摘要
提出一种基于GPU的恒星检索并行算法,解决大视场下星表检索在仿真应用中效率不高的问题。首先使用经纬度分区法将星表划分为星区存储,然后在可快速查询的分区星表上,提出构造球面三角形法精确求出探测视场覆盖的星区,以有效减小搜索范围。最后,采用计算统一设备架构(CUDA)计算平台,将并行的视场内恒星检索过程放入GPU下进行并行加速。实验结果表明,与面向CPU的实现相比,所提算法获得数十倍的加速比,并且在大视场、宽星等域下将检索时间控制在毫秒级别,满足了实时仿真要求。
A GPU-based parallel star retrieval method is proposed to improve the efficiency of searching stars from star catalogue in computer simulation, especially when the Field of View （FOV） is large. By the novel algorithm, the stars in catalogue are classified and stored in different zones by using latitude and longitude zoned method firstly. Based on the easily accessible star catalogue, the star zones covered by the FOV can be computed exactly by constructing a spherical triangle around the FOV. As a result, the searching scope is reduced effectively. Finally, a CUDA computation platform is used to run the parallel process of star retrieving from those star zones on GPU. Experimental resnhs show that, in comparison with CPU-oriented implementation, the proposed algorithm achieves up to decades times speedup, and the processing time is limited within a millisecond level in large FOV and wide star magnitude domain. It meets the requirement of real-time simulation.
出处
《宇航学报》
EI
CAS
CSCD
北大核心
2012年第5期584-589,共6页
Journal of Astronautics
基金
国家"863"高技术研究发展计划(2009AA01Z303)
关键词
通用处理机
星表检索
CUDA
并行加速
分区法
GPU
Star catalogue retrieval
CUDA
Parallel acceleration
Partition method
