The applications of HPC systems are generally those large-scale computations beyond the reach of ordinary computers, including medi- cal imaging, genetic analysis and comparison, computer animation, energy exploration, climate simulation, astronomy, space, and various physical and chemical computations. The nodes of a HPC system work in parallel, i.e. they have to compute while processing tasks as well as exchange data with each other during rocessing. The performance of a HPC system is proportional to the scale of the given cluster. In contrast, the performance of a set of HPC systems is the sum of the processing capacities of the nodes within the given cluster. There are many classifications applicable to HPC systems, but typically they can fall into one of three types of classifications.