Computational design of the NCAR community climate model

James J. Hack; James M. Rosinski; David L. Williamson; Byron A. Boville; John E. Truesdale

doi:10.1016/0167-8191(95)00036-6

Computational design of the NCAR community climate model

James J. Hack, James M. Rosinski, David L. Williamson, Byron A. Boville, John E. Truesdale

Atmospheric Modeling and Predictability

National Center for Atmospheric Research

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

17 Scopus citations

Abstract

An overview of the computational design for the latest version of the NCAR Atmospheric General Circulation Model, designated CCM2, is presented. Parallel implementation details are driven by two major algorithmic classes of computation that require different patterns of data communication, the spectral transform method and the semi-Lagrangian advection technique. The organization and performance characteristics of a shared-memory parallel implementation, and an analogous distributed-memory message-passing parallel implementation are described. The advantages and limitations of this coarse-grained partitioning are discussed in the context of global climate modeling research.

Original language	English
Pages (from-to)	1545-1569
Number of pages	25
Journal	Parallel Computing
Volume	21
Issue number	10
DOIs	https://doi.org/10.1016/0167-8191(95)00036-6
State	Published - Oct 1995

Keywords

Atmospheric general circulation modeling
Climate modeling
Distributed-memory parallel computing
Shared-memory parallel computing

Access to Document

10.1016/0167-8191(95)00036-6

Cite this

@article{9113eeba297645ecb54125f803b48569,

title = "Computational design of the NCAR community climate model",

abstract = "An overview of the computational design for the latest version of the NCAR Atmospheric General Circulation Model, designated CCM2, is presented. Parallel implementation details are driven by two major algorithmic classes of computation that require different patterns of data communication, the spectral transform method and the semi-Lagrangian advection technique. The organization and performance characteristics of a shared-memory parallel implementation, and an analogous distributed-memory message-passing parallel implementation are described. The advantages and limitations of this coarse-grained partitioning are discussed in the context of global climate modeling research.",

keywords = "Atmospheric general circulation modeling, Climate modeling, Distributed-memory parallel computing, Shared-memory parallel computing",

author = "Hack, \{James J.\} and Rosinski, \{James M.\} and Williamson, \{David L.\} and Boville, \{Byron A.\} and Truesdale, \{John E.\}",

year = "1995",

month = oct,

doi = "10.1016/0167-8191(95)00036-6",

language = "English",

volume = "21",

pages = "1545--1569",

journal = "Parallel Computing",

issn = "0167-8191",

publisher = "Elsevier B.V.",

number = "10",

}

TY - JOUR

T1 - Computational design of the NCAR community climate model

AU - Hack, James J.

AU - Rosinski, James M.

AU - Williamson, David L.

AU - Boville, Byron A.

AU - Truesdale, John E.

PY - 1995/10

Y1 - 1995/10

N2 - An overview of the computational design for the latest version of the NCAR Atmospheric General Circulation Model, designated CCM2, is presented. Parallel implementation details are driven by two major algorithmic classes of computation that require different patterns of data communication, the spectral transform method and the semi-Lagrangian advection technique. The organization and performance characteristics of a shared-memory parallel implementation, and an analogous distributed-memory message-passing parallel implementation are described. The advantages and limitations of this coarse-grained partitioning are discussed in the context of global climate modeling research.

AB - An overview of the computational design for the latest version of the NCAR Atmospheric General Circulation Model, designated CCM2, is presented. Parallel implementation details are driven by two major algorithmic classes of computation that require different patterns of data communication, the spectral transform method and the semi-Lagrangian advection technique. The organization and performance characteristics of a shared-memory parallel implementation, and an analogous distributed-memory message-passing parallel implementation are described. The advantages and limitations of this coarse-grained partitioning are discussed in the context of global climate modeling research.

KW - Atmospheric general circulation modeling

KW - Climate modeling

KW - Distributed-memory parallel computing

KW - Shared-memory parallel computing

UR - https://www.scopus.com/pages/publications/0029387618

U2 - 10.1016/0167-8191(95)00036-6

DO - 10.1016/0167-8191(95)00036-6

M3 - Article

AN - SCOPUS:0029387618

SN - 0167-8191

VL - 21

SP - 1545

EP - 1569

JO - Parallel Computing

JF - Parallel Computing

IS - 10

ER -

Computational design of the NCAR community climate model

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this