Photograph of Patrick Damme.

Dr.-Ing. Patrick Damme

Postdoc Researcher at Technische Universität Berlin
Faculty IV - Electrical Engineering and Computer Science
Berlin Institute for the Foundations of Learning and Data (BIFOLD)
Big Data Engineering (DAMS Lab) Group

Office: Room TEL-0814, Ernst-Reuter-Platz 7, 10587 Berlin, Germany
patrick.damme(æ)tu-berlin.de


I'm a postdoc researcher in the DAMS Lab research group headed by Matthias Boehm at Technische Universität Berlin and the BIFOLD research center in Berlin, Germany. My research interests are centered around database systems, machine learning systems, and techniques for making complex analyses of large data volumes efficient, scalable, and simple. In that context, my current topics of interest include extensible data systems, compilation and runtime techniques, as well as language abstractions for declarative analyses. The main vehicle of this research is DAPHNE, an open and extensible system infrastructure for integrated data analysis pipelines combining data management and query processing, machine learning training and scoring, as well as high-performance computing and simulations.

Until fall 2022, I was a university project assistant at Graz University of Technology and a senior researcher (postdoc) at the co-located Know-Center GmbH in Graz, Austria. During that time, I started my research in the DAPHNE EU-project and became one of the main contributors of the DAPHNE system.

Before that, in 2020, I received my PhD (Dr.-Ing.) from Technische Universität Dresden in Dresden, Germany, where I was a research associate in the Dresden Database Systems group. I was supervised by Wolfgang Lehner and co-supervised by Dirk Habich. In my PhD thesis, I investigated the use of lightweight integer compression for the intermediate results of complex OLAP queries in in-memory column stores as a means to address the memory wall. This work led to the development of MorphStore, a research prototype of a query processing engine for columnar data, based on compression and SIMD as first-class citizens. I've also collaborated with colleagues on topics like SIMD, NVRAM, resilience, and energy efficiency in database systems.



Publications

2023
 
  • Aristotelis Vontzalidis, Stratos Psomadakis, Constantinos Bitsakos, Mark Dokter, Kevin Innerebner, Patrick Damme, Matthias Boehm, Florina M. Ciorba, Ahmed Eleliemy, Vasileios Karakostas, Aleš Zamuda, Dimitrios Tsoumakos: DAPHNE Runtime: Harnessing Parallelism for Integrated Data Analysis Pipelines. Euro-Par Workshops 2023.
  • Patrick Damme, Matthias Boehm: Enabling Integrated Data Analysis Pipelines on Heterogeneous Hardware through Holistic Extensibility (Extended Abstract (New Idea)). NoDMC@BTW 2023.
  • Lucas Woltmann, Patrick Damme, Claudio Hartmann, Dirk Habich, Wolfgang Lehner: Learned Selection Strategy for Lightweight Integer Compression Algorithms. EDBT 2023.

2022
 
  • Patrick Damme, Marius Birkenbach, Constantinos Bitsakos, Matthias Boehm, Philippe Bonnet, Florina M. Ciorba, Mark Dokter, Pawel Dowgiallo, Ahmed Eleliemy, Christian Faerber, Georgios I. Goumas, Dirk Habich, Niclas Hedam, Marlies Hofer, Wenjun Huang, Kevin Innerebner, Vasileios Karakostas, Roman Kern, Tomaž Kosar, Alexander Krause, Daniel Krems, Andreas Laber, Wolfgang Lehner, Eric Mier, Marcus Paradies, Bernhard Peischl, Gabrielle Poerwawinata, Stratos Psomadakis, Tilmann Rabl, Piotr Ratuszniak, Pedro Silva, Nikolai Skuppin, Andreas Starzacher, Benjamin Steinwender, Ilin Tolovski, Pınar Tözün, Wojciech Ulatowski, Yuanyuan Wang, Izajasz P. Wrosz, Aleš Zamuda, Ce Zhang, Xiaoxiang Zhu: DAPHNE: An Open and Extensible System Infrastructure for Integrated Data Analysis Pipelines. CIDR 2022.

2021
 
  • Mikhail Zarubin, Patrick Damme, Alexander Krause, Dirk Habich, Wolfgang Lehner: SIMD-MIMD Cocktail in a Hybrid Memory Glass: Shaken, Not Stirred. SYSTOR 2021.

2020
 
  • Patrick Damme: Analytical Query Processing Based on Continuous Compression of Intermediates. PhD Thesis, Dresden University of Technology, Germany.
  • Patrick Damme, Annett Ungethüm, Johannes Pietrzyk, Alexander Krause, Dirk Habich, Wolfgang Lehner: MorphStore: Analytical Query Engine with a Holistic Compression-Enabled Processing Model. PVLDB 13(11).
  • Annett Ungethüm, Johannes Pietrzyk, Patrick Damme, Alexander Krause, Dirk Habich, Wolfgang Lehner, Erich Focht: Hardware-Oblivious SIMD Parallelism for In-Memory Column-Stores. CIDR 2020.
  • Mikhail Zarubin, Patrick Damme, Dirk Habich, Wolfgang Lehner: Polymorphic Compressed Replication of Columnar Data in Scale-Up Hybrid Memory Systems. SYSTOR 2020.
  • Patrick Damme, Annett Ungethüm, Johannes Pietrzyk, Alexander Krause, Dirk Habich, Wolfgang Lehner: MorphStore: Analytical Query Engine with a Holistic Compression-Enabled Processing Model. CoRR abs/2004.09350.

2019
 
  • Johannes Pietrzyk, Dirk Habich, Patrick Damme, Erich Focht, Wolfgang Lehner: Evaluating the Vector Supercomputer SX-Aurora TSUBASA as a Co-Processor for In-Memory Database Systems. Datenbank-Spektrum 19(3).
  • Patrick Damme, Annett Ungethüm, Juliana Hildebrandt, Dirk Habich, Wolfgang Lehner: From a Comprehensive Experimental Survey to a Cost-based Selection Strategy for Lightweight Integer Compression Algorithms. ACM Trans. Database Syst. 44(3).
  • Johannes Pietrzyk, Dirk Habich, Patrick Damme, Wolfgang Lehner: First Investigations of the Vector Supercomputer SX-Aurora TSUBASA as a Co-Processor for Database Systems. BTW (Workshops) 2019.
  • Mikhail Zarubin, Patrick Damme, Thomas Kissinger, Dirk Habich, Wolfgang Lehner, Thomas Willhalm: Integer Compression in NVRAM-centric Data Stores: Comparative Experimental Analysis to DRAM. DaMoN 2019.
  • Dirk Habich, Patrick Damme, Annett Ungethüm, Johannes Pietrzyk, Alexander Krause, Juliana Hildebrandt, Wolfgang Lehner: MorphStore - In-Memory Query Processing based on Morphing Compressed Intermediates LIVE. SIGMOD 2019.

2018
 
  • Annett Ungethüm, Johannes Pietrzyk, Patrick Damme, Dirk Habich, Wolfgang Lehner: Conflict Detection-Based Run-Length Encoding - AVX-512 CD Instruction Set in Action. ICDE Workshops 2018.
  • Dirk Habich, Patrick Damme, Annett Ungethüm, Wolfgang Lehner: Make Larger Vector Register Sizes New Challenges?: Lessons Learned from the Area of Vectorized Lightweight Compression Algorithms. DBTest@SIGMOD 2018.

2017
 
  • Annett Ungethüm, Patrick Damme, Johannes Pietrzyk, Alexander Krause, Dirk Habich, Wolfgang Lehner: Balancing Performance and Energy for Lightweight Data Compression Algorithms. ADBIS (Short Papers and Workshops) 2017.
  • Patrick Damme, Dirk Habich, Juliana Hildebrandt, Wolfgang Lehner: Lightweight Data Compression Algorithms: An Experimental Survey (Experiments and Analyses). EDBT 2017.
  • Patrick Damme, Dirk Habich, Juliana Hildebrandt, Wolfgang Lehner: Insights into the Comparative Evaluation of Lightweight Data Compression Algorithms. EDBT 2017.
  • Juliana Hildebrandt, Dirk Habich, Thomas Kühn, Patrick Damme, Wolfgang Lehner: Metamodeling Lightweight Data Compression Algorithms and its Application Scenarios. ER Forum/Demos 2017.
  • Patrick Damme: Query Processing Based on Compressed Intermediates. PhD@VLDB 2017.

2016
 
  • Juliana Hildebrandt, Dirk Habich, Patrick Damme, Wolfgang Lehner: Model Kit for Lightweight Data Compression Algorithms. EDBT 2016.
  • Juliana Hildebrandt, Dirk Habich, Patrick Damme, Wolfgang Lehner: Compression-Aware In-Memory Query Processing: Vision, System Design and Beyond. ADMS/IMDM@VLDB 2016.

2015
 
  • Patrick Damme, Dirk Habich, Wolfgang Lehner: Direct Transformation Techniques for Compressed Data: General Approach and Application Scenarios. ADBIS 2015.
  • Dirk Habich, Patrick Damme, Wolfgang Lehner: Optimierung der Anfrageverarbeitung mittels Kompression der Zwischenergebnisse. BTW 2015.
  • Till Kolditz, Dirk Habich, Patrick Damme, Wolfgang Lehner, Dmitrii Kuvaiskii, Oleksii Oleksenko, Christof Fetzer: Resiliency-aware Data Compression for In-memory Database Systems. DATA 2015.
  • Juliana Hildebrandt, Dirk Habich, Patrick Damme, Wolfgang Lehner: Modularisierung leichtgewichtiger Kompressionsalgorithmen. GvD 2015.
  • Hannes Voigt, Patrick Damme, Wolfgang Lehner: Enjoy FRDM - Play with a Schema-flexible RDBMS. ICDE 2015.
  • Patrick Damme, Dirk Habich, Wolfgang Lehner: A Benchmark Framework for Data Compression Techniques. TPCTC 2015.

2013
 
  • Julian Eberius, Patrick Damme, Katrin Braunschweig, Maik Thiele, Wolfgang Lehner: Publish-time Data Integration for Open Data Platforms. WOD 2013.

Teaching

At TU Berlin

Winter 2024/25
 
Summer 2024
 
Winter 2023/24
 
Summer 2023
 

At TU Graz

Summer 2022
 
  • Data Management (assistant lecturer)
Winter 2021/22
 
  • Architecture of Database Systems (practical exercise)

At TU Dresden

Winter 2017/18
 
  • Information Retrieval (exercise)
Winter 2016/17
 
  • Information Retrieval (exercise)
Winter 2015/16
 
  • Information Retrieval (exercise)

Service

2026
 
  • PC member EDBT 2026

2025
 
  • PC member PVLDB Volume 18 (for VLDB 2025)
  • PC member EDBT 2025
  • PC member NoDMC@BTW 2025

2024
 
  • PC member PVLDB Volume 17 (for VLDB 2024)
  • Reviewer VLDBJ

2023
 
  • PC member EDBT 2023  Distinguished PC Member Award
  • PC member DEEM@SIGMOD 2023
  • PC member NoDMC@BTW 2023

2022
 
  • PC member CDMS@VLDB 2022
  • PC member DEEM@SIGMOD 2022
  • PC member GvDB 2022