The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Workshop:ISAV21: In Situ Infrastructures for Enabling Extreme Scale Analysis and Visualization
Authors: Pascal Grosset (Los Alamos National Lab) and James Ahrens (Los Alamos National Laboratory)
Abstract: As simulations get larger and produce more data, domain scientists are increasingly using in situ methods to analyze and visualize data as they are being produced. Most tools for in situ, which allow domain scientists to monitor their simulations, such as ParaView Catalyst and VisIt Libsim, tend to be bulky and require the scientist to request and wait for compute nodes or download full datasets (of the order of terabytes or petabytes) on desktops/laptops for analysis. In this paper, we present a very lightweight framework that allows users to visualize snapshots of a simulation without having to request additional compute nodes from a supercomputer when analysis or visualization is needed or download full datasets. We extend the Seer framework, an open-source in situ framework, to sub-sample and store simulation data, which can then be accessed and manipulated from the user's local machine using a dashboard created using Plotly's Dash interface.