Does A Fish Need a Bicycle? The Case for On-Chip NPUs in DBMS

Summary: Evaluates on-chip neural processing units (NPUs) as lightweight, low-latency alternatives to GPUs for in-DB ML tasks, avoiding host–device transfers and GPU cost/complexity. Shows NPUs excel for small-scale, latency-sensitive tasks such as learned indexes and ML-based operators. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 584
Venue: CIDR
Year: 2026
Pagerank: 5.093636e-05
Overall Rank: 10,130 | 30.50%
DOI: -

Incoming Non-self Citations Over Time

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

Authors

1. Alexander Baumstark (Technische Universit2t Ilmenau)
2. Kai-Uwe Sattler (Technische Universit2t Ilmenau)

BibTeX Citation

@inproceedings{baumstark_cidr26,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '26},
        title = {{Does A Fish Need a Bicycle? The Case for On-Chip NPUs in DBMS}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Baumstark, Alexander and Sattler, Kai-Uwe},
        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 14 of 14 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
43	The Case for Learned Index Structures	2018	SIGMOD	0.00046060254
378	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00019638121
2,355	QueryFormer: A Tree Transformer Model for Query Plan Representation	2022	VLDB	8.7022189e-05
2,823	Query Processing on Tensor Computation Runtimes	2022	VLDB	8.0893814e-05
2,888	AI Meets Database: AI4DB and DB4AI	2021	SIGMOD	7.9941489e-05
3,614	Cloudy with High Chance of DBMS: A 10-year Prediction for Enterprise-Grade ML	2020	CIDR	7.2568185e-05
3,874	Tensors: An abstraction for general data processing	2021	VLDB	7.0561161e-05
4,089	TCUDB: Accelerating Database with Tensor Processors	2022	SIGMOD	6.9096857e-05
4,434	LEON: A New Framework for ML-Aided Query Optimization	2023	VLDB	6.7079088e-05
4,643	Learned Index Benefits: Machine Learning Based Index Performance Estimation	2022	VLDB	6.5907466e-05
5,456	InferDB: In-Database Machine Learning Inference Using Indexes	2024	VLDB	6.2131252e-05
7,066	Aero: Adaptive Query Processing of ML Queries	2025	SIGMOD	5.712204e-05
7,757	CAMAL: Optimizing LSM-trees via Active Learning	2024	SIGMOD	5.5508469e-05
8,221	NeurDB: On the Design and Implementation of an AI-powered Autonomous Database	2025	CIDR	5.4640314e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	563	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB
2	4,089	TCUDB: Accelerating Database with Tensor Processors	2022	SIGMOD
3	2,679	Database Servers on Chip Multiprocessors: Limitations and Opportunities	2007	CIDR
4	13,432	Using Deep Learning Models to Replace Large Materialized Views in Relational Database	2021	CIDR
5	8,221	NeurDB: On the Design and Implementation of an AI-powered Autonomous Database	2025	CIDR
6	13,343	Database Perspective on LLM Inference Systems	2025	VLDB
7	2,823	Query Processing on Tensor Computation Runtimes	2022	VLDB
8	5,340	Machine Learning for Databases	2021	VLDB
9	10,041	DBMS Fitting: Why should we learn what we already know?	2020	CIDR
10	2,175	From Natural Language Processing to Neural Databases	2021	VLDB