[1]杜松江,张思超.采用GPU的提升纹理缓存命中光线投射方法[J].华侨大学学报(自然科学版),2016,37(5):627-632.[doi:10.11830/ISSN.1000-5013.201605020]
　DU Songjiang,ZHANG Sichao.Improving Texture Cache-Hit Rate of GPU-Based Ray Casting[J].Journal of Huaqiao University(Natural Science),2016,37(5):627-632.[doi:10.11830/ISSN.1000-5013.201605020]
点击复制

采用GPU的提升纹理缓存命中光线投射方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第37卷
期数:
2016年第5期
页码:
627-632
栏目:
出版日期:
2016-09-20

文章信息/Info

Title:
Improving Texture Cache-Hit Rate of GPU-Based Ray Casting
文章编号:
1000-5013(2016)05-0627-06
作者:
杜松江1;  张思超2
1. 长江大学工程技术学院 信息工程学院, 湖北 荆州 434020;2. 中国矿业大学 机电工程学院, 江苏 徐州 221116
Author(s):
DU Songjiang1;  ZHANG Sichao2
1. College of Information Engineering, Yangtze University College of Engineering Technology, Jingzhou 434020, China; 2. School of Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou 221116, China
关键词:
三维纹理;  光线投射;  图形处理单元;  纹理缓存
Keywords:
3D texture;  ray casting;  graphics processing unit;  texture cache
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201605020
文献标志码:
A
摘要:
提出一种改善纹理缓存命中率的方法.首先,分析图形处理器(GPU)中三维纹理组织的布局特性;进而提出根据视点的变化动态选择线程配置的策略,目的在于最小化warp级的投射光线纹理访存跨距;最后,算法用CUDA(compute unified device architecture)实现并验证.实验结果表明:当视点分别围绕x,y,z坐标轴旋转时,改进后算法的帧速率分别为改进前的1.08,1.14,0.98倍.
Abstract:
This paper presents a method of improving the texture cache hitrate for GPU-based volume rendering. Firstly, we analyze the data layout of 3D texture in GPU. Based on it, a dynamic strategy of selecting the thread block shape according to the viewpoint is proposed. The strategy can minimize the access stride for the warp-level threads. Finally, we realize the method in CUDA(compute unified device architecture)and testify the effectiveness. The experimental results show that when the viewpoint rotates around the x-, y-, z- axis, the frame rates are 1.08, 1.14 and 0.98 time faster than that of static thread block shape configuration, respectively.

参考文献/References:

[1] KRUGER J,WESTERMANN R.Acceleration techniques for GPU-based volume rendering[C]//Proceedings of the 14th IEEE Visualization.Washington D C:IEEE Computer Society,2003:287-292.
[2] SALAMA C R,KELLER M,KOHLMANN P.High-level user interfaces for transfer function design with semantics[J].Visualization and Computer Graphics,2006,12(5):1021-1028.
[3] GOBBETTI E,MARTON F,GUITIáN J A I.A single-pass GPU ray casting framework for interactive out-of-core rendering of massive volumetric datasets[J].Visual Computer,2008,24(7/8/9):797-806.
[4] 李国和,段忠祥,吴卫江,等.针对全空子数据体的 GPU 体绘制[J].中国图象图形学报,2014.19(4):577-582.
[5] OWENS J D,HOUSTON M,LUEBKE D,et al.GPU computing[J].Proceedings of the IEEE,2008,96(5):879-899.
[6] MAR?áLEK L,HAUBER A,SLUSALLEK P.High-speed volume ray casting with CUDA[C]//IEEE Symposium on Interactive Ray Tracing.Los Angeles:CA Press,2008:185.
[7] ZHANG Changgong,XI Ping,ZHANG Chaoxin.CUDA-based volume ray-casting using cubic B-spline[C]//International Conference on Virtual Reality and Visualization.Beijing:IEEE Press,2011:84-88.
[8] 甘新标,沈立,王志英.基于CUDA的并行全搜索运动估计算法[J].计算机辅助设计与图形学学报,2010,22(3):457-460.
[9] 赵丽丽,张盛兵,张萌,等.基于CUDA的高速FFT计算[J].计算机应用研究,2011,28(4):155-159.
[10] 肖江,胡柯良,邓元勇.基于CUDA的矩阵乘法和FFT性能测试[J].计算机工程,2009,35(10):7-10.
[11] 王蓓蕾,朱志良,孟琭.基于CUDA加速的SIFT特征提取[J].东北大学学报(自然科学版),2013,34(2):200-204.
[12] JENKINS J,ARKAKAR I,OWENS J D,et al.Lessons learned from exploring the backtracking paradigm on the GPU[J].Lecture Notes in Computer Science,2011,6853(2):425-437.
[13] 周洪,樊晓桠,赵丽丽.基于CUDA的稀疏矩阵与矢量乘法的优化[J].计算机测量与控制,2010,18(8):1906-1908.
[14] SANDERS J,KANDROT E.CUDA by example:an introduction to general-purpose GPU programming[M].Boston:Addison-Wesley Professional,2010:116-117.
[15] MONTRYM J,MORETON H.The geforce 6800[J].IEEE Micro,2005(2):41-51.
[16] MORTON G M.A computer oriented geodetic data base and a new technique in file sequencing[M].New York:International Business Machines Company,1966:56-60.

备注/Memo

备注/Memo:
收稿日期: 2016-03-15
通信作者: 张思超(1973-),男,教授,博士,主要从事数据库应用、软件工程的研究.E-mail:dusongjiang2014@163.com.
基金项目: 国家自然科学基金资助项目(51204186)
更新日期/Last Update: 2016-09-20