Parallel Processing in Eigenfunction-based Spatial Filtering Using MPI+OpenMP Hybrid Parallelization
-
摘要: 针对现有的特征函数空间滤值方法存在算法复杂、计算效率低下、难以满足海量空间数据应用需求等问题,提出一种特征函数空间滤值并行化方法。基于主从模型(master/slave模型)和MPI+OpenMP混合编程模式,充分挖掘多核集群下计算机的性能,并在多核集群平台上与纯MPI算法进行了对比实验。结果表明,基于MPI+OpenMP的方法能够获得更高的并行加速比和计算效率。Abstract: Based on the master/slave model,we present a hybrid MPI+OpenMP parallel implementation for the eigenfunction-base spatial filtering on the multi-core cluster.There are two different implementations of the algorithm: one based on MPI and the other based on a hybrid parallel paradigm with MPI+OpenMP.The experimental results show that MPI+OpenMP method can cut down the process-time effectively and improve the filtering efficiency.
-
Keywords:
- spatial filtering /
- eigenfunction /
- multi-core /
- cluster /
- parallel compute
-
-
[1] 马劲松沈婕,徐寿成,. 利用Douglas-Peucker并行算法在多核处理器上实时综合地图线要素[J]. 武汉大学学报(信息科学版). 2011(12)[2] 郭庆胜李留所,贾玉明,孙艳,. 顾及空间自相关的统计数据分级质量评价[J]. 武汉大学学报(信息科学版). 2006(03)[3] (美)TimothyG.Mattson,(美)BeverlyA.Sanders,(美)BernaL.Massingill著,敖富江译,. 并行编程模式[M]. 清华大学出版社, 2005[4] Arthur Getis. Screening for spatial dependence in regression analysis[J] 1990,Papers of the Regional Science Association(1):69～81
计量
- 文章访问数:
- HTML全文浏览量:
- PDF下载量:
下载:
