摘要
为解决SART迭代重建算法计算耗时的问题,在单GPU基础上,利用多块GPU的并行计算能力,提出了一种多GPU加速迭代重建算法。实验结果表明,与CPU重建相比,在不影响重建图像质量的情况下,采用GPU重建速度有明显提高,且增加GPU数量可以进一步提高重建速度。
In order to solve the problem that the simultaneous algebraic reconstruction technique is very time-consuming,this paper proposes a multi-GPU parallel acceleration method on the basis of single-GPU-accelerated reconstruction.The experimental result shows that compared with the CPU reconstruction speed,the muti-GPU reconstruction speed improves significantly,while the precision of reconstructed images keeps the same,and the reconstruction speed can be further improved by increasing the number of GPUs.This method is of a higher value in engineering.
出处
《强激光与粒子束》
EI
CAS
CSCD
北大核心
2013年第9期2418-2422,共5页
High Power Laser and Particle Beams
基金
中国工程物理研究院应用电子学研究所自研课题(2012CXZY01)
关键词
计算机断层成像
统一计算机架构
SART
多GPU
computer tomography
computer unified device architecture
simultaneous algebraic reconstruction technique
multi GPU
