General topicsTechnique

What is a supercomputer and its features?

What is a supercomputer and its features?

What is a supercomputer ? A supercomputer is a computer whose capacity to work is much higher than that of an ordinary computer. This is why the word “super” is used in it. These computers are used only because of their high-performance systems. These computers were used primarily for scientific and engineering tasks that required high-speed calculations.

Their processing speed is thousands of times faster than all other normal computers. Here today in this article we will learn about the so-called supercomputer, how it works , and what are its advantages compared to the rest of the traditional computers.

So let’s get started without delay and get complete information about what a supercomputer is.

The so-called supercomputer What is the supercomputer?

Before knowing what a supercomputer is, if we know what a computer is, it will be easy for us to understand it. Speaking of computer, it is a multi-purpose device that takes information (data) through an input process, stores it and then processes it as needed, and eventually produces some kind of output.

Whereas if I’m talking about a supercomputer, it’s not only a much faster computer and a very large computer: it works quite differently, usually using parallel processing instead of sequential processing like normal processing is used in a computer. So instead of doing one thing at a time, he’s doing multiple things at once.

A supercomputer is a computer that is currently running at the highest operating rate. It is called Mahasanganak. After all, where is the supercomputer used?

Traditionally, supercomputers are mostly used for scientific and engineering applications so that they can handle large databases as well as perform large amounts of calculations. In terms of performance, it runs thousands of times faster and more accurate than regular computers.

Supercomputer performance is measured in FLOPS, which means floating point operations per second. Therefore, the more times it loads on the computer, the more powerful it is.

What is supercomputing?

Supercomputing is a form of high-performance computing that defines or computes using a powerful computer, a supercomputer. Also, using it, the final result can be found in the shortest possible time.

What is serial and parallel processing?

Let us know what is the difference between serial and parallel processing ? In a normal computer, only one work is performed at a time, which means that after only one task is completed, another work is processed, and this processing is called sequential processing .

For example, a man sitting in the grocery store in a mall, after picking up any item that comes in the conveyor belt, he scans it with a scanner and passes it to the customer’s bag, doing the work in a distinct chain of operations that is why it is called sequential processing.

Here, no matter how quickly you keep things in the conveyor belt or fill things in your bag after scanning, but the speed of this process depends on the speed of scanning or processing of that operator, which is always one item at a time. happen in. The best example of this is the Turing machine .

Whereas the typical modern supercomputer runs at very high speed, breaking the problem down into small parts and working one piece at a time. So this process is called parallel processing.

If there are many friends at grocery checkout, divide items among themselves and checkout together at different counters and later collect all things in one place, it will get the work done very soon and won’t take much time. Since the work is divided here, it didn’t take much time to get the processing done. This is why parallel processing is very fast compared to serial processing.

Larger and more powerful supercomputers use parallel processing. With this, they can perform any operation quickly and in less time. When it comes to large and complex work like weather forecasting, genetic synthesis, mathematical modeling, etc., we really need computing power. In such a situation, parallel processing is more useful for a supercomputer. In general, there are two basic methods of parallel processing: Symmetric Multiprocessing (SMP) and Massive Parallel Processing (MPP).

What are clusters?

If you wish, you can build a supercomputer where you have to put many processors in a giant box and instruct them to solve complex problems in which they can use parallel processing.

Or there is another way in which you have to buy multiple impersonal computers and put them in the same room, and also connect them together with the help of a fast local area network (LAN) so that they work widely in the same way. This type of supercomputer is called a cluster. Google uses these cluster supercomputers for its users’ web searches in its data centers.

What is the network?

A network is also a supercomputer very similar to a cluster (i.e. a group of separate computers), but has computers in different locations with each other over the Internet (or any other computer network). This type of computing is also called distributed computing, where the power of a computer is spread to multiple locations as opposed to a single location (central computing).

For example, the CERN Worldwide LHC Computing Grid, in which data from the LHC (Large Hadron Collider) particle accelerator are collected in one place, and a grid supercomputer was used for this.

The chances of more failures in Grids Supercomputer are lower, since all computers are connected to each other, so you get rid of problems caused by parallel processing, where crashes are common.

What is the operating system used in supercomputers?

You might be surprised to learn that to power supercomputers, only normal operating systems are used that we use to power our computers, but we know that more modern supercomputers actually have caravans and non-self workstations. It consists of groups.

Until a few years ago, Unix was used depending on the operating system, while today Linux is used instead. It is open source . Since supercomputers are generally solving scientific problems, their application programs are written in traditional scientific programming languages ​​such as Fortran, or in more popular modern languages ​​such as C and C++.

Supercomputer Features

If we talk about ordinary computers, then MIPS (Million Instructions Per Second) is used to measure their computing speed. Through it the processor manages basic programming commands such as reading, writing, storing, etc. To compare two computers, their MIPS is compared.

But the way supercomputers are evaluated is a little different. Since most scientific computations are done in this, it is measured by floating point operations per second (FLOPS). Let’s see the list made according to these FLOPS.

lonliness flops Example decade
a hundred flop 100 = 10 to the power of 2 ENEAC ~Forties
KFLOPS (kiloflops) 1000 = 10 to the power of 3 IBM 704 ~ fifties
MFLOPS (mega flops) 1000000 = 10 to the 6 power CDC 6600 ~ 1960s
GFLOPS (Gigaflops) 1000000000 = 10 to the 9th power Cray-2 ~ 1980s
TFLOPS (teraflop) 1000000000000 = 10 to the 12 ASCI Red ~ 90’s
PFLOPS (Petaflops) 1000000000000 = 10 to the power of 15 Jaguar ~ 2010
EFLOPS (Exaflop) 10000000000000000000 = 10 to the power of 18 ????? ~ 2020s

super computer price

Supercomputers are very expensive. NEC’s in-house supercomputers typically carry multi-million dollar price tags, with even lower-cost models costing around $100,000.

When was the supercomputer invented?

If you study the history of computers, you will find that not one individual contributed to them, but many people have contributed from time to time. Somewhere then we got to see such amazing machines. But when it comes to the supercomputer , a great deal of the credit goes to Seymour Cray (1925-1996) . Because his contribution is the highest in supercomputers. You can also call him the father of the supercomputer.

946: John Mowgli and J. Presper Eckert built ENIAC (Electronic Numerical Integration and Computer), at the University of Pennsylvania. It was the first general-purpose electronic computer, was about 25 meters (80 ft) long and weighed about 30 tons. It was designed to deal with military scientific problems and was the first scientific supercomputer.

1953: IBM developed the first general-purpose mainframe computer, called the IBM 701 (also known as the Defense Calculator), and about 20 machines were sold to various government and military agencies. The 701 was the first supercomputer on the market. Gene Amdahl, an engineer from IBM, later redesigned it and named its upgraded version the IBM 704, a machine with a computing speed of about 5 KFLOPS (5000 FLOPS).

1956: IBM then develops the Stretch supercomputer for Los Alamos National Laboratory. It was the world’s fastest supercomputer about 10 years ago.

1957: Seymour Cray co-founded the Control Data Corporation (CDC) this year and pioneered the creation of fast, mobile, high-performance computers, including the CDC 1604 (announced 1958) and 6600 (released in 1964), which challenged In earnest, IBM’s dominance of central computing.

1972: Leaves Cray Control Data and creates its own Cray Research and builds high-end computers – the first true supercomputer. Their main idea was how the connections within the machine could be reduced so that the machines could be faster. Previous Cray computers were often C-shaped, so they could be separated from other machines.

1976: The first Cray-1 supercomputer is installed at Los Alamos National Laboratory. His speed at the time was about 160 MFLOPS .

1979: Cray then developed a faster eight-processor model, the 1.9 GFLOP Cray-2. In this, the wire connections were dropped from 120 cm to 41 cm (16 in) compared to previous figures.

1983: Thinking Machines Corporation manufactured a large-scale parallel processing machine, which used about 64,000 parallel processors .

1989: Seymour Cray founded a new computer company, Cray Computer, where he developed Cray-3 and Cray-4.

1990: Due to cuts in defense spending and the development of powerful RISC workstations, companies such as Silicon Graphics pose a serious threat to supercomputer makers.

1993: Fujitsu Numerical Wind Tunnel builds the world’s fastest computer with 166 vector processors.

1994: Thinking Machines file for bankruptcy protection.

1995: Cray Computer also began to sink due to financial difficulties, so it filed for bankruptcy protection. Besides, Seymour Cray died suddenly in a road accident on October 5, 1996.

1996: Cray Research (the original company of Cray) was acquired by Silicon Graphics.

1997: ASCI Red, a supercomputer built from Pentium processors by Intel and Sandia National Laboratories, becomes the world’s first Teraflop (TFLOP) supercomputer.

1997: IBM’s Deep Blue supercomputer defeats Garry Kasparov at chess.

2008: The Jaguar supercomputer, built by Cray Research and Oak Ridge National Laboratory, became the world’s first petaflop science supercomputer (PFLOP). which were later overtaken by the machines of Japan and China.

2011-2013: The Jaguar was extensively (and expensively) upgraded, dubbed Titan, and later became the world’s fastest supercomputer, which was later downgraded by the Chinese machine Tianhe-2.

2014: European consortium Mont-Blanc announces that it is building an exaflop (1018 FLOP) supercomputer with energy-efficient processors for smartphones and tablets.

2017: Chinese scientists announce that they are making a prototype of an exaflop supercomputer, which is based on Tianhe-2.

2018: China is at the forefront of the race for the fastest supercomputer, their Sunway Taihu Lite is currently the fastest supercomputer in the entire world.

What are the 5 fastest supercomputers in the world?

There is a lot of competition in all countries in terms of computing power, and who can be on top, but the place for the top is the same. Peak performance in supercomputing is always changing. Even in the definition of a supercomputer it is written that it is such a machine that “always runs at its highest operating rate.”

Due to the competition, it makes supercomputing more interesting, since scientists and engineers are always continuing their research at better and better computing speed. Let’s get to know the top 5 supercomputers in the world .

  • Sunway Taihulite (China)
  • Tianhe-2 (China)
  • Biz Dent (Switzerland)
  • Gyoko (Japan)
  • Titan (USA)

supercomputer name in india

Do you know when India’s first supercomputer Param 8000 was launched? It started in 1991 in India. India also has some supercomputers in India. Let’s know the name of the supercomputer in India.

  • SahasraT (Cray XC40)
  • Aditya (IBM / Lenovo System)
  • TIFR Color Boson
  • IIT Delhi HPC
  • Baram Uefa 2

How many supercomputers are there in India?

There are more than 40 supercomputers in India.

What is the fastest supercomputer in India?

PARAM SIDDHI AI is India’s fastest supercomputer.

What is the first supercomputer in India?

The PARAM 8000  supercomputer , was India’s first supercomputer. It was made by India itself.

What did you learn today

I hope I have given you complete information about what is a supercomputer and I hope you have understood what is a supercomputer. If you have any doubts about this article or if you want there to be some improvement in it, you can write low comments on it.

Through these ideas of yours, we will get a chance to learn something and improve it. If you liked this post of my supercomputer or learned something from it, please share this post on social networks like Facebook, Twitter, etc. to show your happiness and curiosity.

Related Articles

Back to top button