Extreme Event Analysis in Next Generation Simulation Architectures
Time:
Tuesday, June 20, 2017 03:45 pm - 04:15 pm
Room:
Panorama 3 Messe Frankfurt
Breaks:
03:15 pm - 03:45 pm Coffee Break
Speaker:
Stephen Hamilton, Johns Hopkins University
Abstract:
Numerical simulations present challenges because they generate petabyte-scale data that must be extracted and reduced during the simulation. We demonstrate a seamless integration of feature extraction for a simulation of turbulent fluid dynamics. The simulation produces on the order of 6 terabytes per timestep. In order to analyze and store this data, we extract velocity data from a dilated volume of the strong vortical regions and also store a lossy compressed representation of the data. Both reduce data by one or more orders of magnitude. We extract data from user checkpoints while they reside on temporary burst buffer NVRAM (non-volatile random-access memory) stores. In this way, analysis and compression do not interfere with simulation computations. Our results demonstrate that we can visualize a world-class direct numerical simulation of turbulence at runtime and gather meaningful scientific data for archival and post analysis.
;){kind=link}