High performance computing (HPC) is the use of parallel processing so that to aggregate computing power and obtain much higher performance than the one of a typical computer and solve large scale and complex problems in various fields, such as science, engineering or business.
HPC has made possible the solution of the most advanced problems in an efficient, reliable and quick way. The performance of supercomputers is measured in floating-point operations per second (FLOPS) and it worths mention that some supercomputers work at more than a petaflop or 1015 floating-point operations per second.
In the systems with massive numbers of processors, there are two operational options to follow. In the first one, hundreds or thousands of computers are distributed across a network and contribute to the solution a common problem; all of them report the results to a central server, which is responsible for the integration of all these bits and pieces and the production of the overall solution. In the second option, hundreds or thousands of processors are placed nearby in a cluster and work together on a common task, eliminating moving data around, which can be extremely time consuming.
Although supercomputers are mostly used by scientific researchers, engineers, academic institutions and government agencies, the growing demand for processing power and speed has made HPC essential for business of all sizes and fields.