Dynamic Scheduling for Progressive Large-Scale Visualization.

The ever-increasing compute capacity of high-performance systems enables scientists to simulate physical phenomena with a high spatial and temporal accuracy. Thus, the simulation output can yield dataset sizes of many terabytes. An efficient analysis and visualization process becomes very difficult especially for explorative scenarios where users continuously change input parameters. Using a distributed rendering pipeline may relieve the visualization frontend considerably but is often not sufficient. Therefore, we additionally propose a progressive data streaming and rendering approach. The main contribution of our method is the importance-guided order of data processing for block structured datasets. This requires a dynamic scheduling of data chunks on the parallel post-processing system which has been implemented by using an R-Tree. In this paper, we demonstrate the efficiency of our implementation for view-dependent feature extraction with varying viewpoints.