Abstract
The hardware landscape is changing from homogeneous multi-core systems towards wildly heterogeneous systems combining different computing units, like CPUs and GPUs. To utilize these heterogeneous environments, database query execution has to adapt to cope with different architectures and computing behaviors. In this paper, we investigate the simple idea of partitioning an operator’s input data and processing all data partitions in parallel, one partition per computing unit. For heterogeneous systems, data has to be partitioned according to the performance of the computing units. We define a way to calculate the partition sizes, analyze the parallel execution exemplarily for two database operators, and present limitations that could hinder significant performance improvements. The findings in this paper can help system developers to assess the possibilities and limitations of intra-operator parallelism in heterogeneous environments, leading to more informed decisions if this approach is beneficial for a given workload and hardware environment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albutiu, M.-C., Kemper, A., Neumann, T.: Massively parallel sort-merge joins in main memory multi-core database systems. Proc. VLDB Endow. 5, 1064–1075 (2012)
Batcher, K.E.: Sorting networks and their applications. In: Proceedings of the April 30–May 2, 1968, Spring Joint Computer Conference, AFIPS 1968 (Spring), New York, USA (1968)
Boncz, P.A., Kersten, M.L., Manegold, S.: Breaking the memory wall in MonetDB. Commun. ACM 51(12), 77–85 (2008)
DeWitt, D.J., Gerber, R.H., Graefe, G., Heytens, M.L., Kumar, K.B., Muralikrishna, M.: GAMMA - a high performance dataflow database machine. In: Proceedings of VLDB (1986)
Esmaeilzadeh, H., Blem, E., Amant, R.S., Sankaralingam, K., Burger, D.: Dark silicon and the end of multicore scaling. In: ISCA, New York, USA. ACM (2011)
Heimel, M., Saecker, M., Pirk, H., Manegold, S., Markl, V.: Hardware-oblivious parallelism for in-memory column-stores. PVLDB 6, 709–720 (2013)
Huismann, I., Stiller, J., Froehlich, J.: Two-level parallelization of a fluid mechanics algorithm exploiting hardware heterogeneity. Comput. Fluids 117, 114–124 (2015)
Karnagel, T., Habich, D., Schlegel, B., Lehner, W.: Heterogeneity-aware operator placement in column-store DBMS. Datenbank-Spektrum 14, 211–221 (2014)
Mayr, T., Bonnet, P., Gehrke, J., Seshadri, P.: Query processing with heterogeneous resources. Technical Report, Cornell University, March 2000
Merrill, D.G., Grimshaw, A.S.: Revisiting sorting for GPGPU stream architectures. In: Proceedings of PACT 2010, New York, USA. ACM (2010)
Merry, B.: A performance comparison of sort and scan libraries for GPUs. Parallel Process. Lett. 25(04), 1550007 (2015)
Satish, N., Harris, M., Garland, M.: Designing efficient sorting algorithms for manycore GPUs. In: Proceedings of IPDPS 2009, Washington, DC, USA. IEEE Computer Society (2009)
Acknowledgments
This work is funded by the German Research Foundation (DFG) within the Cluster of Excellence “Center for Advancing Electronics Dresden”. Parts of the hardware were generously provided by Dresden GPU Center of Excellence.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Karnagel, T., Habich, D., Lehner, W. (2016). Limitations of Intra-operator Parallelism Using Heterogeneous Computing Resources. In: Pokorný, J., Ivanović, M., Thalheim, B., Šaloun, P. (eds) Advances in Databases and Information Systems. ADBIS 2016. Lecture Notes in Computer Science(), vol 9809. Springer, Cham. https://doi.org/10.1007/978-3-319-44039-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-44039-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44038-5
Online ISBN: 978-3-319-44039-2
eBook Packages: Computer ScienceComputer Science (R0)