A highly scalable Met Office NERC Cloud model

Nicholas Brown; Michele Weiland; Adrian Hill; Ben Shipway; Chris Maynard; Thomas Allen; Mike Rezny

A highly scalable Met Office NERC Cloud model

Nicholas Brown, Michele Weiland, Adrian Hill, Ben Shipway, Chris Maynard, Thomas Allen, Mike Rezny

Computer Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Large Eddy Simulation is a critical modelling tool for scien- tists investigating atmospheric flows, turbulence and cloud microphysics. Within the UK, the principal LES model used by the atmospheric research community is the Met Office Large Eddy Model (LEM). The LEM was originally devel- oped in the late 1980s using computational techniques and assumptions of the time, which means that the it does not scale beyond 512 cores. In this paper we present the Met Office NERC Cloud model, MONC, which is a re-write of the existing LEM. We discuss the software engineering and architectural decisions made in order to develop a flexible, extensible model which the community can easily customise for their own needs. The scalability of MONC is evaluated, along with numerous additional customisations made to fur- ther improve performance at large core counts. The result of this work is a model which delivers to the community signifi- cant new scientific modelling capability that takes advantage of the current and future generation HPC machines.

Original language	English
Title of host publication	Proceedings of the 3rd International Conference on Exascale Applications and Software
Place of Publication	Edinburgh
Publisher	University of Edinburgh
ISBN (Electronic)	978-0-9926615-1-9
ISBN (Print)	978-0-9926615-1-9
Publication status	Published - 21 Apr 2015
Event	Exascale Applications and Software Conference 2015 - Edinburgh, United Kingdom Duration: 21 Apr 2015 → 23 Apr 2015

Conference

Conference	Exascale Applications and Software Conference 2015
Country/Territory	United Kingdom
City	Edinburgh
Period	21/04/15 → 23/04/15

Keywords / Materials (for Non-textual outputs)

MONC
LEM
Large Eddy Simulation
Met Office

Access to Document

MONC_EASC2015Accepted author manuscript, 234 KBLicence: Creative Commons: Attribution No Derivatives (CC-BY-ND)

http://dl.acm.org/citation.cfm?id=2820108

1 Finished

Development of a Met Office NERC cloud model (MONC)
Weiland, M. (Principal Investigator)
NERC
1/01/14 → 31/08/15
Project: Research

1 Software

Met Office NERC Cloud model (MONC)
Brown, N. & Weiland, M., 30 Apr 2018
Research output: Non-textual form › Software

Met Office NERC Cloud model (MONC)
Brown, N. (Creator) & Weiland, M. (Creator), Edinburgh DataShare, 30 Apr 2018
DOI: 10.7488/ds/2343
Dataset

1 Participation in workshop, seminar, course

ECMWF Workshop on Scalability
Weiland, M. (Invited speaker)
2014
Activity: Participating in or organising an event types › Participation in workshop, seminar, course

Cite this

@inproceedings{8f85bc9e5e6c4fc49d0133f41dee5ea4,

title = "A highly scalable Met Office NERC Cloud model",

abstract = "Large Eddy Simulation is a critical modelling tool for scien- tists investigating atmospheric flows, turbulence and cloud microphysics. Within the UK, the principal LES model used by the atmospheric research community is the Met Office Large Eddy Model (LEM). The LEM was originally devel- oped in the late 1980s using computational techniques and assumptions of the time, which means that the it does not scale beyond 512 cores. In this paper we present the Met Office NERC Cloud model, MONC, which is a re-write of the existing LEM. We discuss the software engineering and architectural decisions made in order to develop a flexible, extensible model which the community can easily customise for their own needs. The scalability of MONC is evaluated, along with numerous additional customisations made to fur- ther improve performance at large core counts. The result of this work is a model which delivers to the community signifi- cant new scientific modelling capability that takes advantage of the current and future generation HPC machines.",

keywords = "MONC, LEM, Large Eddy Simulation, Met Office",

author = "Nicholas Brown and Michele Weiland and Adrian Hill and Ben Shipway and Chris Maynard and Thomas Allen and Mike Rezny",

year = "2015",

month = apr,

day = "21",

language = "English",

isbn = "978-0-9926615-1-9",

booktitle = "Proceedings of the 3rd International Conference on Exascale Applications and Software",

publisher = "University of Edinburgh",

address = "United Kingdom",

note = "Exascale Applications and Software Conference 2015 ; Conference date: 21-04-2015 Through 23-04-2015",

}

Brown, N , Weiland, M, Hill, A, Shipway, B, Maynard, C, Allen, T & Rezny, M 2015, A highly scalable Met Office NERC Cloud model. in Proceedings of the 3rd International Conference on Exascale Applications and Software. University of Edinburgh, Edinburgh, Exascale Applications and Software Conference 2015, Edinburgh, United Kingdom, 21/04/15. <http://dl.acm.org/citation.cfm?id=2820108>

TY - GEN

T1 - A highly scalable Met Office NERC Cloud model

AU - Brown, Nicholas

AU - Weiland, Michele

AU - Hill, Adrian

AU - Shipway, Ben

AU - Maynard, Chris

AU - Allen, Thomas

AU - Rezny, Mike

PY - 2015/4/21

Y1 - 2015/4/21

N2 - Large Eddy Simulation is a critical modelling tool for scien- tists investigating atmospheric flows, turbulence and cloud microphysics. Within the UK, the principal LES model used by the atmospheric research community is the Met Office Large Eddy Model (LEM). The LEM was originally devel- oped in the late 1980s using computational techniques and assumptions of the time, which means that the it does not scale beyond 512 cores. In this paper we present the Met Office NERC Cloud model, MONC, which is a re-write of the existing LEM. We discuss the software engineering and architectural decisions made in order to develop a flexible, extensible model which the community can easily customise for their own needs. The scalability of MONC is evaluated, along with numerous additional customisations made to fur- ther improve performance at large core counts. The result of this work is a model which delivers to the community signifi- cant new scientific modelling capability that takes advantage of the current and future generation HPC machines.

AB - Large Eddy Simulation is a critical modelling tool for scien- tists investigating atmospheric flows, turbulence and cloud microphysics. Within the UK, the principal LES model used by the atmospheric research community is the Met Office Large Eddy Model (LEM). The LEM was originally devel- oped in the late 1980s using computational techniques and assumptions of the time, which means that the it does not scale beyond 512 cores. In this paper we present the Met Office NERC Cloud model, MONC, which is a re-write of the existing LEM. We discuss the software engineering and architectural decisions made in order to develop a flexible, extensible model which the community can easily customise for their own needs. The scalability of MONC is evaluated, along with numerous additional customisations made to fur- ther improve performance at large core counts. The result of this work is a model which delivers to the community signifi- cant new scientific modelling capability that takes advantage of the current and future generation HPC machines.

KW - MONC

KW - LEM

KW - Large Eddy Simulation

KW - Met Office

M3 - Conference contribution

SN - 978-0-9926615-1-9

BT - Proceedings of the 3rd International Conference on Exascale Applications and Software

PB - University of Edinburgh

CY - Edinburgh

T2 - Exascale Applications and Software Conference 2015

Y2 - 21 April 2015 through 23 April 2015

ER -

A highly scalable Met Office NERC Cloud model

Abstract

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Projects

Development of a Met Office NERC cloud model (MONC)

Research output

Met Office NERC Cloud model (MONC)

Datasets

Met Office NERC Cloud model (MONC)

Activities

ECMWF Workshop on Scalability

Cite this