基于GPU并行计算实现快速显微CT重构

来源 :核技术 | 被引量 : 3次 | 上传用户:ch3
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
图像处理器(GPU,graphics processing unit)是一种高度并行化的流式处理器,将其引入显微CT重构可大幅加快重构速度。将CT重建程序并行化设计,使用CUDA编程标准成功实现程序编写,在单块NVDIA GTX295的GPU上运行CT重建程序。结果表明,与CPU串行方法相比,使用GPU并行计算最高可得150倍左右的加速比,将重构时间缩短至15 min左右。因此可认为,GPU并行处理可显著提高显微CT重构速度,采用优化设计的GPU服务器还可进一步提高重构速度。
其他文献
Many real-world networks are demonstrated to either have layered network structures in themselves or interconnect with other networks,forming multilayer network
期刊
Wireless sensing is an excellent approach for remotely operated solar power system.Not only being able to get the sensor data,such as voltage,current,and temper
Smartphones and other connected devices rely on data services,such as Web Services (WS),Google Cloud Messaging (GCM) and Firebase Cloud Messaging (FCM),to share
期刊
The long awaited cloud computing concept is a reality now due to the transformation of computer generations.However,security challenges have become the biggest
股票指数期货是金融期货中产生最晚的一个类别。自1982年2月美国堪萨斯期货交易所上市交易以来,股票指数期货日益受到各类投资者的重视,交易规模迅速扩大,交易品种不断增加
This paper studies the performance of a submillimeter wave antenna operating between frequencies 0.1 THz and 10 THz with a 4-cyano-4-pentylbiphenyl [5CB] substa
20世纪90年代,Ogawa等[1]运用高场磁共振设备首次描述了鼠脑部血氧水平依赖(blood oxygen level dependent,BOLD)MR信号产生的机制.BOLD-MRI随即被广泛地应用于中枢神经功能
In the Vehicular Ad-hoc NETworks (VANET),the collection and dissemination of life-threatening traffic event information by vehicles are of utmost importance.How