LLM-Augmented SQL Tuning Advisor for Heterogeneous Warehouses
Keywords:
SQL optimization, large language models, heterogeneous warehouses, cross-platform translation, query tuningAbstract
The objective of this article is to introduces a Large Language Model (LLM)-enhanced SQL Tuning Advisor for cross-platform SQL optimisation in Oracle, DB2, and SQL Server data warehousing systems. Transformer-based models automatically rewrite and semantically convert SQL queries across languages, improving syntax and execution logic for each platform with the average query length may be cut by 35% in real-world testing which means performance has increased and workloads are easier to move.
Downloads
References
S. Chaudhuri and V. Narasayya, “An Efficient Cost-Driven Index Selection Tool for Microsoft SQL Server,” in Proceedings of the 23rd International Conference on Very Large Data Bases, 1997, pp. 146–155.
G. Graefe, “Query Evaluation Techniques for Large Databases,” ACM Computing Surveys, vol. 25, no. 2, pp. 73–170, Jun. 1993.
M. Stonebraker et al., “C-Store: A Column-oriented DBMS,” in Proceedings of the 31st International Conference on Very Large Data Bases, 2005, pp. 553–564.
C. Curino, E. P. C. Jones, Y. Zhang, and S. Madden, “Relational Cloud: A Database Service for the Cloud,” IEEE Data Eng. Bull., vol. 35, no. 1, pp. 3–8, Mar. 2012.
A. Pavlo et al., “A Comparison of Approaches to Large-Scale Data Analysis,” in Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data, 2009, pp. 165–178.
L. Wang et al., “Adaptive SQL Query Tuning for Heterogeneous Database Systems,” IEEE Trans. Knowl. Data Eng., vol. 32, no. 5, pp. 843–857, May 2020.
J. F. Naughton et al., “The Case for Language-Model Based Code Understanding in Database Systems,” Proceedings of the VLDB Endowment, vol. 15, no. 12, pp. 3357–3360, Aug. 2022.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proceedings of NAACL-HLT, 2019, pp. 4171–4186.
T. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems (NeurIPS), 2020.
A. Radford et al., “Language Models are Unsupervised Multitask Learners,” OpenAI, 2019.
R. Zhang et al., “Deep Learning for Query Optimization: A Survey,” ACM Computing Surveys, vol. 54, no. 7, pp. 1–37, Sep. 2021.
Y. Shen et al., “A Survey on Neural Code Generation,” IEEE Transactions on Software Engineering, vol. 48, no. 7, pp. 2183–2208, Jul. 2022.
K. Kundu et al., “Cross-Database Query Translation: A Survey,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 11, pp. 5336–5355, Nov. 2022.
A. Marcus et al., “Neo: A Learned Query Optimizer,” in Proceedings of the VLDB Endowment, vol. 12, no. 11, pp. 1705–1718, 2019.
P. Bailis et al., “The Future of Database Systems: From Human-Designed to Learned,” Communications of the ACM, vol. 64, no. 9, pp. 46–55, Sep. 2021.
M. Krishnan and S. Madden, “Learning to Optimize Joins with Deep Reinforcement Learning,” Proceedings of the VLDB Endowment, vol. 12, no. 11, pp. 1705–1718, 2019.
L. Gong et al., “Automated SQL Query Optimization using Transformer Models,” in IEEE International Conference on Data Engineering (ICDE), 2023, pp. 1562–1573.
M. Zhu et al., “SQL Translation and Optimization for Heterogeneous Data Warehouses,” Information Systems, vol. 105, pp. 101667, 2022.
J. G. Simmons and B. W. Lohr, “Techniques for Query Plan Generation in DB2,” IBM Journal of Research and Development, vol. 41, no. 3, pp. 271–280, May 1997.
H. J. Moon et al., “Oracle Database SQL Tuning Advisor: A Comprehensive Overview,” ACM SIGMOD Record, vol. 44, no. 3, pp. 39–45, Sep. 2015.
