Research on parallel algorithm of high-power microwave devices simulation based on MPI-3
Simulation of high-power microwave source devices generally uses parallel algorithms to speed up the operation. In recent years, with the upgrade of parallel technology, the parallel efficiency of the particle simulation software has been further improved. Existing MPI-2 parallel technology of parti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2022-07-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0094850 |
| _version_ | 1811320329900916736 |
|---|---|
| author | Yulan Hu Dagang Liu Laqun Liu Huihui Wang Qiang Li |
| author_facet | Yulan Hu Dagang Liu Laqun Liu Huihui Wang Qiang Li |
| author_sort | Yulan Hu |
| collection | DOAJ |
| description | Simulation of high-power microwave source devices generally uses parallel algorithms to speed up the operation. In recent years, with the upgrade of parallel technology, the parallel efficiency of the particle simulation software has been further improved. Existing MPI-2 parallel technology of particle simulation software CHIPIC realizes the access to the local memory space of other processes through message passing. The new version of the MPI-3 standard provides the shared memory feature, which allows the data to be directly called by each process in the shared memory window, which reduces the information transmission. In this paper, based on the shared memory feature of MPI-3, the electromagnetic particle simulation parallel algorithm and dynamic load balancing algorithm are designed in the particle simulation software. The implementation of the two algorithms can improve the parallel efficiency from different aspects. The RKA and magnetic isolation oscillator high-power microwave devices are used as the test models. The test results show that the electromagnetic particle simulation parallel algorithm based on the shared memory feature of MPI-3 can improve the efficiency of the software by up to 44%. The efficiency of the dynamic load balancing algorithm based on MPI-3 can also be improved by up to 38%. |
| first_indexed | 2024-04-13T12:57:43Z |
| format | Article |
| id | doaj.art-8288138f44ff4d3193b84a5ae11cfcfb |
| institution | Directory Open Access Journal |
| issn | 2158-3226 |
| language | English |
| last_indexed | 2024-04-13T12:57:43Z |
| publishDate | 2022-07-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj.art-8288138f44ff4d3193b84a5ae11cfcfb2022-12-22T02:46:00ZengAIP Publishing LLCAIP Advances2158-32262022-07-01127075313075313-810.1063/5.0094850Research on parallel algorithm of high-power microwave devices simulation based on MPI-3Yulan Hu0Dagang Liu1Laqun Liu2Huihui Wang3Qiang Li4School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSimulation of high-power microwave source devices generally uses parallel algorithms to speed up the operation. In recent years, with the upgrade of parallel technology, the parallel efficiency of the particle simulation software has been further improved. Existing MPI-2 parallel technology of particle simulation software CHIPIC realizes the access to the local memory space of other processes through message passing. The new version of the MPI-3 standard provides the shared memory feature, which allows the data to be directly called by each process in the shared memory window, which reduces the information transmission. In this paper, based on the shared memory feature of MPI-3, the electromagnetic particle simulation parallel algorithm and dynamic load balancing algorithm are designed in the particle simulation software. The implementation of the two algorithms can improve the parallel efficiency from different aspects. The RKA and magnetic isolation oscillator high-power microwave devices are used as the test models. The test results show that the electromagnetic particle simulation parallel algorithm based on the shared memory feature of MPI-3 can improve the efficiency of the software by up to 44%. The efficiency of the dynamic load balancing algorithm based on MPI-3 can also be improved by up to 38%.http://dx.doi.org/10.1063/5.0094850 |
| spellingShingle | Yulan Hu Dagang Liu Laqun Liu Huihui Wang Qiang Li Research on parallel algorithm of high-power microwave devices simulation based on MPI-3 AIP Advances |
| title | Research on parallel algorithm of high-power microwave devices simulation based on MPI-3 |
| title_full | Research on parallel algorithm of high-power microwave devices simulation based on MPI-3 |
| title_fullStr | Research on parallel algorithm of high-power microwave devices simulation based on MPI-3 |
| title_full_unstemmed | Research on parallel algorithm of high-power microwave devices simulation based on MPI-3 |
| title_short | Research on parallel algorithm of high-power microwave devices simulation based on MPI-3 |
| title_sort | research on parallel algorithm of high power microwave devices simulation based on mpi 3 |
| url | http://dx.doi.org/10.1063/5.0094850 |
| work_keys_str_mv | AT yulanhu researchonparallelalgorithmofhighpowermicrowavedevicessimulationbasedonmpi3 AT dagangliu researchonparallelalgorithmofhighpowermicrowavedevicessimulationbasedonmpi3 AT laqunliu researchonparallelalgorithmofhighpowermicrowavedevicessimulationbasedonmpi3 AT huihuiwang researchonparallelalgorithmofhighpowermicrowavedevicessimulationbasedonmpi3 AT qiangli researchonparallelalgorithmofhighpowermicrowavedevicessimulationbasedonmpi3 |