RAVEN --- boosting data analysis for the LHC experiments

  • Authors:
  • Michael Schmelling;Markward Britsch;Nikolai Gagunashvili;Hans Kristjan Gudmundsson;Helmut Neukirchen;Nicola Whitehead

  • Affiliations:
  • Max-Planck-Institute for Nuclear Physics, Heidelberg, Germany;Max-Planck-Institute for Nuclear Physics, Heidelberg, Germany;University of Akureyri, Akureyri, Iceland;University of Akureyri, Akureyri, Iceland;University of Iceland, Reykjavik, Iceland;University of Akureyri, Akureyri, Iceland

  • Venue:
  • PARA'10 Proceedings of the 10th international conference on Applied Parallel and Scientific Computing - Volume 2
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The analysis and visualization of the LHC data is a good example of human interaction with petabytes of inhomogeneous data. After outlining the computational requirements for an efficient analysis of such data sets, a proposal, RAVEN --- a Random Access, Visualization and Exploration Network for petabyte sized data sets, for a scalable architecture meeting these demands is presented. The proposed hardware basis is a network of "CSR"-units based on off-the-shelf components, which combine Computing, data Storage and Routing functionalities. At the software level efficient protocols for broadcasting information, data distribution and information collection are required, together with a middleware layer for data processing.