使用核外解算器的MoM高效并行方案

Yu Zhang, T. Sarkar, P. Ghosh, M. Taylor, A. De
{"title":"使用核外解算器的MoM高效并行方案","authors":"Yu Zhang, T. Sarkar, P. Ghosh, M. Taylor, A. De","doi":"10.1109/AEMC.2007.4638049","DOIUrl":null,"url":null,"abstract":"Currently, the problem size that can be solved in reasonable time using the method of moments (MoM) is limited by the amount of memory installed on the computer. This paper offers a new development which not only breaks this memory constraint, but also maintains the efficiency of running the problem in-core. In this paper, highly efficient parallel matrix filling schemes are presented for parallel in-core and parallel out-of-core method of moments (MoM) integral equation solvers with RWG basis functions. The parallel in-core solver uses RAM, which is often expensive and limited in size. The parallel out-of-core solver is introduced to extend the capability of MoM to solve larger problems which can be as large as the amount of storage on the hard disk. Numerical results on several typical computer platforms show that the parallel matrix filling schemes and matrix equation solvers introduced here are highly efficient and achieve theoretical predictions. The implementation of these advancements with the widely used RWG basis function creates a powerful tool for efficient computational electromagnetic solution of complex real world problems.","PeriodicalId":397229,"journal":{"name":"2007 IEEE Applied Electromagnetics Conference (AEMC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Highly efficient parallel schemes using out-of-core solver for MoM\",\"authors\":\"Yu Zhang, T. Sarkar, P. Ghosh, M. Taylor, A. De\",\"doi\":\"10.1109/AEMC.2007.4638049\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Currently, the problem size that can be solved in reasonable time using the method of moments (MoM) is limited by the amount of memory installed on the computer. This paper offers a new development which not only breaks this memory constraint, but also maintains the efficiency of running the problem in-core. In this paper, highly efficient parallel matrix filling schemes are presented for parallel in-core and parallel out-of-core method of moments (MoM) integral equation solvers with RWG basis functions. The parallel in-core solver uses RAM, which is often expensive and limited in size. The parallel out-of-core solver is introduced to extend the capability of MoM to solve larger problems which can be as large as the amount of storage on the hard disk. Numerical results on several typical computer platforms show that the parallel matrix filling schemes and matrix equation solvers introduced here are highly efficient and achieve theoretical predictions. The implementation of these advancements with the widely used RWG basis function creates a powerful tool for efficient computational electromagnetic solution of complex real world problems.\",\"PeriodicalId\":397229,\"journal\":{\"name\":\"2007 IEEE Applied Electromagnetics Conference (AEMC)\",\"volume\":\"59 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 IEEE Applied Electromagnetics Conference (AEMC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AEMC.2007.4638049\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE Applied Electromagnetics Conference (AEMC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AEMC.2007.4638049","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

目前,矩量法(MoM)在合理时间内所能求解的问题大小受到计算机内存量的限制。本文提供了一种新的发展,既打破了这种内存限制,又保持了问题在内核内运行的效率。本文提出了具有RWG基函数的并联核内和并联核外矩量法积分方程求解器的高效并行矩阵填充方案。并行核内求解器使用RAM,这通常是昂贵的和有限的大小。引入了并行的核外求解器来扩展MoM的能力,以解决更大的问题,可以像硬盘上的存储量一样大。在几个典型的计算机平台上的数值结果表明,本文所介绍的并行矩阵填充格式和矩阵方程求解器是高效的,并能实现理论预测。这些进步与广泛使用的RWG基函数的实现为复杂现实世界问题的有效计算电磁解决创造了一个强大的工具。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Highly efficient parallel schemes using out-of-core solver for MoM
Currently, the problem size that can be solved in reasonable time using the method of moments (MoM) is limited by the amount of memory installed on the computer. This paper offers a new development which not only breaks this memory constraint, but also maintains the efficiency of running the problem in-core. In this paper, highly efficient parallel matrix filling schemes are presented for parallel in-core and parallel out-of-core method of moments (MoM) integral equation solvers with RWG basis functions. The parallel in-core solver uses RAM, which is often expensive and limited in size. The parallel out-of-core solver is introduced to extend the capability of MoM to solve larger problems which can be as large as the amount of storage on the hard disk. Numerical results on several typical computer platforms show that the parallel matrix filling schemes and matrix equation solvers introduced here are highly efficient and achieve theoretical predictions. The implementation of these advancements with the widely used RWG basis function creates a powerful tool for efficient computational electromagnetic solution of complex real world problems.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信