Parallelizing Operational Weather Forecast Models for Portable and Fast Execution

Rodriguez, Bernardo; Hart, Leslie; Henderson, Tom

doi:10.1006/jpdc.1996.0116

Cited by 6 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth to mention, that our kernel functionally is similar to the Nearest Neighbor Tool (NNT) developed by Rodriguez, Hart, and Henderson [3].…”

Section: Communication Kernelmentioning

confidence: 99%

*Parallel Computations in Problems of Climate Modeling

Gloukhov

2004

Parallel Computational Fluid Dynamics 2003

View full text Add to dashboard Cite

The paper is focused on different approaches to parallel implementation of climate models on cluster multiprocessors. We present results of applying either MPI or OpenMP to the model components: atmospheric and oceanic blocks. A library of communication routines was developed for the distributed memory approach. It carries out the basic communication operations, such as boundary exchanges and transpositions of decomposed data. The library has quite general interface that makes it useful for parallelization of a wide range of scientific applications calculated on structured grids. In particular, we have examined it on INM AGCM as well as on a set of atmospheric benchmarks which integrate the equations of hydrothermodynamics of atmosphere under the hydrostatic assumption. An OpenMP implementation of the INM Ocean model has been undertaken and tested on few shared memory systems.

show abstract

“…It is worth to mention, that our kernel functionally is similar to the Nearest Neighbor Tool (NNT) developed by Rodriguez, Hart, and Henderson [3].…”

Section: Communication Kernelmentioning

confidence: 99%

*Parallel Computations in Problems of Climate Modeling

Gloukhov

2004

Parallel Computational Fluid Dynamics 2003

View full text Add to dashboard Cite

show abstract

“…Library-Based Tools -Library-based tools, such as the Runtime System Library (RSL) [18] and FSL's Nearest Neighbor Tool (NNT) [22], are built on top of the lower level libraries and serve to relieve the programmer of handling many of the details of message passing programming. Performance optimizations can be added to these libraries that target specific machine architectures.…”

Section: /18mentioning

confidence: 99%

“…In addition to loop translations, array re-declarations, and other code modifications, the parallel version contains PPP generated calls to SMS library-based routines in the Nearest Neighbor Tool (NNT), Scalable Spectral Tool (SST) and Scalable Runtime System (SRS) shown in the Figure 1. NNT is a set of high-level library routines that address parallel coding issues such as data decomposition, halo region updates and loop translations [22]. SRS provides support for input and output of decomposed data [9].…”

Section: Overview Of Smsmentioning

confidence: 99%

The Scalable Modeling System: A High-Level Alternative to Mpi

Govett

Middlecoff

Hart

et al. 2001

Developments in Teracomputing

View full text Add to dashboard Cite

A directive-based parallelization tool called the Scalable Modeling System (SMS) is described. The user inserts directives in the form of comments into existing Fortran code. SMS translates the code and directives into a parallel version that runs efficiently on both shared and distributed memory high-performance computing platforms. SMS provides tools to support partial parallelization and debugging that significantly decreases code parallelization time. The performance of an SMS parallelized version of the Eta model is compared to the operational version running at the National Centers for Environmental Prediction (NCEP). ecmwf.doc submitted to World Scientific : 4/23/01 : 8:51 AM 2/18 forecasts in real-time using a 60km version of the Rapid Update Cycle (RUC) model. This was the first time anyone had produced operational forecasts in real time using a MPP class system. Since then, FSL has parallelized several weather and ocean models including the Global Forecast System (GFS) and the Typhoon Forecast System (TFS) for the Central Weather Bureau in Taiwan [15], the Rutgers University Regional Ocean Modeling System (ROMS) [8], the National Centers for Environmental Prediction (NCEP) 32 km Eta model [17], the high resolution limited area Quasi Non-hydrostatic (QNH) model [16], and FSL's 40 km Rapid Update Cycle (RUC) model currently running operationally at NCEP [2]. Central to FSL's success with MPPs has been the development of the Scalable Modeling System (SMS). SMS is directive-based parallelization tool that translates Fortran code into a parallel version that runs efficiently on both shared and distributed memory systems. SMS was designed to reduce the effort and time required to parallelize models targeted for MPPs, provide good performance, and allow models to be ported between systems without code change. Further, directive-based SMS parallelization requires no changes to the original serial code.

show abstract