分布式内存环境下的同步计算和数据负载平衡

M. F. Celiktug, M. O. Karsavuran, Seher Acer, C. Aykanat
{"title":"分布式内存环境下的同步计算和数据负载平衡","authors":"M. F. Celiktug, M. O. Karsavuran, Seher Acer, C. Aykanat","doi":"10.1137/22m1485772","DOIUrl":null,"url":null,"abstract":"Several successful partitioning models and methods have been proposed and used for computational load balancing of irregularly sparse applications in a distributed-memory setting. However, the literature lacks partitioning models and methods that encode both computational and data load balancing. In this article, we try to close this gap in the literature by proposing two hypergraph partitioning (HP) models which simultaneously encode computational and data load balancing. Both models utilize a two-constraint formulation, where the first constraint encodes the computational loads and the second constraint encodes the data loads. In the first model, we introduce explicit data vertices for encoding data load and we replicate those data vertices at each recursive bipartitioning (RB) step for encoding data replication. In the second model, we introduce a data weight distribution scheme for encoding data load and we update those weights at each RB step. The nice property of both proposed models is that they do not necessitate developing a new partitioner from scratch. Both models can easily be implemented by invoking any HP tool that supports multiconstraint partitioning as a two-way partitioner at each RB step. The validity of the proposed models are tested on two widely used irregularly sparse applications: parallel mesh simulations and parallel sparse matrix sparse matrix multiplication. Both proposed models achieve significant improvement over a baseline model.","PeriodicalId":21812,"journal":{"name":"SIAM J. Sci. Comput.","volume":"71 1","pages":"399-"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Simultaneous Computational and Data Load Balancing in Distributed-Memory Setting\",\"authors\":\"M. F. Celiktug, M. O. Karsavuran, Seher Acer, C. Aykanat\",\"doi\":\"10.1137/22m1485772\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Several successful partitioning models and methods have been proposed and used for computational load balancing of irregularly sparse applications in a distributed-memory setting. However, the literature lacks partitioning models and methods that encode both computational and data load balancing. In this article, we try to close this gap in the literature by proposing two hypergraph partitioning (HP) models which simultaneously encode computational and data load balancing. Both models utilize a two-constraint formulation, where the first constraint encodes the computational loads and the second constraint encodes the data loads. In the first model, we introduce explicit data vertices for encoding data load and we replicate those data vertices at each recursive bipartitioning (RB) step for encoding data replication. In the second model, we introduce a data weight distribution scheme for encoding data load and we update those weights at each RB step. The nice property of both proposed models is that they do not necessitate developing a new partitioner from scratch. Both models can easily be implemented by invoking any HP tool that supports multiconstraint partitioning as a two-way partitioner at each RB step. The validity of the proposed models are tested on two widely used irregularly sparse applications: parallel mesh simulations and parallel sparse matrix sparse matrix multiplication. Both proposed models achieve significant improvement over a baseline model.\",\"PeriodicalId\":21812,\"journal\":{\"name\":\"SIAM J. Sci. Comput.\",\"volume\":\"71 1\",\"pages\":\"399-\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SIAM J. Sci. Comput.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1137/22m1485772\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SIAM J. Sci. Comput.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1137/22m1485772","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

已经提出了几种成功的分区模型和方法,并将其用于分布式内存环境下不规则稀疏应用程序的计算负载平衡。然而,文献缺乏对计算和数据负载平衡进行编码的划分模型和方法。在本文中,我们试图通过提出两个同时编码计算和数据负载平衡的超图分区(HP)模型来缩小这一文献差距。这两个模型都使用双约束公式,其中第一个约束编码计算负载,第二个约束编码数据负载。在第一个模型中,我们引入了用于编码数据加载的显式数据顶点,并在每个递归双分区(RB)步骤中复制这些数据顶点,用于编码数据复制。在第二个模型中,我们引入了用于编码数据加载的数据权重分布方案,并在每个RB步骤更新这些权重。这两种模型的优点是它们不需要从头开始开发新的分区器。通过在每个RB步骤调用任何支持多约束分区的HP工具作为双向分区器,可以轻松实现这两个模型。通过并行网格模拟和并行稀疏矩阵稀疏矩阵乘法这两种广泛应用的不规则稀疏应用,验证了所提模型的有效性。两种提出的模型都比基线模型取得了显著的改进。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Simultaneous Computational and Data Load Balancing in Distributed-Memory Setting
Several successful partitioning models and methods have been proposed and used for computational load balancing of irregularly sparse applications in a distributed-memory setting. However, the literature lacks partitioning models and methods that encode both computational and data load balancing. In this article, we try to close this gap in the literature by proposing two hypergraph partitioning (HP) models which simultaneously encode computational and data load balancing. Both models utilize a two-constraint formulation, where the first constraint encodes the computational loads and the second constraint encodes the data loads. In the first model, we introduce explicit data vertices for encoding data load and we replicate those data vertices at each recursive bipartitioning (RB) step for encoding data replication. In the second model, we introduce a data weight distribution scheme for encoding data load and we update those weights at each RB step. The nice property of both proposed models is that they do not necessitate developing a new partitioner from scratch. Both models can easily be implemented by invoking any HP tool that supports multiconstraint partitioning as a two-way partitioner at each RB step. The validity of the proposed models are tested on two widely used irregularly sparse applications: parallel mesh simulations and parallel sparse matrix sparse matrix multiplication. Both proposed models achieve significant improvement over a baseline model.
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
期刊最新文献
An Operator-Splitting Optimization Approach for Phase-Field Simulation of Equilibrium Shapes of Crystals A Simple and Efficient Convex Optimization Based Bound-Preserving High Order Accurate Limiter for Cahn-Hilliard-Navier-Stokes System Almost Complete Analytical Integration in Galerkin Boundary Element Methods Sublinear Algorithms for Local Graph-Centrality Estimation Deterministic \(\boldsymbol{(\unicode{x00BD}+\varepsilon)}\) -Approximation for Submodular Maximization over a Matroid
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1