Level set函数快速步进并行重构的分区优化  被引量:1

Optimized domain decomposition for parallel reconstruction of the Level set function by fast marching method

在线阅读下载全文

作  者:夏波[1] 黄筱云[1,2] 陈同庆 程永舟[1] 江诗群[1] XIA Bo;HUANG Xiaoyun;CHEN Tongqing;CHENG Yongzhou;JIANG Shiqun(School of Hydraulic Engineering,Changsha University of Science and Technology,Changsha 410114,China;State Key Laboratory of Coastal and offshore Engineering,Dalian University of Technology,Dalian 116024,China)

机构地区:[1]长沙理工大学水利工程学院,湖南长沙410114 [2]大连理工大学海岸和近海工程国家重点实验室,辽宁大连116024

出  处:《哈尔滨工程大学学报》2019年第9期1601-1607,共7页Journal of Harbin Engineering University

基  金:国家自然科学基金项目(51679015);中国博士后科学基金项目(2014M561230);大连理工大学海岸和近海工程国家重点实验室开放基金项目(LP1511)

摘  要:为进一步提升Level set函数重构的分区并行重构效率,本文采用均分交界面方式进行分区,并保证生成内边界重构节点数量最少。通过运用基于共享存储并行编程(OpenMP)多线程技术的并行计算模型,实现圆球、Zalesak球和哑铃等值面的并行重构。计算结果表明:新分区方法能平衡子区域间计算荷载,减少子区域间信息传递次数和节点回滚次数,与均分区域方法相比,新分区方法能够获得更高计算速度,具有更好的实用性和可扩展性。To further increase the domain-decomposition-based parallel efficiency of the reconstruction of level set function,A strategy based on equal partition of interface is introduced to keep same amount of reconstruction overhead among the subdomains and ensure the least number of reconstructed nodes at interior boundaries.Using a parallel computational model established by OpenMP,a multithreaded,shared-memory parallel programming technique,the isosurface reconstruction examples of sphere,Zalesak's sphere and dumbbell were enforced.Numerical calculation results show that new domain decomposition method can balance the workload of reconstruction among threads and decrease the amount of communication operations between subdomains and rollback operations of nodes.In contrast to the method with equipartition domain,the new domain decomposition method could obtain significant promotion of computational speed and possess better applicability and scalability.

关 键 词:LEVEL set函数 快速步进法 并行重构 分区优化 交界面 共享存储并行编程 多线程技术 加速比 

分 类 号:TV131.2[水利工程—水力学及河流动力学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象