Even if your organization has researched the benefits and advantages of using a supercomputer to tackle tough and complicated problems, you will find that supercomputers also present some disadvantages. The larger and more powerful the supercomputer is, the more infrastructure and maintenance it requires to perform the calculations you intend to achieve.
Storage and Bandwidth
Researchers use supercomputers to do work with enormous sets of data which they process at a high rate while generating increasingly large amounts of additional data, such as when scientists work on weather forecasting or simulate nuclear bomb detonations. A disadvantage is that supercomputers require massive external storage drives whose bandwidth is fast enough to accommodate the data being analyzed and produced. If storage and bandwidth can’t keep up with the data flow, the supercomputer will not be able to work at its full capacity.
Maintenance and Support
Supercomputer systems are built by connecting multiple processing units and can require large rooms to store them. The large number of processors give off greater heat than standard computers, which is a disadvantage because they require a cooling infrastructure. The supercomputer also needs software to monitor how it is used and to detect failures, and a larger than typical support staff to administer and support the computer, its external storage and high-speed network.
A supercomputer that can simulate the location of potential oil deposits or the progress of various permutations of a hurricane system can cost a lot of money, which could be a disadvantage if your organization must work with a limited budget. For example, an IBM Watson supercomputer” costs about $3 million, according to Computerworld magazine. The Fujitsu’s K Computer for the Riken Advanced Institute of Computational Science in Kobe, Japan cost $1.2 billion to build and requires $10 million per year for operational costs, according to the Atlantic.
Unlike ordinary desktop computers that may finish calculating a problem in a few minutes or overnight, supercomputers work on tasks that require intensive calculations which can take extremely long periods to complete. For example, a supercomputer could spend months performing calculations to support research on climate change or to help cure a disease, presenting a disadvantage to people who are in a hurry for quick results.