| 基于CUDA的阈值迭代算法并行实现 |
| |
| 作者姓名： | 耿旻明 蒋成龙 张冰尘 |
| |
| 作者单位： | 1. 中国科学院电子学研究所微波成像技术重点实验室, 北京 100190;2. 中国科学院大学, 北京 100190 |
| |
| 基金项目： | 国家973计划项目(2010CB731905)资助 |
| |
| 摘 要： | 利用CUDA编程在GPU平台设计并行实现阈值的迭代算法,并应用于稀疏微波成像. 仿真实验结果表明,在正确重建信号的前提下,相对于常规的CPU串行计算,采用GPU并行处理能加快运算,提高成像速度.
|
| 关 键 词： | 稀疏微波成像 阈值迭代算法 计算统一设备架构(CUDA) 并行处理 |
| 收稿时间： | 2012-06-15 |
| 修稿时间： | 2013-01-21 |
Parallel implementation of iterative shrinkage-thresholding algorithm via CUDA |
| |
| Authors: | GENG Min-Ming JIANG Cheng-Long ZHANG Bing-Chen |
| |
| Institution: | 1. National Key Laboratory of Microwave Imaging Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;2. University of Chinese Academy of Sciences, Beijing 100190, China |
| |
| Abstract: | We design and implement iterative shrinkage-thresholding algorithm (ISTA) on GPU via CUDA programming, and apply it in sparse microwave imaging. The simulation results show that, compared to CPU-based implementation, GPU-based implementation reconstructs correct signals at a faster computation speed. |
| |
| Keywords: | sparse microwave imaging iterative shrinkage-thresholding algorithm (ISTA) compute unified device architecture (CUDA) parallel processing |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
