TU Berlin

Fachgebiet Datenbanksysteme und InformationsmanagementDIMA@SIGMOD 2015

Logo FG DIMA-new  65px

Inhalt

zur Navigation

DIMA Researchers @SIGMOD 2015

Dienstag, 30. Juni 2015

Members from TU Berlin’s Database Systems and Information Management
Group recently presented their research at the 2015 ACM SIGMOD/PODS
Conference
, which was held between May 31 and June 4 in Melbourne,
Australia. DIMA contributions included organizing a co-located workshop,
presenting two research papers, and offering a demonstration. Among the
attendees were DIMA Chair: Prof. Dr. Volker Markl, DIMA Postdocs: Dr.
Asterios Katsifodimos & Dr. Chen Xu, and DIMA PhD Students: Max Heimel,
Alexander Alexandrov, and Sergey Dudoladov.

Key highlights include:

I. The 4th DanaC: Workshop on Data Analytics at Scale

Organized and chaired by Dr. Asterios Katsifodimos, DanaC was held on May 31, 2015 and sponsored by Oracle. The workshop was a great success. Among the workshops taking place on May 31st at the 2015 SIGMOD/PODS Conference, it was the workshop with the highest number of participants. The agenda included: (i) an industrial keynote by Dr. Carlo Curino (Microsoft Research) on Big Data: Running Punctually at Data-center Scale and Beyond, (ii) an academic keynote by Dr. Chris Ré (Stanford University) on  DeepDive and Its Applications in Science and the Fight Against Human Trafficking!, (iii) four research paper presentations, and (iv) two invited scalable machine learning systems presentations, one on SystemML and the other on Apache SINGA. For more details visit danac.org.

Below we include some photos taken during the event.

Nach oben

II. DIMA Research Papers and Demonstration

DIMA had two research papers and a demonstration paper accepted at this year’s SIGMOD. Alexander Alexandrov presented Emma: A Deeply Embedded Language in Scala that Enables Implicit Parallelism [1], Max Heimel presented GPU Accelerated Selectivity Estimation [2], and Sergey Dudoladov and Dr. Chen Xu demonstrated Optimistic Recovery Techniques for Parallel Dataflows [3]. 

Nach oben

References

[1]    Implicit Parallelism through Deep Language Embedding, Alexander Alexandrov, Andreas Kunft, Asterios Katsifodimos, Felix Schüler, Lauritz Thamsen, Odej Kao, Tobias Herb, and Volker Markl.
[2]    Self-Tuning, GPU Accelerated Kernel Density Models for Multidimensional Selectivity Estimation,Max Heimel, Martin Kiefer, and Volker Markl.
[3]    Optimistic Recovery for Iterative Dataflows in Action, Sergey Dudoladov, Chen Xu, Sebastian Schelter, Asterios Katsifodimos, Stephan Ewen, Kostas Tzoumas, and Volker Markl.

Navigation

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe