LFRic:: Meeting the challenges of scalability and performance portability in Weather and Climate models

S. V. Adams; R. W. Ford; M. Hambley; J. M. Hobson; I. Kavcic; C. M. Maynard; T. Melvin; Eike Müller; S. Mullerworth; A. R. Porter; M. Rezney; B. J. Shipway; R. Wong

doi:10.1016/j.jpdc.2019.02.007

LFRic: Meeting the challenges of scalability and performance portability in Weather and Climate models

S. V. Adams, R. W. Ford, M. Hambley, J. M. Hobson, I. Kavcic, C. M. Maynard, T. Melvin, Eike Müller, S. Mullerworth, A. R. Porter, M. Rezney, B. J. Shipway, R. Wong

Research output: Contribution to journal › Article › peer-review

47 Citations (SciVal)

47 Downloads (Pure)

Abstract

This paper describes LFRic: the new weather and climate modelling system being developed by the UK Met Office to replace the existing Unified Model in preparation for exascale computing in the 2020s. LFRic uses the GungHo dynamical core and runs on a semi-structured cubed-sphere mesh. The design of the supporting infrastructure follows object-oriented principles to facilitate modularity and the use of external libraries where possible. In particular, a ‘separation of concerns’ between the science code and parallel code is imposed to promote performance portability. An application called PSyclone, developed at the STFC Hartree centre, can generate the parallel code enabling deployment of a single source science code onto different machine architectures. This paper provides an overview of the scientific requirement, the design of the software infrastructure, and examples of PSyclone usage. Preliminary performance results show strong scaling and an indication that hybrid MPI/OpenMP performs better than pure MPI.

Original language	English
Pages (from-to)	383-396
Number of pages	14
Journal	Journal of Parallel and Distributed Computing
Volume	132
Early online date	21 May 2019
DOIs	https://doi.org/10.1016/j.jpdc.2019.02.007
Publication status	Published - 1 Oct 2019
Event	Exascale Applications and Software 2018 - Edinburgh, UK United Kingdom Duration: 17 Apr 2018 → 19 Apr 2018 http://www.easc2018.ed.ac.uk/

Keywords

Domain specific language
Exascale
Numerical weather prediction
Separation of concerns

ASJC Scopus subject areas

Software
Theoretical Computer Science
Hardware and Architecture
Computer Networks and Communications
Artificial Intelligence

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.jpdc.2019.02.007

LFricAcceptedAccepted author manuscript, 479 KBLicence: CC BY-NC-ND

Cite this

Adams, S. V., Ford, R. W., Hambley, M., Hobson, J. M., Kavcic, I., Maynard, C. M., Melvin, T., Müller, E., Mullerworth, S., Porter, A. R., Rezney, M., Shipway, B. J., & Wong, R. (2019). LFRic: Meeting the challenges of scalability and performance portability in Weather and Climate models. Journal of Parallel and Distributed Computing, 132, 383-396. https://doi.org/10.1016/j.jpdc.2019.02.007

Adams, SV, Ford, RW, Hambley, M, Hobson, JM, Kavcic, I, Maynard, CM, Melvin, T, Müller, E, Mullerworth, S, Porter, AR, Rezney, M, Shipway, BJ & Wong, R 2019, 'LFRic: Meeting the challenges of scalability and performance portability in Weather and Climate models', Journal of Parallel and Distributed Computing, vol. 132, pp. 383-396. https://doi.org/10.1016/j.jpdc.2019.02.007

@article{b65e20ab18db4fdca226f1868abd5f5c,

title = "LFRic:: Meeting the challenges of scalability and performance portability in Weather and Climate models",

abstract = "This paper describes LFRic: the new weather and climate modelling system being developed by the UK Met Office to replace the existing Unified Model in preparation for exascale computing in the 2020s. LFRic uses the GungHo dynamical core and runs on a semi-structured cubed-sphere mesh. The design of the supporting infrastructure follows object-oriented principles to facilitate modularity and the use of external libraries where possible. In particular, a {\textquoteleft}separation of concerns{\textquoteright} between the science code and parallel code is imposed to promote performance portability. An application called PSyclone, developed at the STFC Hartree centre, can generate the parallel code enabling deployment of a single source science code onto different machine architectures. This paper provides an overview of the scientific requirement, the design of the software infrastructure, and examples of PSyclone usage. Preliminary performance results show strong scaling and an indication that hybrid MPI/OpenMP performs better than pure MPI.",

keywords = "Domain specific language, Exascale, Numerical weather prediction, Separation of concerns",

author = "Adams, {S. V.} and Ford, {R. W.} and M. Hambley and Hobson, {J. M.} and I. Kavcic and Maynard, {C. M.} and T. Melvin and Eike M{\"u}ller and S. Mullerworth and Porter, {A. R.} and M. Rezney and Shipway, {B. J.} and R. Wong",

year = "2019",

month = oct,

day = "1",

doi = "10.1016/j.jpdc.2019.02.007",

language = "English",

volume = "132",

pages = "383--396",

journal = "Journal of Parallel and Distributed Computing",

issn = "0743-7315",

publisher = "Elsevier Academic Press Inc",

note = "Exascale Applications and Software 2018, EASC 2018 ; Conference date: 17-04-2018 Through 19-04-2018",

url = "http://www.easc2018.ed.ac.uk/",

}

TY - JOUR

T1 - LFRic:

T2 - Exascale Applications and Software 2018

AU - Adams, S. V.

AU - Ford, R. W.

AU - Hambley, M.

AU - Hobson, J. M.

AU - Kavcic, I.

AU - Maynard, C. M.

AU - Melvin, T.

AU - Müller, Eike

AU - Mullerworth, S.

AU - Porter, A. R.

AU - Rezney, M.

AU - Shipway, B. J.

AU - Wong, R.

PY - 2019/10/1

Y1 - 2019/10/1

N2 - This paper describes LFRic: the new weather and climate modelling system being developed by the UK Met Office to replace the existing Unified Model in preparation for exascale computing in the 2020s. LFRic uses the GungHo dynamical core and runs on a semi-structured cubed-sphere mesh. The design of the supporting infrastructure follows object-oriented principles to facilitate modularity and the use of external libraries where possible. In particular, a ‘separation of concerns’ between the science code and parallel code is imposed to promote performance portability. An application called PSyclone, developed at the STFC Hartree centre, can generate the parallel code enabling deployment of a single source science code onto different machine architectures. This paper provides an overview of the scientific requirement, the design of the software infrastructure, and examples of PSyclone usage. Preliminary performance results show strong scaling and an indication that hybrid MPI/OpenMP performs better than pure MPI.

AB - This paper describes LFRic: the new weather and climate modelling system being developed by the UK Met Office to replace the existing Unified Model in preparation for exascale computing in the 2020s. LFRic uses the GungHo dynamical core and runs on a semi-structured cubed-sphere mesh. The design of the supporting infrastructure follows object-oriented principles to facilitate modularity and the use of external libraries where possible. In particular, a ‘separation of concerns’ between the science code and parallel code is imposed to promote performance portability. An application called PSyclone, developed at the STFC Hartree centre, can generate the parallel code enabling deployment of a single source science code onto different machine architectures. This paper provides an overview of the scientific requirement, the design of the software infrastructure, and examples of PSyclone usage. Preliminary performance results show strong scaling and an indication that hybrid MPI/OpenMP performs better than pure MPI.

KW - Domain specific language

KW - Exascale

KW - Numerical weather prediction

KW - Separation of concerns

UR - http://www.scopus.com/inward/record.url?scp=85066413388&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2019.02.007

DO - 10.1016/j.jpdc.2019.02.007

M3 - Article

SN - 0743-7315

VL - 132

SP - 383

EP - 396

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

Y2 - 17 April 2018 through 19 April 2018

ER -

LFRic: Meeting the challenges of scalability and performance portability in Weather and Climate models

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

High Performance Computing (HPC) Facility

Cite this

LFRic: Meeting the challenges of scalability and performance portability in Weather and Climate models

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Equipment

High Performance Computing (HPC) Facility

Cite this