Half a century later, even the smallest computer would have occupied a whole room. And today, thanks to microchips, even more powerful computers than ever before are stuck in the pocket. But have you ever wondered how powerful a home-sized computer would be if it were built with these tiny chips? Is it possible to make a super computer in this way? ারWho has super computing power a million times more than you or my laptop or desktop, and it can solve any complex scientific problem in the world? Today's question is, exactly what features help a simple computer to become a super-computer? How is a supercomputer different from your current computer? Let's know all the information about super computing in detail.
What is a super computer?
So, what are the super features that make a computer called a super-computer? Due to the computer to fly? Because of the laser light fence from the computer's CPU? 😛 Or because of the built-in ammunition and cannon with the computer? Hey one minute! It's not super man, super-computer!
In simple terms, computers that are extremely fast, can solve complex scientific problems, can predict the weather, or can predict what the climate of 2050 will be like, and computers that can do such extraordinary things are called supercomputers. Now you might ask, just how fast does a computer work? If I add more RAM and more core processors, more GPUs to my computer, can I do supercomputing too? In order to fully understand the definition of supercomputer that I have given in "simple language", you must first be aware of some of the terms.
Before entering today's main question, we need to know what is a computer? It is basically a machine that completes any simple task. It first receives input data, then processes it into its own power, and finally produces an output result. In fact, a supercomputer means that it has to be a giant computer, or a million-billion times faster than your ordinary computer, but not at all; In fact, it uses completely different methods to accomplish a task. Like your normal desktop or laptop, it does many things at once, not just one at a time. And this is basically the main feature that makes a computer a super computer.
Serial and parallel processing
What is the difference between serial and parallel processing? A normal computer can perform only one task at a time, meaning that it completes one task after another to complete a task and provides the output of the task. And this is called serial processing. Now you might say, "Hey, I play music with my computer at the same time, browse the internet and render videos, and you say one thing at a time"? In fact, your computer can complete millions of commands per second, making it seem like real time to you, even if you do a series of tasks one after the other. Let's try to make the matter clearer with a beautiful example. Imagine for a second you were transposed into the karmic driven world of Earl. Imagine for a second you were transposed into the karmic driven world of Earl. What he will do now he will first get up from his seat, then go to the flour packet rack, bring the flour packet, hand it to you, and count the cash you have given and put it in the drawer. Now look at how quickly he got up from his seat or how quickly he brought flour from the rack and handed it to you, it does not matter. The point is, he's only doing one thing at a time. No matter how fast he provides services to you, he is doing one thing at a time and serving you by doing one thing after another. This is how ordinary computers complete their work.
But today's modern supercomputers work in completely different ways. It divides a task into different parts and processes them at the same time, and this working system is called parallel processing. Now, according to the example above, remember which store you went to to buy 1 kg of flour, 1 liter of oil, and 1 kg of sugar. Now suppose there are 3 people together in that shop to help that shopkeeper. Then everyone can choose a different job one by one to deliver the things you want to you. Someone will bring sugar, someone will bring oil and someone will supply flour and in the same time you will be able to settle the money transaction with the shopkeeper. Notice again, everyone brings different things at the same time but all of them are coming to you together. This way, no matter how many things you want to buy in the store, if there are a lot of people working there, it is possible to complete all the work much faster in the same time. And this is parallel processing, theoretically, our brain also works in parallel processing. At the same time you are reading this article again at the same time your brain is continuing the full internal activity of your body.
Why is parallel processing necessary in super computing?
The computers we use on a regular basis do not need to be so efficient. Browsing the Internet, sending emails, or typing requires very little processing power on your computer. But if you want to do a lot of complex work like changing the color of a very large resolution digital photo, your computer will have to do a lot of processing, which can take up to a few minutes to complete. If you want to do gaming on your computer without just browsing the internet, sending emails, or typing, you will need a lot of fast processor, dedicated GPU and more memory (RAM), otherwise your system will work slow. Fast processor, and with double the memory, your computer will start working dramatically faster. But how fast? This speed also has a limit — because a processor can only do one thing at a time.
Now suppose you are a scientist and you work in a weather office. You need to work together on weather forecasting, new cancer drug tests, and climate modeling by 2050. Now you can upgrade your PC's processor and more memory to complete these tasks, although it will work faster than before, but it still has a working limit. However, if your work is divided into one piece and each piece is worked with a separate processor, ie parallel processing, then your work will be done much faster and more efficiently than before.
Parallel computing
To create a supercomputer, supercomputing requires many processors at once — so that they can work together in parallel and complete many tasks at the same time. The fastest supercomputer of today is The Sunway TaihuLight. It has 40-bit 40,960 multicore processors and 256 processing cores on each processor chip. This means that there are 10,649,600 processors in this entire computer !!!
Parallel computing is certainly an ideal system for supercomputing, but there are some serious problems with parallel computing. Let's go back to the example of that store, but this time we will take the example with the supermarket. Suppose you went to the supermarket with some of your friends to buy some things. Now if you send each of your friends to a separate counter to get some things, in a very short time your things will be bought, and at the end of the shopping all the things will be collected for you. In the same way, a supercomputer completes a task by cutting it into pieces by different processors and then combines the pieces and gives the output. But if a task is too big, sending that task to the processor in pieces and assembling all the pieces at the end of the task becomes a very difficult task for a computer. To do this requires another management system so that each task is delivered to the processor in pieces and the returned pieces are put together and output. But to process this management system also requires a lot of processing power, which can overload the system. Windows OS's Task Manager, for example, displays the processing of almost all programs, but also requires some processing power to display them.
You may be able to complete the shopping in less time by sending your friends to different counters, but it will be too late to pay. Suppose you come to shop for millions of items together and 50,000 friends are collecting items from different counters. If you were shopping from one counter at a time, the cash pay problem would be solved at one counter, but shopping at different counters would result in one problem being split into 50,000 problems.
Similarly, suppose you give a command to a computer to forecast the weather for the next week in front of the whole world. Now your computer will send all this work piece by piece to different processors for processing, if you did the work in one processor then all the processing would be done at once. But in order to process in different processors, the weather forecast of different countries will be processed repeatedly in different processors in each processor. Butt problems can be more serious, because the climate of different countries of the world may be completely different from one country to another. As a result, one processor will have to wait for another processor to finish — and one will need help from another processor to solve the problem. So some work in super computer needs to be done in parallel and some work in serial processing.
Super computing
Types:
It is possible to make a super computer by putting thousands of processors, RAM and GPU in a huge box and doing many complex tasks by doing parallel processing. Or you can make a super computer by connecting many PCs together in the same room with many fast LAN (local area network) cables. This type of supercomputer is called a cluster. Google uses this type of computer to provide search results to its users.
Another type of supercomputer is called a grid - much like a cluster, but different computers are located in different parts of the world and are connected to each other using the Internet or other computer networks. This is an example of a lot of distributed computing, where computers all over the world work together on a single network. You can also call it virtual super computing. Different varsities or research centers around the world make grid supercomputers by connecting their computers to each other. Not every computer on the grid works at the same time, or they don't have to, but together they form a powerful computing system.
Management:
Cluster supercomputers are grouped together across a large space, many times that space can be equal to 3-4 football fields. And these giant-sized computers require a huge amount of electricity to run, with this amount of electricity it is possible to run thousands of homes. Millions of dollars are needed to operate supercomputers to consume so much electricity.
Supercomputers also generate a lot of heat, because when electricity flows through a cable, it also generates heat energy. And for this your normal computer also needs cooling system. But these huge computers can no longer be cooled by ordinary fans. Today's modern supercomputers are cooled by liquids, just as refrigerators do. It costs a lot of electricity to operate this cooling system, secondly it is also harmful to the environment.
Super software runs on which software?
As I said before, a computer is a machine that can do all the normal work (of course virtual 7). If you want, you can run your computer on a supercomputer using your computer's operating system, such as Windows! But most supercomputers run on Linux-based operating systems. These operating systems are highly customizable, meaning they are only made with specific work features. Since supercomputers are primarily used to solve a variety of scientific problems, what need is there for other working features?
What is the use of super computing?
Since the computer is a machine for all common tasks, you can read articles on Internet browsing, mail sending, photo editing, video editing, gaming and even Wirebd with a super-computer. You will need to run various programs on your system to perform these tasks just like your normal computer. Just like you need different apps (applications) to do different things on your Android or iPhone, these are computer programs, but they have different names!
Supercomputers do not do this at the moment. It is used to solve various complex mathematical problems, to solve scientific problems, nuclear missile tests, weather forecasting, climate change, and to test the intensity of encryption. But theoretically, it is possible for a supercomputer to do all the work that your normal computer does.
How powerful is the super computer?
Ordinary computers express their ability to work in the form of MIPS or Million Instructions Per Second. It indicates how many commands (read, write, data store) the system can process to complete a task. MIPS makes it easy to compare two processors, the more powerful a processor is able to operate in MIPS. This is commonly known as processor speed, which is basically expressed as GHz.
But the ability of supercomputers to work is expressed differently. Since these computers are used for scientific purposes, their capabilities are calculated as FLOPS Floating Point Operations Per Second. This is an efficient way to calculate the working capacity of a computer. Let's try to understand these two terms with a short example.
Suppose you are watching a football match, you see that the No. 1 player now has the ball. He got the ball into the goal and scored the goal. And in this way 3 more goals were scored through hits of different players. Now, here MIPS means how many hits the ball has to take from the player to complete a goal. And FLOPS means how many goals that team has scored. This means that the number of millions of commands a processor has to follow to perform one task per second is expressed by MIPS and the number of tasks completed per second is expressed by FLOPS.
Last Phrase:
In terms of computing, we are gaining an admirable ability day by day. The computing devices in today's pockets are much more powerful than the equivalent of a home computer 20 years ago. Today we have almost reached the top of super computing, now let's wait for quantum computing. It may soon be too busy
Comments
Post a Comment