“Data analysis and visualization at the National Center for Supercomputing applications”
Supercomputers are built to endure painfully large simulations and contend with resulting outputs. These are characteristics that scientists are all too willing to test the limits of in their quest for science at scale. The data generated during a scientist’s workflow through an HPC center is the primary target for analysis and visualization. However, the hardware itself is also capable of generating volumes of log/diagnostic data; this presents compelling opportunities to deploy analogous analytic techniques. In this talk, I will briefly discuss some of the many ways in which visualization and analysis may be crammed into the scientific workflow as well as utilized on machine-specific data. I will also provide a practical introduction to mesh-based HPC visualization using VisIt, an open source parallel scientific visualization and data analysis platform.