摘要
针对传统地图代数实现方法应用于海量栅格数据计算时效率低下的问题,在一种全新的GPU并行编程模型CUDA上,利用地图代数算子体现出来的基于栅格点集、处理流程相对固定、数据处理具有内在的并行性等特点,将传统的串行算法映射到GPU并行处理架构上,旨在从串行算法的并行化映射、计算机图形处理器资源的自适应参数调整等多角度来研究地图代数空间并行算法的实现机制,为空间分析算法的优化研究提供一种新的解决思路。
To improve the efficiency in traditional method of map algebra calculation for gigantic raster data,arithmetic operators characteristics are applied,including relatively fixed process flow and inherently parallel specialty,and a new GPU parallel programming model named CUDA is selectsed as technique supports.The realization mechanism surrounding parallel mapping of serial algorithms is discussed in adaptive parameter adjustments on computer graphic processor resources,thus providing a new solution for optimized research of spatial analytic algorithms.
出处
《桂林理工大学学报》
CAS
北大核心
2011年第1期139-143,共5页
Journal of Guilin University of Technology
基金
国家自然科学基金项目(41001225)
