BTW Logo

The objective of this one-day workshop is to explore challenges and opportunities of data processing on existing and future heterogeneous hardware architectures. Today's processors are no longer mainly bound by the density and frequency of transistors, but by their power and heat budgets. The so-called "power wall" forces hardware suppliers to rely more on the design of specialized devices optimized for certain types of calculations, which results in an increasingly heterogeneous hardware landscape. Therefore, to meet the performance requirements of the modern information society, tomorrow's database systems will have to exploit and embrace this increased heterogeneity.

The purpose of the workshop is to assist in the training and growth of a community of researchers and industry practitioners working on data (co-)processing issues on heterogeneous systems. To this end, we want to provide a forum to discuss challenges, progress and directions, while creating an environment for networking with people working on related topics and fostering future collaborations. Especially in the presence of the SPP 2037 on Scalable Data Management for Future
Hardware, we want to strengthen collaborations beyond single SPP projects by bringing them into contact with other researchers. This workshop is co-organized by the GI-Arbeitskreis Data Management on Modern Hardware.

Topics of Interest

The scope of the workshop includes, but is not limited to:

  • Applications of modern hardware in
    • data mining
    • data-intensive machine learning
    • query processing
    • non-traditional applications (e.g. graph processing)
  • Algorithms and data structures for efficient data processing on and across different (co-)processors (e.g., GPUs, APUs, Accelerator cards, FPGAs)
  • Exploitation of specialized ASICs
  • Efficient memory management, data placement and data transfer strategies in heterogeneous systems
  • Energy efficiency in heterogeneous (co-)processor environments
  • Programming models and hardware abstraction mechanisms for writing data-intensive algorithms on heterogeneous hardware
  • Query optimization, cost estimation and operator placement strategies for heterogeneous hardware
  • Transaction processing in heterogeneous systems

Accepted Papers and Keynote

We are looking forward to the following keynote:

  • Dr. Erich Focht - NEC Deutschland GmbH: The high memory bandwidth vector engine NEC Aurora TSUBASA

We are pleased to announce the accepted papers of the workshop:

  • Sebastian Breß, Henning Funke, Steffen Zeuch, Tilmann Rabl, Volker Markl: An Overview of Hawk: A Hardware-Tailored Code Generator for the Heterogeneous Many Core Age (Extended Abstract)
  • Johannes Pietrzyk, Dirk Habich, Patrick Damme, Wolfgang Lehner: First Investigations of the Vector Supercomputer SX-Aurora TSUBASA as a Co-Processor for Database Systems
  • Tobias Ziegler, Carsten Binnig, Uwe Röhm: Skew-resilient Query Processing for Fast Networks (Extended Abstract)
  • Philipp Götze, Constantin Pohl, Kai-Uwe Sattler: Query Planning for Transactional Stream Processing on Heterogeneous Hardware: Opportunities and Limitations (Novel Ideas & Experience Reports)
  • Christopher Schmidt, Matthias Uflacker: Workload-Driven Data Placement for GPU-Accelerated Database Management Systems (Extended Abstract)
  • Andreas Becher, Achim Herrmann, Stefan Wildermann, Jürgen Teich: ReProVide: Towards Utilizing Heterogeneous Partially Reconfigurable Architectures for Near-Memory Data Processing

Submission Guidelines

Submitted papers will be reviewed by the workshop's Program Committee. Accepted papers will appear in the BTW'19 Workshops proceedings, published as part of LNI. The papers should be written in German or English and adhere to the LNI formatting guidelines.

The workshop solicits research papers describing preliminary and ongoing research results. Hence, we offer the following three types of submission

  • Regular research papers of maximum 20 pages
  • Novel ideas, experience reports of maximum 10 pages
  • Extended abstracts of 2-4 pages

Extended abstracts may present novel ideas or may be used to communicate research results from already published work at high-ranked conferences or journals to our community. Research papers must be an original unpublished work and not under review elsewhere. Novel ideas and experience reports must be stated as such and a comprehensive discussion of the taken or proposed approach, experiences, and its assessment are expected. All papers and reports must be submitted as PDF documents through ConfTool, track NoDMC.

Important Deadlines

  • 05.12.2018 Submission Deadline
  • 19.12.2018 Author Notification
  • 15.01.2019 Camera Ready Version

PC Chairs

  • This email address is being protected from spambots. You need JavaScript enabled to view it. (University of Magdeburg)
  • This email address is being protected from spambots. You need JavaScript enabled to view it. (TU Dresden)

Steering Committee

  • Wolfgang Lehner (TU Dresden)
  • Gunter Saake (University of Magdeburg)
  • Kai-Uwe Sattler (TU Ilmenau)

Program Committee

  • Carsten Binnig (TU Darmstadt)
  • Sebastian Breß (DFKI Berlin)
  • Matthias Böhm (IBM Almaden, Uni Graz)
  • David Broneske (University of Magdeburg)
  • Dirk Habich (TU Dresden)
  • Constantin Pohl (TU Ilmenau)
  • Hannes Rauhe (SAP SE)
  • Knut Stolze (IBM Germany)
  • Jens Teubner (TU Dortmund)