Parallel density-based stream clustering using a multi-user GPU scheduler

A. Tarakji, M. Hassani, L. Georgiev, T. Seidl, R. Leupers

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review


With the emergence of advanced stream computing architectures, their deployment to accelerate long-running data mining applications is becoming a matter of course. This work presents a novel design concept of the stream clustering algorithm DenStream, based on a previously presented scheduling framework for GPUs. By means of our scheduler OCLSched, DenStream runs together with general computation tasks in a multi-user computing environment, sharing the GPU resources. A major point of concern throughout this paper has been to disclose the functionality and purposes of the applied scheduling methods, and to demonstrate the OCLSched’s ability of managing highly complex applications in a multi-task GPU environment. Also in terms of performance, our tests show reasonable improvements when comparing the proposed parallel concept of DenStream with a single-threaded CPU version
Original languageEnglish
Title of host publicationBeyond Databases, Architectures and Structures - 11th International Conference, BDAS 2015, Ustron, Poland, May 26-29, 2015, Proceedings
EditorsS. Kozielski, D. Mrozek, P. Kasprowski, B. Małysiak-Mrozek, D. Kostrzewa
Place of PublicationCham
Number of pages18
ISBN (Electronic)978-3-319-18422-7
ISBN (Print)978-3-319-18421-0
Publication statusPublished - 26 May 2015
Externally publishedYes
Event11th International Conference on Beyond Databases, Architectures and Structures (BDAS 2015) - Ustro ́n, Poland
Duration: 26 May 201529 May 2015
Conference number: 11

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929


Conference11th International Conference on Beyond Databases, Architectures and Structures (BDAS 2015)
Abbreviated titleBDAS 2015
CityUstro ́n


  • OpenCL
  • Data mining
  • Streams
  • Task Scheduling


Dive into the research topics of 'Parallel density-based stream clustering using a multi-user GPU scheduler'. Together they form a unique fingerprint.

Cite this