In-situ visualization course

Content

Scientific visualization and analysis are key ingredients in HPC simulation workflows. For decades, the dominant paradigm has been post-hoc visualization; simulation codes iterate and save files to disk, giving the domain scientists the opportunity to read the data back at a later time for analysis. In recent years though, this paradigm has been stressed by an ever-diverging rate of growth between I/O and compute speeds. In-situ processing helps mitigate these I/O bottlenecks, enabling simulation and visualization calculations to run in-memory, at higher spatial and temporal resolutions, avoiding the transfer of raw data to disks. This full-day course introduces the in-situ visualization paradigm along with Ascent and ParaView Catalyst, two open-source in-situ processing libraries. Both libraries leverage a common interface, Conduit, which provides an intuitive model for describing hierarchical scientific data in C++, C, Fortran, and Python. Attendees will gain hands-on experience learning how to describe simulation data with Conduit and how to use Ascent and Catalyst to transform data, render images, and export results.

Target Audience

Scientific Code Developpers

Schedule

The course will begin at 09:30 and conclude at 16:30 (Central European Time, CET) and will include a one-hour lunch break, as well as a 15-minute break in both the morning and afternoon sessions.

• 09:30 Overview, Motivation, Agenda, Technical details
• Introduction to in-situ visualization, workflows and terminology
• Conduit, an API to describe hierarchical scientific data
• The Mesh Blueprint, usage conventions, examples
• Coffee break
• Ascent, an in-situ visualization and analysis library using Conduit
  Making images
  Transforming data, extracting data
  Queries and Conditional triggers
  Instrumentation examples with Ascent
  • Meshed-based data: heat-diffusion problem (C++/Python/CUDA)
  • Particle-based data: N-body (C++/CUDA)
• Lunch break
• ParaView Catalyst v2, an in-situ visualization and analysis library using Conduit
  The ParaView interactive application
  The Paraview parallel server architecture
  The Catalyst API, and the ParaView Catalyst Blueprint
  Python scripting, Data Extractors
  Instrumentation examples with Catalyst
  • Meshed-based data: heat-diffusion problem (C++/Python/CUDA)
  • Particle-based data: N-body (C++/CUDA)
• Catalyst, connecting to a live simulation, steering
• Coffee break
• Ascent executing ParaView Python code
  Future developments, alternative workflows
  in-transit visualization with ADIOS2 + Fides + ParaView
• Wrap-up, Q&A

16:30 End of Workshop 

Instructor

Jean M. Favre, Senior Visualisation Software Engineer (CSCS)

Jean-Guillaume Piccinali, Senior HPC Performance Engineer (CSCS)

Participation Fee and Registration

All participants must register for the course. The registration fee includes lunch and coffee breaks.

Course Fee: CHF 80.00

Deadline for registration: Friday, December 5, 2025.

Kindly note that the course can take place only if there are sufficient confirmed registrations received by the deadline. The minimum number of participants is eight. Should the minimum number of participants not be reached by the deadline, registered attendees will be informed about the course cancellation. No communication will be sent to confirm the event. Registration for the course will automatically close when we reach the maximum number of participants (30).

How to get to there

• By train

From Oerlikon railway station, you can reach the Andreasturm on foot (see route on map).

More information

Please contact jean.favre@cscs.ch for questions related to the Program content, or helen.biehler@cscs.ch for questions related to the event logistics.

We look forward to welcoming you at CSCS!