ABSTRACT
Petascale simulations utilize the massive computational power available from supercomputers to simulate scientific phenomena at previously unseen levels of detail. Resulting from simulations being performed at such a scale is the ability to easily generate several terabytes of a data in a single day. A more clear-cut goal is to build the global database in situ, performing data reorganization, indexing, reduction, and so on to optimize post-simulation query processing, rather than doing all these data-intensive operations from disk. In any scientific simulation, the application scientist is looking to understand certain phenomena that may be easy to analyze in the physical world. An example of such a pattern is the vortex of a fluid flow, including fluids such as liquid, gas, and plasma. Scientific simulations not only help to understand a physical phenomenon but also provide information that will help replicate the phenomenon under controlled settings.
