Abstract
OLAP (On-Line Analytical Processing) is data and compute intensive application, how to improve the performance of OLAP are researchers always pursued goal. Aggregation is one of high frequently used operations which have a great impact on OLAP performance. Modern GPU (Graphic Process Units) have more raw computing power and higher memory bandwidth, so utilizing GPU accelerating aggregation computation is straight forward. But now GPU equipment does not supports float atomic operation and incremental memory allocation, so GPU algorithm need to be well-designed. In this paper, we discuss real-time aggregation in OLAP based on dense and sparse dataset, which fully utilize the high parallelism and high memory bandwidth and achieve performance improvements approximately 20X over CPU-based algorithms. On dense dataset, source data are chunked based on shared memory size, each thread block processes one chunk, each thread in block computes one cell in chunk cuboid. Algorithms adapts to GPU architecture and high parallelism which ensure high performance of algorithms. But on sparse dataset, there is a complex relationship between the compression dataset and the unknown size of result cuboid, it is impossible to define a straightforward parallelization. So we utilize sort, map and prefix sum primitive finishing source data partition, and reduction primitive aggregation data. At last, we introduce prototype system GPUOLAP (GPU-based OLAP) architecture which is under development now. Our work is a good attempt to real-time OLAP using new hardware.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
The BI Survey Analyzer, http://www.bi-survey.com/
Zhao, Y., Deshpande, P.M., Naughton, J.F.: An Array-based Algorithm for Simultaneous Multidimensional Aggregates. In: SIGMOD 1997, pp. 159–170. ACM Press, New York (1997)
Beyer, K., Ramakrishnan, R.: Bottom-up Computation of Sparse and Iceberg CUBEs. In: SIGMOD 1999, pp. 359–370. ACM Press, New York (1999)
Xin, D., Han, J.W., Li, X.L., Wah, B.W.: Star-Cubing: Computing Iceberg Cubes by Top-down and Bottom-up Integration. In: 29th International Conference on Very Large Data Bases, pp. 476–487. Morgan Kaufmann Publishers, San Francisco (2003)
Shao, Z., Han, J.W., Xin, D.: MM-Cubing: Computing Iceberg Cubes by Factorizing the Lattice Space. In: 16th International Conference on Scientific and Statistical Database Management, pp. 213–222. IEEE Computer Society, Washington (2004)
Hurtado, C.A., Mendelzon, A.O., Vaisman, A.A.: Maintaining Data Cubes Under dimension Updates. In: 15th International Conference on Data Engineering, pp. 346–355. IEEE Computer Society, Washington (1999)
Lee, K.Y., Kim, M.H.: Efficient Incremental Maintenance of Data Cubes. In: 32th International Conference on Very Large Data Bases, pp. 823–833. ACM Press, New York (2006)
Dehne, F., Eavis, T., Hambrusch, S., Rau-Chaplin, A.: Parallelizing the Data CUBE. Distributed and Parallel Databases 11(2), 181–201 (2002)
Dehne, F., Eavis, T., Rau-Chaplin, A.: Cluster Architecture for Parallel Data Warehousing. In: IEEE International Conference on Cluster Computing and the Grid, CCGrid 2001, Brisbane, Australia, pp. 161–168 (2001)
Ng, R., Wagner, A., Yin, Y.: Iceberg-cube Computation with PC Clusters. In: Proceedings of the 2001 ACM SIGMOD International Conference on Management of Data, SIGMOD 2001, pp. 25–36. ACM Press, California (2001)
Lakshmanan, L.V.S., Russakovsky, A., Sashikanth, V.: What-if OLAP Queries with Changing Dimensions. In: 24th International Conference on Data Engineering, pp. 1334–1336. IEEE Press, Cancun (2008)
Real-time OLAP, http://www.sia.com.br/rtolap.htm
Ailamaki, A., DeWitt, D.J., Hill, M.D.: Data Page Layouts for Relational Databases on Deep Memory Hierarchies. The VLDB Journal 11(3), 198–215 (2002)
OpenMP, http://www.openmp.org/
Bingsheng, H., Ke, Y., Rui, F.: Relational Joins on Graphics Processors. In: SIGMOD 2008, pp. 511–524. ACM Press, New York (2008)
Ma, W., Agrawal, G.: A Translation System for Enabling Data Mining Applications on GPUs. In: 23th International Conference on Supercomputing, pp. 400–409. ACM Press, New York (2009)
Programming Guide NVIDIA CUDA Compute Unified Device Architecture Version 2.0 (July 6, 2008)
Govindaraju, N., Gray, J., Kumar, R., Manocha, D.: GPUTeraSort: High Performance Graphics Coprocessor Sorting for Large Database Management. In: SIGMOD 2006, pp. 325–336. ACM Press, Chicago (2006)
CUDPP: CUDA Data Parallel Primitives Library, http://www.gpgpu.org/developer/cudpp/
Satish, N., Harris, M., Garland, M.: Designing Efficient Sorting Algorithms for Manycore GPUs. In: 23rd IEEE Intel Parallel & Distributed Processing Symposium. IEEE Press, Rome (2009)
Govindaraju, N.K., Raghuvanshi, N., Henson, M., Tuft, D., Manocha, D.: A Cache-Efficient Sorting Algorithm for Database and Data Mining Computations using Graphics Processors. Technical report, TR05-016 (2005)
Fang, W., Lu, M., Xiao, X., He, B., Luo, Q.: Frequent Itemset Mining on Graphics Processors. In: 5th International Workshop on Data Management on New Hardware, pp. 34–42. ACM Press, New York (2009)
He, B., Lu, M., Yang, K., Fang, R., Govindaraju, N.K., Luo, Q., Sander, P.V.: Relational Query Coprocessing on Graphics Processors. ACM Transaction, Database System, 1–39 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, G., Zhou, G. (2012). GPU-Based Aggregation of On-Line Analytical Processing. In: Zhao, M., Sha, J. (eds) Communications and Information Processing. Communications in Computer and Information Science, vol 288. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31965-5_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-31965-5_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31964-8
Online ISBN: 978-3-642-31965-5
eBook Packages: Computer ScienceComputer Science (R0)