A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc
International Journal of Advanced Computer Science and Applications(IJACSA), 5(12), 2014 As environmental models (such as Accelerated Climate Model for Energy (ACME), Parallel Reactive Flow and Transport Model (PFLOTRAN), Arctic Terrestrial Simulator (ATS), etc.) became more and more complicated, we...
Published in: | International Journal of Advanced Computer Science and Applications |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
The Science and Information (SAI) Organization
2014
|
Subjects: | |
Online Access: | https://doi.org/10.14569/IJACSA.2014.051203 |
id |
ftthesai:oai:thesai.org:10.14569/IJACSA.2014.051203 |
---|---|
record_format |
openpolar |
spelling |
ftthesai:oai:thesai.org:10.14569/IJACSA.2014.051203 2023-05-15T15:13:10+02:00 A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc D. Wang W. Wu F. Winkler W. Ding O. Hernandez 2014 https://doi.org/10.14569/IJACSA.2014.051203 eng eng The Science and Information (SAI) Organization OpenACC; Climate Modeling; Community Land Model; Functional Testing; Performance Analysis; Compiler-assisted Analysis text 2014 ftthesai https://doi.org/10.14569/IJACSA.2014.051203 2018-01-26T22:14:55Z International Journal of Advanced Computer Science and Applications(IJACSA), 5(12), 2014 As environmental models (such as Accelerated Climate Model for Energy (ACME), Parallel Reactive Flow and Transport Model (PFLOTRAN), Arctic Terrestrial Simulator (ATS), etc.) became more and more complicated, we are facing enormous challenges regarding to porting those applications onto hybrid computing architecture. OpenACC emerges as a very promising technology, therefore, we have conducted a feasibility analysis on porting the Community Land Model (CLM), a terrestrial ecosystem model within the Community Earth System Models (CESM)). Specifically, we used automatic function testing platform to extract a small computing kernel out of CLM, then we apply this kernel into the actually CLM dataflow procedure, and investigate the strategy of data parallelization and the benefit of data movement provided by current implementation of OpenACC. Even it is a non-intensive kernel, on a single 16-core computing node, the performance (based on the actual computation time using one GPU) of OpenACC implementation is 2.3 time faster than that of OpenMP implementation using single OpenMP thread, but it is 2.8 times slower than the performance of OpenMP implementation using 16 threads. On multiple nodes, MPI_OpenACC implementation demonstrated very good scalability on up to 128 GPUs on 128 computing nodes. This study also provides useful information for us to look into the potential benefits of “deep copy” capability and “routine” feature of OpenACC standards. We believe that our experience on the environmental model, CLM, can be beneficial to many other scientific research programs who are interested to porting their large scale scientific code using OpenACC onto high-end computers, empowered by hybrid computing architecture. http://thesai.org/Downloads/Volume5No12/Paper_3-A_Feasibility_Study_on_Porting_the_Community.pdf Text Arctic The Science and Information (SAI) Organization: Publications Arctic International Journal of Advanced Computer Science and Applications 5 12 |
institution |
Open Polar |
collection |
The Science and Information (SAI) Organization: Publications |
op_collection_id |
ftthesai |
language |
English |
topic |
OpenACC; Climate Modeling; Community Land Model; Functional Testing; Performance Analysis; Compiler-assisted Analysis |
spellingShingle |
OpenACC; Climate Modeling; Community Land Model; Functional Testing; Performance Analysis; Compiler-assisted Analysis D. Wang W. Wu F. Winkler W. Ding O. Hernandez A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc |
topic_facet |
OpenACC; Climate Modeling; Community Land Model; Functional Testing; Performance Analysis; Compiler-assisted Analysis |
description |
International Journal of Advanced Computer Science and Applications(IJACSA), 5(12), 2014 As environmental models (such as Accelerated Climate Model for Energy (ACME), Parallel Reactive Flow and Transport Model (PFLOTRAN), Arctic Terrestrial Simulator (ATS), etc.) became more and more complicated, we are facing enormous challenges regarding to porting those applications onto hybrid computing architecture. OpenACC emerges as a very promising technology, therefore, we have conducted a feasibility analysis on porting the Community Land Model (CLM), a terrestrial ecosystem model within the Community Earth System Models (CESM)). Specifically, we used automatic function testing platform to extract a small computing kernel out of CLM, then we apply this kernel into the actually CLM dataflow procedure, and investigate the strategy of data parallelization and the benefit of data movement provided by current implementation of OpenACC. Even it is a non-intensive kernel, on a single 16-core computing node, the performance (based on the actual computation time using one GPU) of OpenACC implementation is 2.3 time faster than that of OpenMP implementation using single OpenMP thread, but it is 2.8 times slower than the performance of OpenMP implementation using 16 threads. On multiple nodes, MPI_OpenACC implementation demonstrated very good scalability on up to 128 GPUs on 128 computing nodes. This study also provides useful information for us to look into the potential benefits of “deep copy” capability and “routine” feature of OpenACC standards. We believe that our experience on the environmental model, CLM, can be beneficial to many other scientific research programs who are interested to porting their large scale scientific code using OpenACC onto high-end computers, empowered by hybrid computing architecture. http://thesai.org/Downloads/Volume5No12/Paper_3-A_Feasibility_Study_on_Porting_the_Community.pdf |
format |
Text |
author |
D. Wang W. Wu F. Winkler W. Ding O. Hernandez |
author_facet |
D. Wang W. Wu F. Winkler W. Ding O. Hernandez |
author_sort |
D. Wang |
title |
A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc |
title_short |
A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc |
title_full |
A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc |
title_fullStr |
A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc |
title_full_unstemmed |
A Feasibility Study on Porting the Community Land Model onto Accelerators Using Openacc |
title_sort |
feasibility study on porting the community land model onto accelerators using openacc |
publisher |
The Science and Information (SAI) Organization |
publishDate |
2014 |
url |
https://doi.org/10.14569/IJACSA.2014.051203 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_doi |
https://doi.org/10.14569/IJACSA.2014.051203 |
container_title |
International Journal of Advanced Computer Science and Applications |
container_volume |
5 |
container_issue |
12 |
_version_ |
1766343758087979008 |