基于GPU并行射线跟踪的电波预测算法研究  

Parallel Ray-tracing Algorithm of Radio-wave Propagation Prediction Based on GPU

作　　者：谭南[1] 陈辉[1] 

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《微计算机信息》2011年第11期104-106,共3页Control & Automation

基　　金：基金:基金申请人:谭南;项目名称:预测城市小区电磁波传播软件平台开发;基金颁发部门:广西壮族自治区教育厅(2010105950809M14)

摘　　要：针对利用射线跟踪算法进行小区电波预测的计算量非常大,运行时间较长,在实际工程中难以应用等的问题,本文在研究已有并行射线跟踪算法,即主从模式和对等模式并行射线跟踪的基础上,采用图形处理器(GPU)作为计算平台,结合GPU高并行处理能力,运用CUDA的编程框架,并在NVIDIA公司出厂的GEFORCE 9800GT上,实现了对城市小区的简单模型环境的电波预测。实验结果表明,基于GPU并行射线跟踪算法适用于城市小区的电波预测研究,该算法能大大节省通信时间,缩短计算时间,更方便更实用。Ray-tracing algorithm for predicting radio-wave propagation in urban microcell needs a great deal of computation time. In order to more widely using this algorithm, we need to solve these problems. In this paper, based on previous research of parallel ray-tracing, namely Master/Slaves Model （MSM） and Peer to Peer Model （PPM）, present a new method which combines with the capability for parallel processing of GPU, and uses CUDA programming framework. In GEFORCE 9800GT produced by NVIDIA, we conduct some experiments to forecast radio-wave propagation in simple city environment. The results show that this method in the paper which could save communication-time and computation-time is more convenient than that uses several computes.

关 键 词：电波传播预测 射线跟踪 并行算法 GPU CUDA编程框架 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]