Home » Blog » 8th TUC Meeting - Tim Hegeman (TU Delft). Social Network Benchmark, Analytics workload.

8th TUC Meeting - Tim Hegeman (TU Delft). Social Network Benchmark, Analytics workload.

  • Posted on: 23 December 2016
  • By: Adrian Diaz

Tim Hegeman from TU Delft presented a very interesting talk about Social Network Benchmark analytics. Graphalytics is a benchmark developed by TU Delft for graph analytics, complex and holistic graph computations.

As per today, over 100 graph analytics systems exist, Hegeman explains, but they’re not comprehensive and there's where Graphalytics excels. It consists on algorithms and datasets (workload) that have been selected using a 2-stage process to ensure the representativity of the workload. The stages of the process were:

  • Identity common classes of datasets/algorithms
  • Selection of datasets/algorithms to make a set diverse enough to touch each choke point

One key aspect of the benchmark is its driver, in this case Graphalytics is developed to provide 3 basic functions:

  • Upload the graph. Allows-preprocessing of a graph to convert it to a platform-specific format, copy it to a distributed filesystem, insert in into a database…
  • Execute an algorithm. Executes a single algorithm on an already uploaded graph and store the output on the machine running Graphalytics.
  • Delete a graph.

Near the end of his talk Hegeman introduced Granula, a tool that platform developers can use for monitoring, modeling, archiving and visualizing the performance of graph analytic systems. You can see his whole presentation and his slides in the links below.

Remember to plan your assistance tot the upcoming 9th TUC Meeting at SAP's HQ in Walldorf, Germany the 9-10th of February!

 

If you want to know more about Graphalytics and its capabilities check the following links:

LDBC's page dedicated to Graphalytics

Github Repo

 

Categories: 

Add new comment