首页 | 本学科首页   官方微博 | 高级检索  
     

基于多核CPU+GPU运算的电磁场高效体绘制算法研究
引用本文:陈宇峰,张 铂,李 林.基于多核CPU+GPU运算的电磁场高效体绘制算法研究[J].计算机工程与应用,2018,54(18):218-222.
作者姓名:陈宇峰  张 铂  李 林
作者单位:北京理工大学 计算机学院,北京 100081
摘    要:雷达探测范围作为电磁场的一个典型代表,由于其在军事决策时扮演着重要的作用,所以对探测范围可视化的准确性和实时性的要求很严格。传统的面绘制三维数据场信息会造成大量的空间信息丢失。因此,采用体绘制技术来获取电磁场中的三维数据场信息。针对传统体绘制技术算法执行效率较低的问题,提出使用多核CPU+GPU的架构来加速体绘制,从而实现实时处理。实验表明,采用提出的方法可以大幅减少体绘制中光线绘制的时间,充分利用CPU的空闲存储资源和计算资源。

关 键 词:电磁场  体绘制  多核CPU+GPU  并行计算  

Research of high-efficient volume rendering algorithm for electromagnetic field based on multi-core CPU+GPU parallel computing
CHEN Yufeng,ZHANG Bo,LI Lin.Research of high-efficient volume rendering algorithm for electromagnetic field based on multi-core CPU+GPU parallel computing[J].Computer Engineering and Applications,2018,54(18):218-222.
Authors:CHEN Yufeng  ZHANG Bo  LI Lin
Affiliation:School of Computer Science, Beijing Institute of Technology, Beijing 100081, China
Abstract:As a typical representative of the electromagnetic field, the detection range of radar plays an important role in military decision making. So the requirement of the accuracy and real-time of the radar detection range is very strict. The traditional surface rendering of 3D data field will cause a lot of loss of spatial information. Therefore, the volume rendering technology is adopted to obtain three dimensional radar data field information. Aiming at the problem of low efficiency of traditional volume rendering algorithm, a multi-core CPU+GPU architecture is proposed to accelerate volume rendering, so as to realize real-time processing. The experimental results show that the proposed method can greatly reduce the time of ray rendering in volume rendering, and make full use of CPU’s free storage resources and computing resources.
Keywords:electromagnetic field  volume rendering  multi-core CPU+GPU  parallel computing  
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号