Skip to main content
SpringerLink
Log in

Cooking DBMS Operations using Granular Primitives

An Overview on a Primitive-based RDBMS Query Evaluation

  • Schwerpunktbeitrag
  • Published:
Datenbank-Spektrum Aims and scope Submit manuscript

Abstract

The increasing heterogeneity of the underlying hardware forces modern database system engineers to implement multiple variants of a single database operator (e.g., join, selection). With increasing heterogeneity, these variants become too complex to maintain and tune for different devices. To overcome these disadvantages, developers use an alternative, primitive-based operator design. This design paradigm splits the database operators into granular functions or primitives and executes a given operator by combing the necessary primitives. Hence, we require only a limited set of these primitives as we reuse them for multiple database operations. Thus, tuning a single primitive improves efficiency of all the database operations using it.

In this survey, we provide an overview of a primitive-based database engine. First, we list different primitives from literature and place them in a hierarchy from the finest granular level to a complete database operator. Second, for each of primitive we list its possible tuning opportunities. Finally, we discuss the significance of primitive-based execution on the query engine. Overall, this survey aims to serve as a general reference for implementing a primitive-based query engine and possible strategies to tune it for specific processors.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Abadi DJ, Myers DS, DeWitt DJ, Madden S (2007) Materialization strategies in a column-oriented DBMS. Proceedings of the International Conference on Data Engineering (ICDE). IEEE, Istanbul, Turkey, pp 466–475

    Google Scholar 

  2. Albutiu MC, Kemper A, Neumann T (2012) Massively parallel sort-merge joins in main memory multi-core database systems. Proceedings VLDB Endowment 5(10):1064–1075

    Article  Google Scholar 

  3. Blelloch GE (1990a) Prefix sums and their applications

    Google Scholar 

  4. Blelloch GE (1990b) Vector models for data-parallel computing. MIT Press, Cambridge, MA, USA

    Google Scholar 

  5. Boncz PA, Kersten ML (1999) MIL primitives for querying a fragmented world. VLDB J 8(2):101–119

    Article  Google Scholar 

  6. Breß S (2014) The design and implementation of CoGaDB: a column-oriented GPU-accelerated DBMS. Datenbank Spektrum 14(3):199–209

    Article  Google Scholar 

  7. Breß S, Köcher B, Funke H, Rabl T, Markl V (2017) Generating custom code for efficient query execution on heterogeneous processors. Computing Research Repository (CoRR) abs/1709.00700

    Google Scholar 

  8. Broneske D, Breß S, Heimel M, Saake G (2014) Toward hardware-sensitive database operations. Proeedings of the International Conference on Extending Database Technology (EDBT), pp 1–6

    Google Scholar 

  9. Broneske D, Köppen V, Saake G, Schäler M (2017a) Accelerating multi-column selection predicates in main-memory – the Elf approach. In: Proceedings of the International Conference on Data Engineering (ICDE), pp 647–658

    Google Scholar 

  10. Broneske D, Meister A, Saake G (2017b) Hardware-sensitive scan operator variants for compiled selection pipelines. In: Datenbanksysteme für Business, Technologie und Web (BTW)

    Google Scholar 

  11. Diamos G, Wu H, Lele A, Wang J et al (2012) Efficient relational algebra algorithms and data structures for GPU. Tech. rep.. Georgia Institute of Technology, ‎Atlanta, Georgia‎

    Google Scholar 

  12. Govindaraju N, Raghuvanshi N, Henson M, Tuft D, Manocha D (2005) A cache-efficient sorting algorithm for database and data mining computations using graphics processors. Tech. rep.. University of North Carolina, Chapel Hill, NC, USA

    Google Scholar 

  13. Graefe G (1993) Query evaluation techniques for large databases. ACM Comput Surv 25(2):73–170

    Article  Google Scholar 

  14. He B, Yang K, Fang R, Lu M, Govindaraju N, Luo Q, Sander P (2008) Relational joins on graphics processors. Proceedings of the International Conference on Management of Data (SIGMOD). ACM, Vancouver, Canada, pp 511–524

    Google Scholar 

  15. He B, Lu M, Yang K, Fang R, Govindaraju NK, Luo Q, Sander PV (2009) Relational query coprocessing on graphics processors. ACM Trans Database Syst 34(4):1–21

    Article  Google Scholar 

  16. Heimel M, Saecker M, Pirk H, Manegold S, Markl V (2013) Hardware-oblivious parallelism for in-memory column-stores. Proceedings VLDB Endowment 6(9):709–720

    Article  Google Scholar 

  17. Hennessy JL, Patterson DA (2011) Computer architecture: a quantitative approach, 5th edn. Morgan Kaufmann Publishers Inc, San Francisco, CA, USA

    MATH  Google Scholar 

  18. Horn D (2005) Stream reduction operations for GPGPU applications. In: Pharr M (ed) GPU Gems, vol 2. Addison-Wesley, pp 573–589

  19. Kim C et al (2010) FAST: fast architecture sensitive tree search on modern CPUs and GPUs. Proceedings of the International Conference on Management of Data (SIGMOD). ACM, Indianapolis, Indiana, USA, pp 339–350

    Google Scholar 

  20. Knuth DE (1997) The art of computer programming: fundamental algorithms, vol 1, 3rd edn. Addison Wesley Longman Publishing Co., Inc., Redwood City, CA, USA

    MATH  Google Scholar 

  21. Neumann T (2011) Efficiently compiling efficient query plans for modern hardware. Proceedings VLDB Endowment 4(9):539–550

    Article  Google Scholar 

  22. Pantela S, Idreos S (2015) One loop does not fit all. Proceedings of the International Conference on Management of Data (SIGMOD). ACM, Melbourne, Australia, pp 2073–2074

    Google Scholar 

  23. Pirk H, Moll O, Zaharia M, Madden S (2016) Voodoo – A vector algebra for portable database performance on modern hardware. Proceedings VLDB Endowment 9(14):1707–1718

    Article  Google Scholar 

  24. Polychroniou O, Ross KA (2014) A comprehensive study of main-memory partitioning and its application to large-scale comparison- and radix-sort. Proceedings of the International Conference on Management of Data (SIGMOD), pp 755–766

    Google Scholar 

  25. Polychroniou O, Ross KA (2015) Efficient lightweight compression alongside fast scans. Proceedings of the International Workshop on Data Management on New Hardware (DaMoN).

    Book  Google Scholar 

  26. Polychroniou O, Raghavan A, Ross KA (2015) Rethinking simd vectorization for in-memory databases. Proceedings of the International Conference on Management of Data (SIGMOD), pp 1493–1508

    Google Scholar 

  27. Rao J, Ross K (2000) Making B+-Trees cache conscious in main memory. In: Proceedings of the International Conference on Management of Data (SIGMOD). ACM, Dallas, Texas, USA, pp 475–486

    Google Scholar 

  28. Rauhe H, Dees J, Sattler KU, Faerber F (2013) Multi-level parallel query execution framework for CPU and GPU. In: Proceedings of the European Conference on Advances in Databases and Information Systems (ADBIS). Springer, Genoa, Italy, pp 330–343

    Chapter  Google Scholar 

  29. Richter S, Alvarez V, Dittrich J (2015) A seven-dimensional analysis of hashing methods and its implications on query processing. Proceedings VLDB Endowment 9(3):96–107

    Article  Google Scholar 

  30. Rosenfeld V, Heimel M, Viebig C, Markl V (2015) The operator variant selection problem on heterogeneous hardware. Proceedings of the International Workshop on Accelerating Analytics and Data Management Systems Using Modern Processor and Storage Architectures (ADMS).

    Google Scholar 

  31. Ross KA (2004) Selection conditions in main memory. ACM Trans Database Syst 29(1):132–161

    Article  Google Scholar 

  32. Ross KA (2007) Efficient hash probes on modern processors. In: Proceedings of the International Conference on Data Engineering (ICDE), pp 1297–1301

    Google Scholar 

  33. Schuhknecht FM, Khanchandani P, Dittrich J (2015) On the surprising difficulty of simple things. Proceedings VLDB Endowment 8(9):934–937

    Article  Google Scholar 

  34. Sengupta S, Harris M, Zhang Y, Owens JD (2007) Scan primitives for GPU computing. In: Proceedings of the ACM Symposium on Graphics Hardware (SIGGRAPH). Eurographics Association, San Diego, California, pp 97–106

    Google Scholar 

  35. Sidler D, Owaida M, István Z, Kara K, Alonso G (2017) doppiodb: a hardware accelerated database. In: International Conference on Field Programmable Logic and Applications (FPL), pp 1–1

    Google Scholar 

  36. Sitaridi EA, Ross KA (2013) Optimizing select conditions on GPUs. Proceedings of the International Workshop on Data Management on New Hardware (DaMoN), pp 1–8

    Google Scholar 

  37. Willhalm T, Boshmaf Y, Plattner H, Popovici N, Zeier A, Schaffner J (2009) SIMD-scan: ultra fast in-memory table scan using on-chip vector processing units. Proceedings VLDB Endowment 2(1):385–394

    Article  Google Scholar 

  38. Willhalm T, Oukid I, Müller I, Faerber F (2013) Vectorizing database column scans with complex predicates. In: Proceedings of the International Workshop on Accelerating Analytics and Data Management Systems Using Modern Processor and Storage Architectures (ADMS), pp 1–12

    Google Scholar 

  39. Wu H, Diamos G, Cadambi S, Yalamanchili S (2012) Kernel weaver: automatically fusing database primitives for efficient GPU computation. In: Proceedings of the International Symposium on Microarchitecture (MICRO). IEEE, Vancouver, BC, Canada, pp 107–118

    Google Scholar 

  40. Zeuch S, Freytag J (2015) Selection on modern CPUs. Proceedings of the International Workshop on In-Memory Data Mangement and Analytics (IMDM), pp 1–8

    Google Scholar 

  41. Zeuch S, Freytag JC, Huber F (2014) Adapting tree structures for processing with SIMD instructions. In: Proceedings of the International Conference on Extending Database Technology (EDBT), pp 97–108

    Google Scholar 

Download references

Acknowledgements

This work was partially funded by the DFG (grant no.: SA 465/51-1 and PI 447/9)

Author information

Authors and Affiliations

  1. Otto-von-Guericke-University, Magdeburg, Germany

    Bala Gurumurthy, David Broneske, Tobias Drewes, Thilo Pionteck & Gunter Saake

Authors
  1. Bala Gurumurthy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. David Broneske
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tobias Drewes
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Thilo Pionteck
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Gunter Saake
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bala Gurumurthy.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gurumurthy, B., Broneske, D., Drewes, T. et al. Cooking DBMS Operations using Granular Primitives. Datenbank Spektrum 18, 183–193 (2018). https://doi.org/10.1007/s13222-018-0295-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13222-018-0295-8

Keywords

Search

Navigation