My research interests lie in the areas of distributed and parallel computing systems, database management systems and stream processing engines, with a current focus on optimization of streaming queries. At the moment, I am working on the design of highly efficient incremental operators with compiler-based techniques.
- G. Theodorakis, A. Koliousis, P. R. Pietzuch, and H. Pirk,
LightSaber: Efficient Window Aggregation on Multi-core Processors in
Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD 2020, Portland, OR, USA, Jun 2020
- G. Theodorakis, P. R. Pietzuch, H. Pirk,
SlideSide: A fast Incremental Stream Processing Algorithm for Multiple Queries
in Advances in Database Technology - 23rd InternationalConference on Extending Database Technology, EDBT 2020, Copenhagen, Denmark, Mar 2020
- G. Theodorakis, A. Koliousis, P. Pietzuch and H. Pirk,
Hammer Slide: Work- and CPU-efficient Streaming Window Aggregation
in 9th International Workshop on Accelerating Analytics and Data Management Systems
Using Modern Processor and Storage Architectures (ADMS),
Rio de Janeiro, Brazil,
Aug 2018. [pdf]
- Optimisation of streaming queries based on window semantics with code generation [GitHub]
- "Do We Need Distributed Stream Processing?"
- Integration of Apache Calcite – a dynamic data management framework – and
SABER – a hybrid relational stream processing engine. Introduction of rate-based optimisation techniques to improve the throughput, the latency and the CPU utilization of streaming queries. [GitHub] [DiplomaThesis]
Talks & Presentations
- SlideSide: A fast Incremental Stream Processing Algorithm for Multiple Queries in EDBT/ICDT 2020 Joint Conference, 1st April, 2020, Copenhagen, Denmark
- LightSaber: Efficient Window Aggregation on Multi-core Processors poster in PhD Workshop on Next-Generation Cloud Infrastructure of Microsoft Research, Cambridge, UK, Nov. 2019.
- "Hardware-efficient Stream Processing" in Flink Forward Berlin 2018, Berlin, Germany, Sep 2018. [slides] [video]
- "Hammer Slide: Work- and CPU-efficient Streaming Window Aggregation" in ADMS@VLDB 2018, Rio de Janeiro, Brazil, Aug 2018. [slides]