The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Workshop:ISAV 2020: In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization
Authors: Pascal Grosset (Los Alamos National Lab) and Jesus Pulido and James Ahrens (Los Alamos National Laboratory)
Abstract: In situ analysis is now commonly used in many simulations. Prior to the simulation being run, the user specifies what in situ analysis should be run and the results of that analysis are saved to disk while the simulation is running. It is, however, sometimes hard to know what analysis to run before a simulation has started, and that often results in the user saving full datasets to disk for analysis later. In this paper, we present a framework, \framework, that allows users to change, in real time, which in situ analysis to run. \framework also allows many users to each run their own in situ analysis, in a "personalized workspace", independent of each other. Finally \framework can be easily integrated into simulations and plays well with other in situ analysis frameworks, such as ParaView Catalyst.