Input/Output analysis and optimization for GRAPES regional model
The new generation Global/Regional Assimilation and PreEdiction System(GRAPES) is a homegrown numerical weather prediction software developed by China Meteorological Administration(CMA). As the requirements for model resolution and prediction timeliness increase, the Input/Output(I/O) performance of...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | Chinese |
| Published: |
National Computer System Engineering Research Institute of China
2022-01-01
|
| Series: | Dianzi Jishu Yingyong |
| Subjects: | |
| Online Access: | http://www.chinaaet.com/article/3000145075 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839639536008691712 |
|---|---|
| author | Yang Bin Wang Jingyu Liu Weiguo Cai Huiyi Yu Fei Deng Liantang Huang Liping |
| author_facet | Yang Bin Wang Jingyu Liu Weiguo Cai Huiyi Yu Fei Deng Liantang Huang Liping |
| author_sort | Yang Bin |
| collection | DOAJ |
| description | The new generation Global/Regional Assimilation and PreEdiction System(GRAPES) is a homegrown numerical weather prediction software developed by China Meteorological Administration(CMA). As the requirements for model resolution and prediction timeliness increase, the Input/Output(I/O) performance of GRAPES becomes a critical performance bottleneck. This paper performs a deep analysis of I/O behavior for the GRAPES regional model，and proposes, designs and implements a high-performance I/O framework. This framework achieves a flexible and configurable output method through binary encoding and multiple I/O channels. At the same time, asynchronous I/O is included by non-blocking communication, which hides the I/O and communication overhead. The framework has been tested on the Sugon Pai supercomputer, and the results show that the framework can not only improve I/O performance by up to over ten times but also reduce the performance uncertainty caused by performance jitter. |
| format | Article |
| id | doaj-art-a4c2662ea3a44a4f8708a8b4638f3fd6 |
| institution | Matheson Library |
| issn | 0258-7998 |
| language | zho |
| publishDate | 2022-01-01 |
| publisher | National Computer System Engineering Research Institute of China |
| record_format | Article |
| series | Dianzi Jishu Yingyong |
| spelling | doaj-art-a4c2662ea3a44a4f8708a8b4638f3fd62025-07-04T08:18:48ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982022-01-01481394510.16157/j.issn.0258-7998.2124223000145075Input/Output analysis and optimization for GRAPES regional modelYang Bin0Wang Jingyu1Liu Weiguo2Cai Huiyi3Yu Fei4Deng Liantang5Huang Liping6School of Software，Shandong University，Jinan 250101，ChinaNational Research Center of Parallel Computer Engineering & Technology，Beijing 100086，ChinaSchool of Software，Shandong University，Jinan 250101，ChinaNational Supercomputing Center in Wuxi，Wuxi 214072，ChinaNumerical Weather Prediction Center of CMA，Beijing 100081，ChinaNumerical Weather Prediction Center of CMA，Beijing 100081，ChinaNumerical Weather Prediction Center of CMA，Beijing 100081，ChinaThe new generation Global/Regional Assimilation and PreEdiction System(GRAPES) is a homegrown numerical weather prediction software developed by China Meteorological Administration(CMA). As the requirements for model resolution and prediction timeliness increase, the Input/Output(I/O) performance of GRAPES becomes a critical performance bottleneck. This paper performs a deep analysis of I/O behavior for the GRAPES regional model，and proposes, designs and implements a high-performance I/O framework. This framework achieves a flexible and configurable output method through binary encoding and multiple I/O channels. At the same time, asynchronous I/O is included by non-blocking communication, which hides the I/O and communication overhead. The framework has been tested on the Sugon Pai supercomputer, and the results show that the framework can not only improve I/O performance by up to over ten times but also reduce the performance uncertainty caused by performance jitter.http://www.chinaaet.com/article/3000145075i/o optimizationasynchronous i/ograpescma-mesoregional model |
| spellingShingle | Yang Bin Wang Jingyu Liu Weiguo Cai Huiyi Yu Fei Deng Liantang Huang Liping Input/Output analysis and optimization for GRAPES regional model Dianzi Jishu Yingyong i/o optimization asynchronous i/o grapes cma-meso regional model |
| title | Input/Output analysis and optimization for GRAPES regional model |
| title_full | Input/Output analysis and optimization for GRAPES regional model |
| title_fullStr | Input/Output analysis and optimization for GRAPES regional model |
| title_full_unstemmed | Input/Output analysis and optimization for GRAPES regional model |
| title_short | Input/Output analysis and optimization for GRAPES regional model |
| title_sort | input output analysis and optimization for grapes regional model |
| topic | i/o optimization asynchronous i/o grapes cma-meso regional model |
| url | http://www.chinaaet.com/article/3000145075 |
| work_keys_str_mv | AT yangbin inputoutputanalysisandoptimizationforgrapesregionalmodel AT wangjingyu inputoutputanalysisandoptimizationforgrapesregionalmodel AT liuweiguo inputoutputanalysisandoptimizationforgrapesregionalmodel AT caihuiyi inputoutputanalysisandoptimizationforgrapesregionalmodel AT yufei inputoutputanalysisandoptimizationforgrapesregionalmodel AT dengliantang inputoutputanalysisandoptimizationforgrapesregionalmodel AT huangliping inputoutputanalysisandoptimizationforgrapesregionalmodel |