SENSEI + Python

Workshop held at the Swiss National Supercomputing Centre held on March 21 and 22, 2018 in Lugano, Switzerland

Extreme-scale computer simulations are faced with a constantly widening gap between computational and I/O rates; one alternative to overcome this challenge is based on the idea of in situ processing, where visualization and analysis processing is performed while data is still resident in memory. The SENSEI in situ Data Interface is an API that promotes code portability and reusability. From the simulation view, a developer can instrument their code with the SENSEI API and then make use of any number of in situ infrastructures, such as ADIOS, ParaView Catalyst, GLEAN and VisIt Libsim. This tutorial presents the fundamentals of in situ data analysis and visualization leveraging this generic interface. Attendees will learn the basics of in situ analysis and visualization while being exposed to advanced analysis such as time-dependent autocorrelation and interactive monitoring and steering. We demonstrate the infrastructure coupling of mini-apps using ADIOS, ParaView Catalyst, and VisIt Libsim.