link to homepage

Navigation and service

Training course "Introduction to Parallel In-Situ Visualization"

01 Apr 2018 00:00
01 Apr 2018 00:00
Jülich Supercomputing Centre, Ausbildungsraum 2, building 16.3, room 211


Date has not yet been fixed.


Target audience:
Staff members who want to use VisIt for visualization.

With each generation of supercomputers, memory and CPU performance grows faster than the access and capacity of hard disks. As a result, I/O performance is continuously reduced compared to the rest of the supercomputer. This trend hinders the traditional visualization paradigm.<br> One solution is the coupling of simulations with real-time visualization - called in situ visualization. In situ visualizing is visualization that necessarily starts before the data producer finishes. The key aspect of in situ visualization is that data is used for visualization/analysis while still in memory. This type of visualization can extract and preserve important information from the simulation that is lost when the simulation proceeds.

The course will cover an introduction and the basic aspects of in situ visualization. In the second half we will focus on the use of in situ visualization in massive parallel environments. Especially the integration into existing simulation codes will be discussed. In a hands-on session the integration of ParaView/Catalyst and VisIt/Libsim will be demonstrated on an small parallel application.

Topics covered will include:

  • Introduction to In Situ Visualization
  • In-Situ Visualization with ParaView/Catalyst and VisIt/Libsim
  • Hands-on session
Knowledge about programming of parallel applications in C/C++ or Fortran
This course is taught in English.
1 day
probably April 2018
Jülich Supercomputing Centre, Ausbildungsraum 2, building 16.3, room 211
Number of participants:
minimum 5
Jens Henrik Göbbert, Dr. Herwig Zilken, JSC
Photo Jens Henrik Göbbert
Jens Henrik Göbbert
Phone: +49 2461 61-96498
Please register with Jens Henrik Göbbert until 15 March 2018.
If you do not belong to the staff of Forschungszentrum Jülich, we need these data for registration:
Given name, name, birthday, nationality, complete home address, email address