What Are Supercomputing, High-Performance Computing and Cloud Computing?
In recent years, the terms “supercomputing”, “high performance computing” and “cloud computing” have often been talked about, but most people do not seriously understand what they are and what the difference is. This article will answer these questions in detail for you.
Supercomputing is based on supercomputer. Supercomputers are computers capable of supercomputing. Supercomputing uses computers to research, design products and support complex decisions. In addition to the most advanced computing hardware systems, it also includes software systems and testing tools, and algorithms to solve complex computing. At present, China’s supercomputers are in the leading position in the world. In last year’s supercomputer 500 strong selection, China’s “Sunway TaihuLight” won the championship. Although such a giant has been developed, the specific application of supercomputers in China is still in a relatively backward position compared with the United States and Germany.
High Performance Computing, referred to as HPC, is the application of high-performance computers. High-performance computers are parallel computers composed of traditional ultra high-speed computers and multiple CPU. However, generally speaking, HPC is almost equivalent to supercomputing, mainly for scientific computing, engineering simulation, animation rendering and other fields, belonging to the computing-intensive applications. The design and manufacture of private cars, the orbit simulation of space shuttles, the design of Nike shoes, the development of drugs and so on all belong to the category of high performance computing. At first, high performance computing was used in cryptography, meteorological monitoring and so on. Later, it was extended to many simulation, such as the first principles of condensed matter physics, finite element analysis and so on. At present, the artificial intelligence industry is booming again, which involves deep learning, machine vision and so on. It needs to provide a lot of algorithmic support, which also injects new vitality into HPC.
Cloud computing and HPC are two completely different concepts, although their concepts overlap in recent years, but the starting points are completely different. The National Institute of Standards and Technology (NIST) defines cloud computing as a pay-per-use model that provides available, convenient and on-demand network access to the configurable computing resource sharing pool (resources include network, server, storage, application software, services). These resources can be provided quickly with little management effort or little interaction with service providers. In other words, cloud computing is a business technology that distributes and pays for on-demand. It is currently mainly used in Web 2.0, social networks, enterprise IT construction and informatization.
The table above gives a comparison between HPC architecture and cloud computing architecture. It can be seen that cloud computing architecture has virtualization technology and can have better user interface. However, in terms of hardware facilities, cloud computing is still very backward compared with HPC. And the industry may pay more attention to virtualization, flexibility and dynamic research, ignoring the development of computer system technology, which is also the current cloud computing hard power less than HPC. Perhaps in the near future, cloud computing platforms will eventually replace HPC infrastructure, but the road is still long.
At present, the construction of cloud computing data center is highly concerned. Comparing with general data centers and computer rooms, cloud computing data centers pay more attention to flexibility, enabling users to pay on demand like cloud computing in terms of line, IP, etc. Cloud computing data center is a new power of current data center. Optical interconnection devices with high performance, low power consumption, low cost and high reliability are the general trend. Recently, Gigalight (www.gigalight.com) officially launched the 100G QSFP28 CLR4 optical module for professional data center. Compared with the CWDM4 optical module which requires link support for FEC (forward error correction), CLR4 supports both links with FEC and links without FEC, and achieves excellent results in HPC, cloud computing data center and other scenarios.
This is an original article wrote by Gigalight. If reproduced, please indicate the source: https://www.gigalight.com/community/posts/tutorials/what-are-supercomputing-high-performance-computing-and-cloud-computing.html