| 基于CUDA的双三次B样条缩放方法 |
| |
| 引用本文： | 桂叶晨,冯前进,刘磊,陈武凡.基于CUDA的双三次B样条缩放方法[J].计算机工程与应用,2009,45(1):183-185. |
| |
| 作者姓名： | 桂叶晨 冯前进 刘磊 陈武凡 |
| |
| 作者单位： | 南方医科大学,生物医学工程学院,广州,510515 |
| |
| 摘 要： | Nvidia在GeForce 8系列显卡上推出的CUDA(统一计算设备架构)技术使GPU通用计算(GPGPU)从图形硬件流水线和高级绘制语言中解放出来,开发人员无须掌握图形学编程方法即可在单任务多数据模式(SIMD)下完成高性能并行计算。研究了CUDA的设计思想和编程方式,改进了基于双三次B样条曲面的图像缩放算法,使用多个线程将计算中耗时的B样条重采样部分改造成SIMD模式,并分别采用CUDA中全局存储器和共享存储器策略在CUDA上完成图像缩放的全过程。实验结果表明,基于CUDA的B样条曲面并行插值方法成功实现了硬件加速,相对于CPU上运行的B样条缩放算法,其执行效率明显提高,易于扩展,对于大规模数据处理呈现出良好的实时处理能力。
|
| 关 键 词： | 双三次B样条 统一计算设备架构(CUDA) 图形处理器(GPU) 图像缩放 重采样 |
| 收稿时间： | 2008-7-22 |
| 修稿时间： | 2008-9-27
|
Parellel bicubic B-spine interpolation algorithms for image zooming based on CUDA |
| |
| GUI Ye-chen,FENG Qian-jin,LIU Lei,CHEN Wu-fan.Parellel bicubic B-spine interpolation algorithms for image zooming based on CUDA[J].Computer Engineering and Applications,2009,45(1):183-185. |
| |
| Authors: | GUI Ye-chen FENG Qian-jin LIU Lei CHEN Wu-fan |
| |
| Affiliation: | GUI Ye-chen,FENG Qian-jin,LIU Lei,CHEN Wu-fan The Department of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China |
| |
| Abstract: | The new launch of CUDA(Compute Unified Device Architecture) technology by Nvidia has freed GPGPU(Computation on the Graphic Processing Unit) technology from the graphics fixed pipeline and high-level shader language,allowing the design and implementation of SIMD (Single Instruction,Multiple Data) parallel algorithms on a much more simple way than previous method based on texture rendering.In this paper,the core concept of CUDA is first studied,then bi-cubic B-spline algorithm for image zooming is redesigned... |
| |
| Keywords: | Bi-cubic B-spine Compute Unified Device Architecture（CUDA） Graphic Processing Unit（GPU） image zooming resampling |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 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 |
|
