direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

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 [1], 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: [2] 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 [3] 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 [4] (Microsoft Research) on Big Data: Running Punctually at Data-center Scale and Beyond, (ii) an academic keynote by Dr. Chris Ré [5] (Stanford University) on  DeepDive [6] 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 [7] and the other on Apache SINGA [8]. For more details visit danac.org [9].

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


[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.

------ Links: ------

Zusatzinformationen / Extras


Schnellnavigation zur Seite über Nummerneingabe

Copyright TU Berlin 2008