Please wait a minute...
浙江大学学报(工学版)
J4  2009, Vol. 43 Issue (8): 1349-1360    DOI: 10.3785/j.issn.1008-973X.2009.
计算机科学技术     
图形处理器在数据库技术中的应用
杨珂1,罗琼2,石教英1
(1.浙江大学 CAD&CG国家重点实验室，浙江 杭州 310058； 2.香港科技大学 计算机科学与工程学系，香港)
Application of graphics processors to database technologies
 YANG Ke1, LUO Qiong2, SHI Jiao-Ying1
1. State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou 310058, China;
2. Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, China
 全文: PDF(2694 KB)   HTML
摘要：

综述了图形处理器上的通用计算（GPGPU）技术以及利用图形处理器（GPU）进行数据库处理的工作。将GPU技术的发展划分为固定功能架构、分离渲染架构和统一渲染架构3个时代，归纳了GPGPU技术的难点和现状。对于3个时代的GPU，分别论述其体系结构带来的机会与存在的局限，提出了相应的通用计算模型。综述了GPU用于数据库领域的相关研究，这些应用包括谓词、布尔组合和聚集、排序、连接、多维索引等。根据GPU技术的推动因素展望了GPGPU技术的趋势，归纳了GPU技术可以被利用的3个层面：图形流水线和通用并行计算、交互式多媒体、图形学理论与方法。以数据库技术为例展望了在每个层面上通用计算的趋势。
Abstract:

Surveyed general-purposed computing on GPUs (GPGPU) and using graphics processors (GPUs) on database processing. Divided GPU technology’s development into three periods, namely fixed functional, separated shader and unified shader. Summarized the difficulties and status quo of GPGPU. For each period, described the opportunities and limitations by the architecture, and provided the corresponding general computing model. Surveyed the applications in database area, including predicates, Boolean combination and aggregation, sort, join, multidimensional index etc. By analyzing the motivation factors of GPU technology, envisioned the trend of GPGPU technology, and summarized three layers upon which to utilize the GPU technology, namely graphics pipeline and general parallel computing, interactive multimedia, graphics theory and methods. Took database technology as example to envision the trend on each layer.
出版日期: 2009-09-28
:  TP 301.6  
基金资助:

国家“973”重点基础研究发展规划资助项目（2002CB312105）
通讯作者: 石教英，男，教授，博导, E-mail: jyshi@cad.zju.edu.cn     E-mail: yk.cadcg@gmail.com
作者简介: 杨珂（1981-），男，新疆和田人，博士生，主要从事数据库可视化与分析研究.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

杨珂, 罗琼, 石教英. 图形处理器在数据库技术中的应用[J]. J4, 2009, 43(8): 1349-1360.

YANG Ke, LUO Qiong, SHI Jiao-Ying. Application of graphics processors to database technologies. J4, 2009, 43(8): 1349-1360.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2009.    或    http://www.zjujournals.com/eng/CN/Y2009/V43/I8/1349

[1] OWENS J D, LUEBKE D, GOVINDARAJU N, et al. A survey of general-purpose computation on graphics hardware [J]. Computer Graphics Forum, 2007, 26(1): 80-113.
[2] 吴恩华. 图形处理器用于通用计算的技术、现状及其挑战[J]. 软件学报, 2004, 15(10): 1493-1504.
WU En-hua. State of the art and future challenge on general purpose computation by graphics processing unit [J]. Journal of Software, 2004, 15(10): 1493-1504.
[3] BUCK I. GeForce 8800 & NVIDIA CUDA [C]∥ Proceedings of Supercomputing 2006 Workshop “General-Purpose GPU Computing: Practice and Experience”. Tampa: Springer-Verlag, 2006: 44-54.
[4] RAMAKRISHNAN R, GEHRKE J. Database management systems [M]. 3rd ed. New York: McGraw-Hill, 2007.
[5] QIONG Luo. GPUQP [EB/OL]. [2007-03-12]. http:∥www.cse.ust.hk/gpuqp/.
[6] SUN C, AGRAWAL D, EL ABBADI A. Hardware acceleration for spatial selections and joins [C]∥ Proceedings of SIGMOD. San Diago: ACM, 2003: 455-466.
[7] BANDI N, SUN C, AGRAWAL D, et al. Hardware acceleration in commercial databases: a case study of spatial operations [C]∥ Proceedings of VLDB. Toronto: ACM, 2004: 590-601.
[8] GOVINDARAJU N, LLOYD B, WANG W, et al. Fast computation of database operations using graphics processors [C]∥ Proceedings of SIGMOD. San Diego: ACM, 2004: 215-226.
[9] GOVINDARAJU N, RAGHUVANSHI N, MANOCHA D. Fast and approximate stream mining of quantiles and frequencies using graphics processors [C]∥ Proceedings of SIGMOD. Baltimore: ACM, 2005: 611-622.
[10] GOVINDARAJU N, GRAY J, KUMAR R, et al. GPUTeraSort: high performance graphics coprocessor sorting for large database management [C]∥ Proceedings of SIGMOD. Chicago: ACM, 2006: 325-336.
[11] TARDITI D, PURI S, OGLESBY J. Accelerator: using data-parallelism to program GPUs for general-purpose uses [C]∥ Proceedings of ASPLOS. San Jose: ACM, 2006: 325-335.
[12] BUCK I, FOLEY T, HORN D, et al. Brook for GPUs: stream computing on graphics hardware [C]∥ Proceedings of SIGGRAPH. Los Angeles: ACM, 2004: 201-218.
[13] Rapidmind Inc. Sh [EB/OL]. [2005-04-21]. http:∥libsh.org.
[14] AMD stream processing SDK [EB/OL]. [2007-09-08]. http:∥ati.amd.com/products/streamprocessor/.
[15] NVIDIA CUDA (compute unified device architecture) [EB/OL].\[2006-12-09\].http:∥www.nvidia.com/object/cuda-home.html
[16] OpenMP API [EB/OL]. [2008-04-06]. http:∥www.openmp.org/.
[17] NVIDIA Corporation. CUDA \[EB/OL\].[2006-12-09]. http:∥developer.nvidia.com/object/cuda.html.
[18] GPGPU website [EB/OL]. [2001-03-02]. http:∥www.gpgpu.org/.
[19] YANG Ke, HE Bing-sheng, FANG Rui, et al. In-memory grid files on graphics processors [C]∥ Proceedings of SIGMOD DaMoN Workshop. Beijing: ACM, 2007: 45-53.
[20] HE Bing-sheng, YANG Ke, FANG Rui, et al. Relational joins on graphics processors [C]∥ Proceedings of SIGMOD. Vancouver: ACM, 2008: 321-331.
[21] FANG Rui, HE Bing-sheng, LU Mian, et al. GPUQP: query co-processing using graphics processors [C]∥ Proceedings of SIGMOD. Beijing: ACM, 2007: 1206-1211.
[22] BATCHER K E. Sorting networks and their applications [C]∥ Proceedings of AFIPS Spring Joint Computer Conference. Atlantic: AFIPS, 1968: 98-105.
[23] PURCELL T J, DONNER C, CAMMARANO M, et al. Photon mapping on programmable graphics hardware [C]∥ Proceedings of Graphics Hardware. San Diego: ACM, 2003: 41-50.
[24] HARRIS M. Introduction to CUDA [C]∥ Proceedings of SIGGRAPH 2007. GPGPU: General-Purpose Computation on Graphics Hardware. San Diego: ACM, 2007: 301-312.
[25] HENSLEY J. Close to the metal [C]∥ Proceedings of SIGGRAPH 2007. GPGPU: General-Purpose Computation on Graphics Hardware. San Diego: ACM, 2007: 120-130.
[26] HWU W M, KURT D. UIUC course tutorial [EB/OL] [2007-09-08]. http:∥courses.ece.uiuc.edu/ece498/al1/Syllabus.html.
[27] GAEDE V, GUNTHER O. Multidimensional access methods [J]. ACM Computing Surveys, 1998, 30(2): 170-231.
[28] YANG Ke, HE Bing-sheng, LUO Qiong, et al. Stack-based parallel recursion on graphics processors [C]∥ Proceedings of SIGPLAN Symposium on PPoPP. Dublin: ACM, 2009.
[29] LEFEBVRE S, HORNUS S, NEYRET F. Octree textures on the GPU [M]∥ GPU Gems 2. Redwood: Addison Wesley, 2005.
[30] HORN D, SUGERMAN J, HOUSTON M, et al. Interactive k-D tree GPU raytracing [C]∥ Proceedings of I3D. Seattle: ACM, 2007: 167-174.
[31] NIEVERGELT J, HINTERBERGER H, SEVCIK K C. The grid file: an adaptable, symmetric multikey file structure [J]. Transaction on Database Systems, 1984, 9(1): 38-71.
[32] SENGUPTA S, HARRIS M, ZHANG Y, et al. Scan primitives for GPU computing [C]∥ Proceedings of Graphics Hardware. San Diego: ACM, 2007: 154-165.
[33] Khronos Group. OpenCL overview [EB/OL]. [2008-12-10]. http:∥www.khronos.org/opencl/.
[34] SHALF J. The new landscape of parallel computer architecture [J]. Journal of Physics,doi:10.1088/1742-6596/78/1/012066, 2007.
[35] CAO F, TUNG A K H, ZHOU A Y. Scalable clustering using graphics processors [C]∥ Proceedings of WAIM. Hong Kong: [s.n.], 2006: 372-384.
[36] 杨珂,罗琼,石教英. 平行散点图:基于GPU的可视化分析方法[J]. 计算机辅助设计与图形学学报, 2008, 20(9): 12191228.
YANG-Ke, LUO Qiong, SHI Jiao-ying. Parallel scatterplots: visual analysis on graphics processors [J]. Journal of CAD&CG, 2008, 20(9): 12191228.
[37] GUTTMAN A. R-trees: a dynamic index structure for spatial searching [C]∥ Proceedings of SIGMOD. Boston: ACM, 1984: 47-54.
[38] JACOX E, SAMET H. Spatial join techniques [J]. Transaction on Database Systems, 2007, 32(1): 225-235.
[39] HAN Jia-wei, KAMBER M. Data mining: concepts and techniques [M]. 2nd ed. San Mateo: Morgan Kaufmann, 2006.
[40] YANG Ke, LI Yi-nan, LUO Qiong, et al. I3DC: interactive three-dimensional cubes, demo [C]∥ Proceedings of ICDE. Shanghai: IEEE, 2009.
[41] BABCOCK B, BABU S, DATAR M, et al. Models and issues in data stream systems [C]∥ Proceedings of SIGMOD. Madison: ACM, 2002: 67-78.
[42] KEIM D, KRIEGEL H P. VisDB: database exploration using multidimensional visualization [J]. IEEE Computer Graphics and Applications, 1994, 14(5): 40-49.
[43] SPENCE R. Information visualization [M]. 2nd ed. Upper Saddle River: Prentice-Hall (Pearson), 2007.
[44] AMMOURA A, ZAIANE O, GOEBEL R. Towards a novel OLAP interface for distributed data warehouses [C]∥ Proceedings of DaWaK. Munich: Springer- Verlag, 2001: 174-185.
[45] KEIM D, MANSMANN F, SCHINEIDEWIND J, et al. Challenges in visual data analysis [C]∥ Proceedings of Information Visualization. Baltimore: IEEE, 2006: 18-29.
[46] YANG Li. Interactive exploration of very large relational datasets through 3D dynamic projections [C]∥ Proceedings of SIGKDD. Boston: ACM, 2000: 236-243.
[47] FLOREK M, NOVOTN M. Interactive information visualization using graphics hardware, poster [C]∥ Proceedings of SCCG. Budmerice: [s.n.], 2006: 38-45.
[48] GOBRON S, MESTRE D. Information visualization of multi-dimensional cellular automata using GPU programming [C]∥ Proceedings of Information Visualization. Sacramento: IEEE, 2007: 33-39.
[49] KOSARA R, HAUSER H, GRESH D. An interaction view on information visualization [C]∥ Proceedings of Eurographics. Granada: ACM, 2003: 123-137.
[50] GUHA S, KRISHNAN S, VENKATASUBRAMANIAN S. Data visualization and mining using the GPU [C]∥ Proceedings of SIGKDD. [S.l.]: ACM, 2005: 1310-1319.
[51] 杨珂. 基于图形处理器的数据管理技术研究[D]. 杭州:浙江大学, 2008.
YANG Ke. GPU-based data management [D]. Hangzhou: Zhejiang University, 2008.
[52] 周昆. 数字几何处理:理论与应用[D]. 杭州: 浙江大学, 2002.
ZHOU Kun. Digital geometry processing: theory and applications [D]. Hangzhou: Zhejiang University, 2002.
[53] RAMAMOORTHI R, HANRAHAN P. A signal-processing framework for forward and inverse rendering [D]. Stanford: Stanford University, 2002.
[54] NG R, RAMAMOORTHI, HANRAHAN P. All-frequency shadows using non-linear wavelet lighting approximation [J]. Transactions on Graphics, 2003, 22(3): 376-381.
[55] DAS A, GEHRKE J, RIEDWALD M. Approximate join processing over data streams [C]∥ Proceedings of SIGMOD. San Diago: ACM, 2003: 40-51.
[56] SUN Xin, ZHOU Kun, CHEN Yan-yun, et al. Interactive relighting with dynamic BRDFs [C]∥ Proceedings of SIGGRAPH. San Diego: ACM, 2007: 145-167.
[57] FALOUTSOS C, KOLDA T G, SUN J. Mining large graphs and streams using matrix and tensor tools [C]∥ Proceedings of SIGMOD. Beijing: ACM, 2007: 325-333.
No related articles found!