Many a times we wonder what actually is High Performance Computing, What purposes does a High Performance Computing serve, how a High Performance Computing is different from our Personal Computers. Here I have tried to put all the answers together. As we all know High Performance Computing is the fastest computing way of its generation. It can solve problems which is not possible to be solved by our Personal Computers. The processing speed of a High Performance Computing is thousand times better than that of a Personal Computer and that is why we call it High Performance Computing. Thus we can conclude that High Performance Computing refers to aggregation of power in a computer so that we can use it for solving problems in engineering, business etc. which cannot be solved by desktop computers or others simple computers.
High Performance Computing
To achieve more than the normal operational ability in terms of throughput. Actual operation of an algorithm
In simple terms High Performance Computing provides a Computing technique which is much faster and accurate than other Computing techniques.
Why High Performance Computing?
1. Universities, Research Organizations usually use High Performance Computing to match the speed they require.
2. Super computers are most expensive machines.
3. Small organizations cannot afford this.
4. However most of the organizations need more computing power to solve business problems.
5. Right solution is HPC that bridges this gap.
Goals of High Performance Computing
1. Increase processing speed.
2. Reduce cost.
3. Increase efficiency and achieve Scalability.
Types of HPC
High Performance Computing can be achieved using:
- Super computers
- Cluster computers
- Super Computers: Offers much faster processing speeds. Their memory systems and interconnects are much better. They are used for Fluid dynamics and Weather forecasting.
Super Computers
- Cluster computers: Cost effective technology for HPC. Users are turning to use Clusters of Computers instead of traditional use of Super computers for high speed purposes. Cluster Computers are used in bio-informatics and in the operation of genes.
Cluster Computer
Results has shown that Cluster Computing is better than Supercomputing. Reasons for the same are:
Price/performance: It provides better order of magnitude than Super computers.
Individual HPC resource: One of the original goals of the Beowulf clusters was to put more computational power in the hands of the individual.
Machine adaptability: New codes can be designed without changing the previous codes.
Open source: The classic Beowulf cluster is made on Linux and other open sources.
Open standards: Because of this we can write standards and can run that code to any system.
