OpenVX与三维渲染在多态GPU上的并行实现

doi:10.11772/j.issn.1001-9081.2015.01.0053

计算机应用 ›› 2015, Vol. 35 ›› Issue (1): 53-57.DOI: 10.11772/j.issn.1001-9081.2015.01.0053

OpenVX与三维渲染在多态GPU上的并行实现

延酉玫¹, 李涛², 王鹏博¹, 韩俊刚¹, 李雪丹², 姚静¹, 乔虹²

1. 西安邮电大学计算机学院, 西安710121;
2. 西安邮电大学电子工程学院, 西安710121

收稿日期:2014-07-23 修回日期:2014-09-17 出版日期:2015-01-01 发布日期:2015-01-26
通讯作者: 延酉玫
作者简介:延酉玫(1988-),女,青海西宁人,硕士研究生,主要研究方向:并行程序设计、计算机图形学;李涛(1954-),男,北京人,博士,CCF会员,主要研究方向:计算机体系结构、集成电路设计、计算机图形学硬件、系统软件、机器学习;王鹏博(1990-),男,陕西商洛人,硕士研究生,主要研究方向:并行程序设计.
基金资助:
国家自然科学基金重点项目(61136002).

Parallel implementation of OpenVX and 3D rendering on polymorphic graphics processing unit

YAN Youmei¹, LI Tao², WANG Pengbo¹, HAN Jungang¹, LI Xuedan², YAO Jing¹, QIAO Hong²

1. School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an Shaanxi 710121, China;
2. School of Electronic Engineering, Xi'an University of Posts and Telecommunications, Xi'an Shaanxi 710121, China

Received:2014-07-23 Revised:2014-09-17 Online:2015-01-01 Published:2015-01-26

摘要/Abstract

摘要：

针对图像处理与机器视觉以及三维图形渲染等所具有的大规模并行处理特征,通过充分利用面向图形图像处理的多态阵列架构(PAAG)处理器的可编程性以及灵活的并行处理方式,采用操作级并行与数据级并行相结合的并行化设计方法,实现了OpenVX中Kernel函数以及3D图形渲染.实验结果表明,在OpenVX标准图像处理Kernel函数以及图形渲染的并行实现中,采用PAAG处理器中的多指令多数据(MIMD)并行处理方式可以获得斜率为1的线性加速比,比传统图形处理器(GPU)中单指令多数据(SIMD)并行处理方式所得到的斜率值小于1的非线性加速比效率更高.

关键词: 多态阵列机, 仿真, OpenVX, 操作并行, 数据并行

Abstract:

For the image processing, computer vision and 3D rendering have the feature of massive parallel processing, the programmability and the flexible mode of parallel processing on the Polymorphic Array Architecture for Graphics (PAAG) platform were utilized adequately, the parallelism design method by combing the operation level parallelism with data level parallelism was used to implement the OpenVX Kernel functions and 3D rendering pipelines. The experimental results indicate that in the parallel implementation of image processing of OpenVX Kernel functions and graphics rendering, using Multiple Instruction Multiple Data (MIMD) of PAAG in parallel processing can obtain a linear speedup that the slope equals to 1, which achieves higher efficiency than the slope as nonlinear speedup that less than 1 of Single Instruction Multiple Data (SIMD) in traditional parallel processing of the Graphics Processing Unit (GPU).

Key words: polymorphic array processor, simulation, OpenVX, operation parallelism, data parallelism

中图分类号:

TP302
TP311

延酉玫, 李涛, 王鹏博, 韩俊刚, 李雪丹, 姚静, 乔虹. OpenVX与三维渲染在多态GPU上的并行实现[J]. 计算机应用, 2015, 35(1): 53-57.

YAN Youmei, LI Tao, WANG Pengbo, HAN Jungang, LI Xuedan, YAO Jing, QIAO Hong. Parallel implementation of OpenVX and 3D rendering on polymorphic graphics processing unit[J]. Journal of Computer Applications, 2015, 35(1): 53-57.

参考文献

[1] QIN G. Design and implementation of video acquisition and display system based on FPGA [D]. Hohhot: Inner Mongolia University, 2009.(青格日勒.基于FPGA的视频采集与显示系统的设计与实现[D].呼和浩特:内蒙古大学,2009.)
[2] ZHOU Y. Parallel computing research for image processing [D]. Chengdu: University of Electronic Science and Technology of China, 2006.(周益民.图像处理并行算法的研究[D].成都:电子科技大学,2006.)
[3] Khronos Group. The OpenVX provisional specification vision 1.0 [EB/OL]. [2014-04-28]. https://www.khronos.org/openvx.
[4] LI T, XIAO L. A thin-core array architecture for graphics and image processing [J]. Journal of Xi'an Institute of Posts and Telecommunications, 2012, 17(3): 41-47.(李涛,肖灵芝.面向图形和图像处理的轻核阵列机结构[J].西安邮电学院学报,2012,17(3):41-47.)
[5] LINDHOLM E, NICKOLLS J, OBERMAN S, et al. NVIDIA Tesla: a unified graphics and computing architecture [J]. IEEE Micro, 2008, 28(2): 39-55.
[6] LI T, XIAO L, HUANG H, et al. PAAG: a polymorphic array architecture for graphics and image processing [C]// PAAP'12: Proceedings of the 2012 Fifth International Symposium on Parallel Architectures, Algorithms and Programming. Washington, DC: IEEE Computer Society, 2012: 242-249.
[7] VEEN A H. Dataflow machine architecture [J]. ACM Computing Surveys, 1986, 18(4): 365-396.
[8] NIXON M. Feature extraction & image processing for computer vision [M]. 3rd ed. Amsterdam: Elsevier, 2012: 1-512.
[9] COMPTON K, HAUCK S. Reconfigurable computing: a survey of systems and software [J]. ACM Computing Surveys, 2002, 34(2): 171-210.
[10] BOYD C. Data-parallel computing [J]. Graphics, 2008, 6(2): 30-39.
[11] XIN D. A new method for image edge detection on CUDA [J]. Journal of Hangzhou Dianzi University, 2008, 28(5): 164-166.(辛大红.基于CUDA的图像边缘检测方法[J].杭州电子科技大学学报,2008,28(5):164-166.)
[12] FENG H. Implementation and performance of FFT and convolution in image filtering on GPU [J]. Computer Engineering and Applications, 2008, 44(2): 120-122.(冯煌.GPU图像处理的FFT和卷积算法及性能分析[J].计算机工程与应用,2008,44(2):120-122.)
[13] ZHANG N, CHEN Y, WANG J. Image parallel processing based on GPU [C]// ICACC 2010: Proceedings of the 2nd International Conference on Advanced Computer Control. Piscataway: IEEE, 2010: 367-370.
[14] PATEL H. GPU accelerated real time polarimetric image processing through the use of CUDA [C]// NAECON 2010: Proceedings of the IEEE 2010 National Aerospace and Electronics Conference. Piscataway: IEEE, 2010: 177-180.

[1]	李进, 王凤, 杨沈宇. 换电模式下电动车货运路径优化模型与算法[J]. 计算机应用, 2021, 41(6): 1792-1798.
[2]	李燕, 陈巧萍. 考虑非支持性评论的网络谣言传播模型[J]. 计算机应用, 2021, 41(4): 1128-1135.
[3]	王江坤, 何坤金, 曹红飞, 王金强, 张燕. 基于光滑粒子流体动力学方法的交互式水流加热仿真[J]. 计算机应用, 2020, 40(5): 1409-1414.
[4]	孙天齐, 胡建鹏, 黄娟, 樊莹. 云环境下Web应用带宽资源预测与管理[J]. 计算机应用, 2020, 40(1): 181-187.
[5]	黄东晋, 段思文, 雷雪, 梁景坤. 基于Voronoi图的群体队形控制方法[J]. 计算机应用, 2019, 39(6): 1799-1803.
[6]	张程, 陈付龙, 刘超, 齐学梅. 基于XML的信息物理融合系统组件建模与仿真[J]. 计算机应用, 2019, 39(6): 1842-1848.
[7]	李静, 刘冬实. 主动容错云存储系统的可靠性评价模型[J]. 计算机应用, 2018, 38(9): 2631-2636.
[8]	高钦泉, 黄伟萍, 杜民, 韦孟宇, 柯栋忠. 基于双目视觉的盆腔微创手术增强现实导航仿真系统的设计[J]. 计算机应用, 2018, 38(9): 2660-2665.
[9]	郑垚宇, 方洋旺, 魏贤智, 陈少华, 高翔, 王宏柯, 彭维仕. 基于云模型的仿真可信度评估方法[J]. 计算机应用, 2018, 38(6): 1535-1541.
[10]	王舰, 王志宏, 张乐君. 复杂网络演化的舆论动力学模型及仿真分析[J]. 计算机应用, 2018, 38(4): 1201-1206.
[11]	吴文燕, 姜鑫, 王晓锋, 刘渊. 虚拟化与数字仿真融合的多尺度网络复现技术[J]. 计算机应用, 2018, 38(3): 746-752.
[12]	张锐, 肖如良, 倪友聪, 杜欣. 逼真生成表格式数据的非时间属性关联模型[J]. 计算机应用, 2017, 37(9): 2684-2688.
[13]	张刚, 姜炜, 刘是枭. 非授权频段长期演进系统中的混合动态分簇算法[J]. 计算机应用, 2017, 37(8): 2145-2149.
[14]	李焱, 刘弘, 郑向伟. 折半聚类算法在基于社会力的人群疏散仿真中的应用[J]. 计算机应用, 2017, 37(5): 1491-1495.
[15]	彭行雄, 肖如良. 基于稳态过程的多重分形Web日志仿真生成算法[J]. 计算机应用, 2017, 37(2): 587-592.

OpenVX与三维渲染在多态GPU上的并行实现

Parallel implementation of OpenVX and 3D rendering on polymorphic graphics processing unit

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics