, Michail Diamantakis, Mats Hamrud, Christian Kühnlein, Pedro Maciel, Gianmarco Mengaldo, Tiago Quintino, Baudouin Raoult, Piotr K. Smolarkiewicz, Nils P. Wedi
Publié dans: Computer Physics Communications, Numéro 220, 2017, Page(s) 188-204, ISSN 0010-4655
Éditeur: Elsevier BV
DOI: 10.1016/j.cpc.2017.07.006

Simulation of the performance and scalability of message passing interface (MPI) communications of atmospheric models running on exascale supercomputers

Auteurs: Yongjun Zheng, Philippe Marguinaud
Publié dans: Geoscientific Model Development, Numéro 11/8, 2018, Page(s) 3409-3426, ISSN 1991-9603
Éditeur: EGU Publications
DOI: 10.5194/gmd-11-3409-2018

Crossing the chasm: how to develop weather and climate models for next generation computers?

Auteurs: Lawrence, Bryan N.; Rezny, Michael; Budich, Reinhard; Bauer, Peter; Behrens, Jörg; Carter, Mick; Deconinck, Willem; Ford, Rupert; Maynard, Christopher; Mullerworth, Steven; Osuna, Carlos; Porter, Andrew; Serradell, Kim; Valcke, Sophie; Wedi, Nils; Wilson, Simon
Publié dans: eISSN: 1991-9603, Numéro 2, 2018, ISSN 1991-9603
Éditeur: Copernicus
DOI: 10.3929/ethz-b-000265172

The ESCAPE project: Energy-efficient Scalable Algorithms for Weather Prediction at Exascale

Auteurs: Andreas Müller, Willem Deconinck, Christian Kühnlein, Gianmarco Mengaldo, Michael Lange, Nils Wedi, Peter Bauer, Piotr K. Smolarkiewicz, Michail Diamantakis, Sarah-Jane Lock, Mats Hamrud, Sami Saarinen, George Mozdzynski, Daniel Thiemert, Michael Glinton, Pierre Bénard, Fabrice Voitus, Charles Colavolpe, Philippe Marguinaud, Yongjun Zheng, Joris Van Bever, Daan Degrauwe, Geert Smet, Piet Termon
Publié dans: Geoscientific Model Development Discussions, 2019, Page(s) 1-50, ISSN 1991-962X
Éditeur: EGU
DOI: 10.5194/gmd-2018-304

Simulation of all-scale atmospheric dynamics on unstructured meshes

Auteurs: Piotr K. Smolarkiewicz, Joanna Szmelter, Feng Xiao
Publié dans: Journal of Computational Physics, Numéro 322, 2016, Page(s) 267-287, ISSN 0021-9991
Éditeur: Academic Press
DOI: 10.1016/j.jcp.2016.06.048

Conference proceedings (1)

A Class of Finite-Volume Models for Atmospheric Flows Across Scales

Auteurs: Joanna Szmelter, Mike Gillard, Piotr Smolarkiewicz, Christian Kühnlein
Publié dans: 2018 Atmospheric and Space Environments Conference, 2018, ISBN 978-1-62410-558-6
Éditeur: American Institute of Aeronautics and Astronautics
DOI: 10.2514/6.2018-3497

Non-peer reviewed articles (1)

Energy-efficient SCalable Algorithms for weather Prediction at Exascale

Auteurs: Peter Bauer, Nils Wedi, Michael Baldauf, Pierre Benard, Oliver Fuhrer, Michal Kulczewski, Alastair McKinstry, Peter Messmer, Nick New, Bent HansenSass, Joanna Szmelter, Piet Termonia, Xavier Vigouroux
Publié dans: Impact, Numéro 2017/1, 2017, Page(s) 69-71, ISSN 2398-7073
Éditeur: Science Impact Ltd
DOI: 10.21820/23987073.2017.1.69

Other (1)

Optimization of IFS Subroutine LAITRI on Intel Knights Landing

Auteurs: Oisın Robinson, Alastair McKinstry, Michael Lysaght
Publié dans: Prace White Papers, Numéro Evaluations on Intel MIC, 2016
Éditeur: PRACE