TQP++: Bridging ML Compilers and Analytical Query Processing on GPUs

Summary: TQP++ repurposes ML-compiler infrastructure for portable, high-performance GPU query processing across nine devices and three vendors. Tiered scheduling, map-reduce fusion, and runtime-adaptive execution deliver sub-second TPC-H SF100 without vendor-specific code. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID: h260431fdcf1f1276
Venue: VLDB
Year: 2026
Pagerank: 4.9605343e-05
Overall Rank: 10,993 | 26.32%
DOI: 10.14778/3827998.3828020
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Wei Cui (Microsoft)
2. Peng Cheng (Microsoft)
3. Carlo Curino (Microsoft)
4. Rathijit Sen (Microsoft)
5. Matteo Interlandi (Microsoft)

BibTeX Citation

@article{cui_vldb26,
        title = {{TQP++: Bridging ML Compilers and Analytical Query Processing on GPUs}},
        author = {Cui, Wei and Cheng, Peng and Curino, Carlo and Sen, Rathijit and Interlandi, Matteo},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {12},
        pages = {4116--4129},
        doi = {10.14778/3827998.3828020},
        url = {https://doi.org/10.14778/3827998.3828020},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 28 of 28 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
21	Efficiently Compiling Efficient Query Plans for Modern Hardware	2011	VLDB	0.00056737487
375	Umbra: A Disk-Based System with In-Memory Performance	2020	CIDR	0.00019660459
382	Apache Calcite: A Foundational Framework for Optimized Query Processing Over Heterogeneous Data Sources	2018	SIGMOD	0.0001946654
651	Amazon Redshift Re-invented	2022	SIGMOD	0.00015126716
748	The Yin and Yang of Processing Data Warehousing Queries on GPU Devices	2013	VLDB	0.00014258503
1,228	A Study of the Fundamental Performance Characteristics of GPUs and CPUs for Database Analytics	2020	SIGMOD	0.00011425748
1,687	POLARIS: The Distributed SQL Engine in Azure Synapse	2020	VLDB	9.8500167e-05
1,835	Data Management for Data Science: Towards Embedded Analytics	2020	CIDR	9.5293678e-05
2,199	Extending Relational Query Processing with ML Inference	2020	CIDR	8.8664379e-05
2,294	Pump Up the Volume: Processing Large Data on GPUs with Fast Interconnects	2020	SIGMOD	8.67775e-05
2,464	Query Processing on Tensor Computation Runtimes	2022	VLDB	8.4081954e-05
2,672	End-to-end Optimization of Machine Learning Prediction Queries	2022	SIGMOD	8.1301225e-05
3,471	Tile-based Lightweight Integer Compression in GPU	2022	SIGMOD	7.258594e-05
3,622	Triton Join: Efficiently Scaling to a Large Join State on GPUs with Fast Interconnects	2022	SIGMOD	7.1350619e-05
3,828	Orchestrating Data Placement and Query Execution in Heterogeneous CPU-GPU DBMS	2022	VLDB	6.9779559e-05
3,951	Deploying a Steered Query Optimizer in Production at Microsoft	2022	SIGMOD	6.8884038e-05
3,997	Designing an Open Framework for Query Optimization and Compilation	2022	VLDB	6.850379e-05
4,872	GOLAP: A GPU-in-Data-Path Architecture for High-Speed OLAP	2024	SIGMOD	6.3582628e-05
5,629	BOSS - An Architecture for Database Kernel Composition	2024	VLDB	6.0424626e-05
5,721	Efficiently Processing Joins and Grouped Aggregations on GPUs	2025	SIGMOD	6.0008904e-05
5,795	The Tensor Data Platform: Towards an AI-centric Database System	2023	CIDR	5.9755414e-05
6,003	Terabyte-Scale Analytics in the Blink of an Eye	2026	VLDB	5.9023799e-05
6,571	Maximus: A Modular Accelerated Query Engine for Data Analytics on Heterogeneous Systems	2025	SIGMOD	5.7278348e-05
6,685	Powerful GPUs or Fast Interconnects: Analyzing Relational Workloads on Modern GPUs	2025	VLDB	5.6936999e-05
7,470	Modularis: Modular Relational Analytics over Heterogeneous Distributed Platforms	2021	VLDB	5.5032592e-05
8,235	Rethinking Analytical Processing in the GPU Era	2026	CIDR	5.3569644e-05
10,063	Share the Tensor Tea: How Databases can Leverage the Machine Learning Ecosystem	2022	VLDB	5.0751118e-05
10,975	ZipFlow: a Compiler-based Framework to Unleash Compressed Data Movement for Modern GPUs	2026	VLDB	4.9605343e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	1,530	Pipelined Query Processing in Coprocessor Environments	2018	SIGMOD
2	8,007	Scaling GPU-Accelerated Databases beyond GPU Memory Size	2025	VLDB
3	10,479	A Backend-Agnostic Compiler for Approximate Query Processing with Probabilistic Tensor Algebra	2026	SIGMOD
4	2,808	GPL: A GPU-based Pipelined Query Processing Engine	2016	SIGMOD
5	7,200	GPUQP: Query Co-Processing Using Graphics Processors	2007	SIGMOD
6	10,063	Share the Tensor Tea: How Databases can Leverage the Machine Learning Ecosystem	2022	VLDB
7	10,794	Scalable GPU Acceleration of Scalar Functions in Analytical Databases: Compilation, Benchmarking, and Optimization	2026	VLDB
8	2,464	Query Processing on Tensor Computation Runtimes	2022	VLDB
9	10,673	TQEx: Tensor-based Query Engine Enhanced by Bridging the Gap	2026	SIGMOD
10	3,775	Hardware-conscious Query Processing in GPU-accelerated Analytical Engines	2019	CIDR