Short Description
The server infrastructure includes a network of 29 powerful server systems of the company Supermicro with multi-core processors based on the x86-64 architecture for calculations and experimental setups in the field of database and algorithm research. The nodes are connected with 40Gbit/s Ethernet, 2x 56Gbit/s Infiniband (10 nodes) and 2x 200Gbit/s Infiniband (10 nodes), and can be used specifically for hardware-related programming and development with RDMA.
Systems with 96GB to 4TB RAM and 12 to 128 CPU cores are available. Furthermore, there are 3x NVIDIA L4 GPUs available. For the storage of research data, fast storage systems in RAID arrays with multiple redundancy and backups at different locations are available. A CI system supports the rapid development of research software.
The system is designed to fulfill different requirement profiles. Memory- and computationally intensive applications as well as distributed calculations can be performed on multiple nodes. In addition, applications and operating systems can be operated in isolation and can be abstracted using virtualization and containers.
For access to the server infrastructure, research computers based on the x86-64 architecture, equipped with various operating systems (Windows, Linux, MacOS) are available.
Contact Person
BEng. Dipl.-Ing. Dr. Daniel Kocher
Research Services
Systems and algorithms for processing data
Storing and querying large data
Similarity Queries
Spatio-temporal database systems
GIS enabled databases
Interconnected nodes with 2x56Gbit/s Infiniband (per computing node) resp. 2x200Gbit/s and 40Gbit/s ethernet technology
Direct Infiniband hardware access for RDMA-enabled software and services
Disaggregated memory technologies
Abstraction and Isolation of running systems using virtualization and container technologies
Database-as-a-service (DH-Infra Project)
Test and Development Infrastructure-as-a-service (DH-Infra Project)
Differential Privacy and other areas of cybersecurity
Methods & Expertise for Research Infrastructure
The research infrastructure is divided into two parts: A research infrastructure and a service infrastructure.
The research infrastructure is designed for research in the field of data engineering with the aim of solving efficiency problems in data processing. In this branch of research, new algorithms are developed, implemented, and empirically evaluated. The empirical evaluation requires precise runtime measurements, measurements of memory consumption, as well as network traffic. This usually requires exclusive and physical access (bare metal) to individual servers or a cluster of servers. The usage is characterized by frequently changing configurations to be able to run tests under different conditions.
The service infrastructure focuses on providing virtualized environment for database and infrastructure as service for the digital humanities in Salzburg and Austria. The design of the service infrastructure ensures that we can flexibly tailor the hardware and software setting to the needs of serviced projects (if physical access to individual servers is not required) while still providing high level of security.
The whole infrastructure is technically professionally administered and offers supporting services for the execution of experiments, e.g. versioned storage of experimental setups and large experimental data, E2EE for sensitive research data, fully automatic provisioning of cluster nodes, as well as databases for measurement results. Furthermore, the whole infrastructure operates without a queuing system (in this case, please refer to the core facility Salzburg Collaborative Computing). Researchers are supported and advised by the technical staff during the setup of their experiments. From a scientific point of view, there is a wealth of experience in the design and empirical evaluation of single-core, multi-core, parallel shared-nothing, and distributed algorithms.
Johannes Gutenberg University Mainz (JGU)
Technical University Munich
Celonis SE, Munich
Findologic GmbH, Salzburg
Salzburg Research GmbH
Universität Graz
Università di Verona
2025 – 2028
Assoz.-Prof. Martin Schäler, Univ. Prof. Frank Pallas, Univ. Prof. Dimitris Simos
DH Infra: Digital Humanities Infrastructure Austria
2023-2026
Assoz.-Prof. Martin Schäler, Univ. Prof. Christina Antenhofer
BMBF
DESQ - Declarative and Efficient Similarity Queries
2022 - 2026
Univ. Prof. Nikolaus Augsten
Fonds zur Förderung der wissenschaftlichen Forschung: FWF
https://dbresearch.uni-salzburg.at/projects/desq/index.php
SPRING – Scalable Process Mining
2021 – 2025
Univ. Prof. Nikolaus Augsten
Industry cooperation Celonis SE (Munich, Germany)
BOSS 1.0: Biblical Online Synopsis Salzburg 1.0
2021 - 2024
Univ. Prof. Nikolaus Augsten, Assoz.-Prof. Martin Schäler, Univ. Prof. Kristin De Troyer
Land Salzburg
https://dbresearch.uni-salzburg.at/projects/
Fast and Flexible Tree Edit Distance (FFTED) Projekt
2017-2021
Univ. Prof. Nikolaus Augsten
Fonds zur Förderung der wissenschaftlichen Forschung: FWF
https://ffted.dbresearch.uni-salzburg.at/
FWF Doctoral College GIScience
2015-2019
Nikolaus Augsten, Euro Beinat, Stefan Lang, Franz Neubauer, Anette Bartsch, Thomas Blaschke, Michael Leitner, Josef Strobl
Fonds zur Förderung der wissenschaftlichen Forschung: FWF
https://dk-giscience.zgis.net/
Synonyms for Search Engines
2018-2019
Univ. Prof. Nikolaus Augsten
Findologic GmbH, Österreichische Forschungsförderungsgesellschaft mbH
DH-Infra 2023-2026 Assoz.-Prof. Martin Schäler, BMBF
DESQ - Declarative and Efficient Similarity Queries
2022 - 2026
Univ. Prof. Dipl.-Ing. Nikolaus Augsten, PhD
Fonds zur Förderung der wissenschaftlichen Forschung: FWF
https://dbresearch.uni-salzburg.at/projects/desq/index.php
BOSS 1.0: Biblical Online Synopsis Salzburg 1.0
2021 - 2024
Univ. Prof. Nikolaus Augsten, Assoz.-Prof. Martin Schäler, Univ. Prof. Kristin De Troyer
Land Salzburg
https://dbresearch.uni-salzburg.at/projects/
Fast and Flexible Tree Edit Distance (FFTED) Projekt
2017-2021
Univ. Prof. Dipl.-Ing. Nikolaus Augsten, PhD
Fonds zur Förderung der wissenschaftlichen Forschung: FWF
https://ffted.dbresearch.uni-salzburg.at/
FWF Doctoral College GIScience
2015-2019
Nikolaus Augsten, Euro Beinat, Stefan Lang, Franz Neubauer, Anette Bartsch, Thomas Blaschke, Michael Leitner, Josef Strobl
Fonds zur Förderung der wissenschaftlichen Forschung: FWF
https://dk-giscience.zgis.net/
Synonyme für Suchmaschinen
2018-2019
Univ. Prof. Dipl.-Ing. Nikolaus Augsten, PhD
Findologic GmbH, Österreichische Forschungsförderungsgesellschaft mbH
Willi Mann (Celonis SE, Germany), Nikolaus Augsten (Univ. Salzburg), Christian S. Jensen (Aalborg Univ., Denmark), Mateusz Pawlik (Univ. Salzburg). SWOOP: Top-k Similarity Joins over Set Streams. VLDB Journal 34(1): 13, 2025. DOI: https://doi.org/10.1007/s00778-024-00880-x
Bianca Löhnert (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Cem Okulmus (Paderborn Univ, Germany), Magdalena Ortiz (TU Vienna, Austria). Query Rewriting for Nested Navigational Queries over Property Graphs. Int. Workshop on Description Logics, 2025. DOI: https://ceur-ws.org/Vol-4091/paper40.pdf
Manuel Widmoser (Univ. Salzburg), Daniel Kocher (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg). Scalable Distributed Inverted List Indexes in Disaggregated Memory. Proc. ACM Manag. Data 2(3): 171, 2024. DOI: https://doi.org/10.1145/3654974
Konstantin Emil Thiel (Univ. Salzburg), Daniel Kocher (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Thomas Hütter (Univ. Salzburg), Willi Mann (Celonis SE, Germany), Daniel Ulrich Schmitt (Univ. Salzburg). FINEX: A Fast Index for Exact and Flexible Density-Based Clustering. Proc. ACM Manag. Data 1(1): 71:1-71:25, 2023: DOI: https://doi.org/10.1145/3588925
Daniel Ulrich Schmitt (Univ. Salzburg), Daniel Kocher (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Willi Mann (Celonis SE, Germany), Alexander Miller (Univ. Salzburg). A Two-Level Signature Scheme for Stable Set Similarity Joins. PVLDB 16(11): 2686-2698, 2023. DOI: https://doi.org/10.14778/3611479.3611480
Manuel Widmoser (Univ. Salzburg), Daniel Kocher (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Willi Mann (Celonis SE, Germany). MetricJoin: Leveraging Metric Properties for Robust Exact Set Similarity Joins. IEEE ICDE Conference: 1045-1058, 2023. DOI: https://doi.org/10.1109/ICDE55515.2023.00085
Pranay Mundra (Univ. of Rochester, USA), Jianhao Zhang (Acho Software Inc, USA), Fatemeh Nargesian (Univ. of Rochester, USA), Nikolaus Augsten (Univ. Salzburg). KOIOS: Top-k Semantic Overlap Set Search. IEEE ICDE Conference: 1531-1543, 2023. DOI: https://doi.org/10.1109/ICDE55515.2023.00121
Thomas Hütter (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Christoph M. Kirsch (Univ. Salzburg), Michael J. Carey (UC Irvine, USA), Chen Li (UC Irvine, USA). JEDI: These aren't the JSON documents you're looking for? ACM SIGMOD Conference: 1584-1597, 2022. DOI: https://doi.org/10.1145/3514221.3517850
Christine Tex (Karlsruhe Institute of Technology, Germany), Martin Schäler (Univ. Salzburg), Klemens Böhm (Karlsruhe Institute of Technology, Germany). Swellfish privacy: Supporting time-dependent relevance for continuous differential privacy. Information Systems Journal 109, 2022. DOI: https://doi.org/10.1016/j.is.2022.102079
Daniel Kocher (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Willi Mann (Celonis SE, Germany). Scaling Density-Based Clustering to Large Collections of Sets. EDBT Conference: 109-120, 2021. DOI: https://doi.org/10.5441/002/edbt.2021.11
Oksana Dolmatova (Univ. Zurich, Switzerland), Nikolaus Augsten (Univ. Salzburg), Michael H. Böhlen (Univ. Zurich, Switzerland). A Relational Matrix Algebra and its Implementation in a Column Store. ACM SIGMOD Conference: 2573-2587, 2020. DOI: https://doi.org/10.1145/3318464.3389747
Thomas Hütter (Univ. Salzburg), Maximilian H. Ganser (Univ. Salzburg), Manuel Kocher (Univ. Salzburg), Merima Halkic (Univ. Salzburg), Sabine Agatha (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg). DeSignate: detecting signature characters in gene sequence alignments for taxon diagnoses. BMC Bioinform. 21(1): 151, 2020. DOI: https://doi.org/10.1186/s12859-020-3498-6
Thomas Hütter (Univ. Salzburg), Mateusz Pawlik (Univ. Salzburg), Robert Löschinger (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg). Effective Filters and Linear-Time Verification for Tree Similarity Joins. IEEE ICDE Conference: 854-865, 2019. DOI: https://doi.org/10.1109/ICDE.2019.00081
Daniel Kocher (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg). A Scalable Index for Top-k Subtree Similarity Queries. ACM SIGMOD Conference: 1624-1641, 2019. DOI: https://doi.org/10.1145/3299869.3319892
Fabian Fier (Humboldt-Univ. zu Berlin, Germany), Nikolaus Augsten (Univ. Salzburg), Panagiotis Bouros (Johannes Gutenberg Univ. Mainz, Germany), Ulf Leser (Humboldt-Univ. zu Berlin, Germany), Johann-Christoph Freytag (Humboldt-Univ. zu Berlin, Germany). Set Similarity Joins on MapReduce: An Experimental Survey. PVLDB 11(10): 1110-1122, 2018. DOI: https://doi.org/10.14778/3231751.3231760
Willi Mann (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Panagiotis Bouros (Aarhus Univ., Denmark). An Empirical Evaluation of Set Similarity Join Techniques. PVLDB 9(9): 636-647, 2016. DOI: https://doi.org/10.14778/2947618.2947620
Mateusz Pawlik (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg). Tree edit distance: Robust and memory-efficient. Inf. Syst. 56: 157-173, 2016. DOI: https://doi.org/10.1016/j.is.2015.08.004
Nikolaus Augsten (Univ. Salzburg), Armando Miraglia (VU Amsterdam, Netherlands), Thomas Neumann (TU München, Germany), Alfons Kemper (TU München, Germany). On-the-fly token similarity joins in relational databases. ACM SIGMOD Conference: 1495-1506, 2014. DOI: https://doi.org/10.1145/2588555.2610530
Scalable Distributed Inverted List Indexes in Disaggregated Memory
Proc. ACM Manag. Data 2(3): 171 (2024)
Manuel Widmoser, Daniel Kocher, Nikolaus Augsten:
https://doi.org/10.1145/3654974
Daniel Ulrich Schmitt, Daniel Kocher, Nikolaus Augsten, Willi Mann, Alexander Miller: A Two-Level Signature Scheme for Stable Set Similarity Joins. Proc. VLDB Endow. 16(11): 2686-2698 (2023)
https://doi.org/10.14778/3611479.3611480
Oksana Dolmatova (Univ. Zurich), Nikolaus Augsten (Univ. Salzburg), Michael H. Böhlen (Univ. Zurich):
A Relational Matrix Algebra and its Implementation in a Column Store. SIGMOD Conference 2020: 2573-2587
https://doi.org/10.1145/3318464.3389747
Thomas Hütter (Univ. Salzburg), Maximilian H. Ganser (Univ. Salzburg), Manuel Kocher (Univ. Salzburg), Merima Halkic (Univ. Salzburg), Sabine Agatha (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg):
DeSignate: detecting signature characters in gene sequence alignments for taxon diagnoses. BMC Bioinform. 21(1): 151 (2020)
https://doi.org/10.1186/s12859-020-3498-6
Set Similarity Joins on MapReduce: An Experimental Survey
2018
Fabian Fier (Humboldt-Universität zu Berlin), Nikolaus Augsten (Univ. Salzburg), Panagiotis Bouros (Johannes Gutenberg University Mainz), Ulf Leser (Humboldt-Universität zu Berlin), Johann-Christoph Freytag (Humboldt-Universität zu Berlin) PVLDB 11(10): 1110-1122
https://doi.org/10.14778/3231751.3231760
An Empirical Evaluation of Set Similarity Join Techniques
2016
Willi Mann (Univ. Salzburg), Nikolaus Augsten (Univ. Salzburg), Panagiotis Bouros (Aarhus Univ., Denmark) PVLDB 9(9): 636-647
https://doi.org/10.14778/2947618.2947620
On-the-fly token similarity joins in relational databases
2014
Nikolaus Augsten (Univ. Salzburg), Armando Miraglia (VU Amsterdam), Thomas Neumann (TU München), Alfons Kemper (TU München) SIGMOD Conference 2014: 1495-1506
https://doi.org/10.1145/2588555.2610530
JEDI: These aren't the JSON documents you're looking for?
2022
Thomas Hütter, Nikolaus Augsten, Christoph M. Kirsch, Michael J. Carey, Chen Li
SIGMOD Conference 2022: 1584-1597
https://doi.org/10.1145/3514221.3517850
Scaling Density-Based Clustering to Large Collections of Sets
2021
Daniel Kocher, Nikolaus Augsten, Willi Mann
EDBT Conference 2021: 109-120
https://doi.org/10.5441/002/edbt.2021.11
Swellfish privacy: Supporting time-dependent relevance for continuous differential privacy
2022
Christine Tex, Martin Schäler, Klemens Böhm
Information Systems Journal 109
https://doi.org/10.1016/j.is.2022.102079
Set Similarity Joins on MapReduce: An Experimental Survey.
2018
Fabian Fier, Nikolaus Augsten, Panagiotis Bouros, Ulf Leser, Johann-Christoph Freytag
PVLDB 11(10): 1110-1122
https://doi.org/10.14778/3231751.3231760
Tree edit distance: Robust and memory-efficient.
2016
Mateusz Pawlik, Nikolaus Augsten
Inf. Syst. 56: 157-173
https://doi.org/10.1016/j.is.2015.08.004
An Empirical Evaluation of Set Similarity Join Techniques.
2016
Willi Mann, Nikolaus Augsten, Panagiotis Bouros
PVLDB 9(9): 636-647
https://doi.org/10.14778/2947618.2947620
On-the-fly token similarity joins in relational databases.
2014
Nikolaus Augsten, Armando Miraglia, Thomas Neumann, Alfons Kemper
SIGMOD Conference 2014: 1495-1506
https://doi.org/10.1145/2588555.2610530