Viktor Rosenfeld

PhD student at the German Research Center for Artificial Intelligence under the supervision of Volker Markl.

My main research interests are data processing on modern multi-core and many-core processors and heterogeneous systems, and adaptive query processing and auto-tuning techniques.

I received my Diplom-Informatik degree from Humboldt University Berlin in 2013, under the supervision of Ulf Leser, for the implementation of an optimized linguistic query language on top of a main-memory, column-oriented database. My thesis grew out of my work as a student researcher working on ANNIS, a database-backed corpus management system and query language for large multi-modal linguistic corpora.

Contact

: DFKI Project Office Berlin
Alt-Moabit 91C
10559 Berlin, Germany

: viktor.rosenfeld@dfki.de
: +49 30 23895 1816

Publications

DaMoN 2019 PDF Poster Slides Git: Performance Analysis and Automatic Tuning of Hash Aggregation on GPUs, Viktor Rosenfeld, Sebastian Breß, Steffen Zeuch, Tilmann Rabl, Volker Markl. In Proceedings of the 15th International Workshop on Data Management on New Hardware (DaMoN 19). [BibTeX]
EDBT 2018 PDF Poster Git: Efficient SIMD Vectorization for Hashing in OpenCL, Tobias Behrens, Viktor Rosenfeld, Jonas Traub, Sebastian Breß, Volker Markl. In Proceedings of the 21st International Conference on Extending Database Technology (EDBT). [BibTeX]
SoCC 2017 PDF Poster Slides: Processing Java UDFs in a C++ environment, Viktor Rosenfeld, Rene Mueller, Pinar Tözün, Fatma Özcan. In Proceedings of SoCC '17, Santa Clara, USA. [BibTeX]
ADMS 2015 PDF Slides Git: The Operator Variant Selection Problem on Heterogeneous Hardware, Viktor Rosenfeld, Max Heimel, Christoph Viebig, Volker Markl. In the Proceedings of the Sixth International Workshop on Accelerating Analytics and Data Management Systems Using Modern Processor and Storage Architectures. [BibTeX]
Diplom thesis PDF: A Linguistic Query Language On Top Of A Column-Oriented Main-Memory Database, Viktor Rosenfeld. Humboldt-Universität zu Berlin, 2012.
DGfS 2009: Search and visualization of richly annotated corpora with ANNIS2, Christian Chiarcos, Thomas Krause, Anke Lüdeling, Julia Ritz, Viktor Rosenfeld, Manfred Stede, Amir Zeldes, and Florian Zipser. In 31. Jahrestagung der Deutschen Gesellschaft für Sprachwissenschaft (Poster), 2009.

Scientific Community Service

Program Committee member: ADMS 2016.

Thesis supervision

Yusuf Güven Toprakkiran: Machine learning from streaming data in heterogeneous computing environments
Larissa Granowsky: Laufzeitanalyse von daten-parallelen Systemen auf Multicore-Prozessoren im Vergleich zu serieller Implementierung (Bachelor thesis)

Teaching

Summer term 2018

Lectures for DBPRA: Datenbankpraktikum

Winter term 2017/2018

Storage lecture and exercises for DBT: Scalable Data Processing