模块化可视化环境中的数据并行与流水线处理技术

DATA PARALLELING AND PIPELINE PROCESSING IN THE MODULAR VISUALIZATION ENVIRONMENT

提高数据处理的规模与效率是模块化可视化环境目前需要解决的一个主要问题 .提出了基于数据分解与组合的模块间数据并行与流水线处理技术 ,同时进行了性能分析和数值实验 .结果表明 ,数据并行与流水线处理能够提高应用执行效率、减少存储需求 。

Eliminating the executing bottleneck of intensive computational modules and increasing the processing size of large datasets is the main problems for the modular visualization environment. In this paper, inter module data paralleling and pipeline processing are presented based on data decomposition and composition, and the result of performance analysis shows these techniques can help to solve the above problems.