Distance visualization of ultrascale data with explorable images

This talk presents a new approach to distance visualization of very large data sets output from scientific supercomputing. The processing power of massively parallel supercomputers increases at a rather fast rate, about an order of magnitude faster every three years, enabling scientists to model complex physical phenomena and chemical processes at unprecedented fidelity. Several petascale computers are already in operation (http://www.top500.org) and exascale computing is around the corner. Each run of a petascale simulation typically outputs several hundred terabytes of data to disk. Transferring data at this scale over wide-area networks to the scientist's laboratory for post-processing analysis is not an option. Even the data files may be transferred, existing desktop data analysis and visualization tools cannot effectively handle such large-scale data. If the scientists may use the same supercomputing facility for data analysis and visualization, there are three viable solutions: in situ visualization, where visualization is computed during the simulation on the same supercomputer co-processing visualization, where visualization is computed during the simulation on a separate computer, and post-processing visualization, where visualization is computed after simulation is over.