Performance Optimization of DRR Algorithm Based on CUDA
CUDA (Compute Unified Device Architecture ) is a development platform for general purpose parallel calculation, which developed by NVIDIA Corporation, that enables dramatic increases in computing performance by harnessing the power of the GPU (Graphics Processing Unit), particularly parallel computing of intensive data, performance optimization js more apparent With millions of CUDA-enabled GPUs sold to date, software developers, scientists and researchers are fmding broad-ranging uses for CUDA, including image and video processing, computational biology and chemistry, fluid dynamics simulation, CT image reconstruction, seismic, analysis, ray tracing, etc. This paper designs and implements the DRR (Digitally Reconstructed Radiograph) parallel algorithm on CUDA platform based on ray tracing parallelism method of the DRR. After CUDA optimization, the algorithm realizes interactive digital image reconstruction. Different resolution image is reconstructed with GPU and CPU respectively, speed performance can ascend to about 7-40 times, and image quality is good.
CUDA GPU DRR ray tracing
Detian Sun
School of Information Science and Engineering Shenyang Ligong University Shenyang, P.R. China
国际会议
重庆
英文
1003-1006
2011-08-20（万方平台首次上网日期，不代表论文的发表时间）