Optimizing Parallel Performance of Streamline Visualization for Large Distributed Flow Datasets
Optimizing Parallel Performance of Streamline Visualization for Large Distributed Flow Datasets
复制标题
DOI：
10.1109/pacificvis.2008.4475463
复制
发表时间：
2008-03
期刊：
影响因子：
--
通讯作者：
Li Chen;I. Fujishiro
中科院分区：
文献类型：
--
作者：
Li Chen;I. Fujishiro
并行性能一直是并行分布式存储计算机上大规模非结构化流动数据流水线可视化的一个具有挑战性的课题。它强烈地依赖于域分区。不合适的分区往往会导致域分区之间严重的负载不平衡和频繁的通信。为了解决这个问题，我们提出了一种考虑流向和特征的流数据划分方法。为了减少分布式域间的通信和同步开销，采用了多层谱图二分法。基于一种各向异性的局部扩散算子定义了相应邻接矩阵中的边权重，该算子赋予沿流方向的强耦合和垂直于流的弱耦合。同时，在分区时还考虑了种子点的分布和涡旋结构等流动特征，以获得良好的负载均衡。实验结果表明了该方法的可行性和有效性。
Parallel performance has been a challenging topic in streamline visualization for large unstructured flow datasets on parallel distributed-memory computers. It depends strongly on domain partitions. Unsuitable partitions often lead to severe load imbalance and high frequent communications among the domain partitions. To address the problem, we present an approach to flow data partitioning taking account of flow directions and features. Multilevel spectral graph bisection method is employed to reduce communication and synchronization overhead among distributed domains. Edge weights in the corresponding adjacent matrix is defined based on an anisotropic local diffusion operator which assigns strong coupling along flow direction and weak coupling orthogonal to flow. Meanwhile, the distributions of seed points and flow features such as vortex structure are also considered in partitioning so as to obtain good load balance. The experimental results are given to show the feasibility and effectiveness of our method.