Many have seen the abbreviation GPU, but not everyone knows what it is. This component which is part of video cards... It is sometimes called a video card, but that is not correct. The GPU is engaged processing commands that form a three-dimensional image. This is the main element, the power of which depends on performance the entire video system.
There is several types such chips - discrete and built-in... Of course, it’s worth mentioning right away that the first one is better. It is put on separate modules. It is powerful and requires good cooling... The second is installed on almost all computers. It is built into the CPU, making the power consumption significantly lower. Of course, it cannot compare with full-fledged discrete chips, but at the moment it shows quite good results.
How the processor works
GPU is engaged processing 2D and 3D graphics. Thanks to the GPU, the CPU of the computer becomes freer and can perform more important tasks. The main feature of the GPU is that it tries to maximize increase speed calculation of graphic information. The chip architecture allows more efficiency process graphic information than the central CPU of a PC.
GPU sets location three-dimensional models in the frame. Is engaged in filtration of the triangles included in them, determines which ones are in sight, and cuts off those that are hidden by other objects.
What do we look at first when choosing a smartphone? Aside from the cost for a moment, the first thing we do, of course, is the screen size. Then we are interested in the camera, the amount of the operative, the number of cores and the frequency of the processor. And here everything is simple: the more, the better, and the less, the worse, respectively. However, modern devices also use a graphics processor, aka GPU. What it is, how it works and why it is important to know about it, we will describe below.
GPU (Graphics Processing Unit) is a processor dedicated exclusively to graphics processing and floating point computing. It primarily exists to ease the work of the main processor when it comes to resource-intensive games or 3D graphics applications. When you play a game, the GPU is responsible for creating graphics, colors and textures, while the CPU can do the artificial intelligence or calculations of the game's mechanics.
The GPU architecture is not very different from the CPU architecture, however, it is more optimized for efficient graphics handling. If you force the GPU to do any other calculations, it will show itself from the worst side.
Video cards that plug in separately and run at high power only exist in laptops and desktops. If we are talking about Android devices, then we are talking about integrated graphics and what we call SoC (System-on-a-Chip). For example, the processor has an integrated Adreno 430 graphics processor. The memory it uses for its work is system memory, while graphics cards in desktop PCs are allocated memory available only to them. True, there are also hybrid chips.
While a multi-core processor runs at high speeds, a GPU has many processor cores running at low speeds and only doing vertex and pixel computation. Vertex machining mainly revolves around a coordinate system. The GPU handles geometric tasks by creating three-dimensional space on the screen and allowing objects to move around it.
Pixel processing is more complex and computationally intensive. At this point, the GPU applies various layers, applies effects, does everything to create complex textures and realistic graphics. After both processes have been processed, the result is transferred to the screen of your smartphone or tablet. All this happens millions of times a second while you are playing a game. 
Of course, this story about the work of the GPU is very superficial, but it is enough to get the correct general idea and be able to keep up a conversation with friends or an electronics seller, or understand why your device is so hot during the game. Later, we will definitely discuss the advantages of certain GPUs in working with specific games and tasks.
Based on materials from AndroidPit
We all know that a video card and a processor have slightly different tasks, but do you know how they differ from each other in the internal structure? As a CPU (eng. - central processing unit) and GPU (eng. - graphics processing unit) are processors and have a lot in common, but they were designed to perform different tasks. You will learn more about this in this article.
Cpu
The main task of the CPU, in simple terms, is to execute the chain of instructions in the shortest possible time. The CPU is designed in such a way as to execute several such chains at the same time, or to split one stream of instructions into several and, after executing them separately, merge them back into one, in the correct order. Each instruction in a thread depends on the ones following it, which is why there are so few execution units in the CPU, and all the emphasis is on execution speed and reducing downtime, which is achieved using the cache memory and the pipeline.
GPU
The main function of the GPU is rendering 3D graphics and visual effects, therefore, everything is a little simpler in it: it needs to receive polygons at the input, and after carrying out the necessary mathematical and logical operations on them, output the pixel coordinates at the output. In fact, the work of a GPU comes down to operating on a huge number of independent tasks, therefore, it contains a large amount of memory, but not as fast as in a CPU, and a huge number of execution units: in modern GPUs there are 2048 and more, at that time like a CPU, their number can reach 48, but most often their number lies in the range of 2-8.
The main differences
The CPU differs from the GPU primarily in the way it accesses memory. In the GPU, it is connected and easily predictable - if a texel of a texture is read from memory, then after a while the turn of neighboring texels will come. The situation is similar with recording - a pixel is written to the framebuffer, and after a few clock cycles, the one located next to it will be recorded. Also, the graphics processor, unlike general-purpose processors, simply does not need a large cache memory, and textures require only 128–256 kilobytes. In addition, faster memory is used on video cards, and as a result, the GPU is available at times more bandwidth, which is also very important for parallel calculations operating with huge data streams.
There are many differences in multithreading support: CPU executes 1 – 2 computation threads per processor core, and the GPU can support several thousand threads per multiprocessor, of which there are several in the chip! And if switching from one thread to another for the CPU costs hundreds of cycles, then the GPU switches several threads in one cycle.
In the CPU, most of the chip area is occupied by instruction buffers, hardware branch prediction and huge amounts of cache memory, while in the GPU, most of the area is occupied by execution units. The above device is schematically shown below:
Computation speed difference
If the CPU is a kind of "boss" who makes decisions in accordance with the instructions of the program, then the GPU is a "worker" who performs a huge amount of the same type of calculations. It turns out that if you supply independent simple mathematical problems to the GPU, then it will cope much faster than the central processor. This distinction is successfully used by bitcoin miners.
Bitcoin mining
The essence of mining is that computers located in different parts of the Earth solve mathematical problems, as a result of which bitcoins are created. All bitcoin transfers along the chain are transferred to miners, whose job is to select from millions of combinations a single hash that matches all new transactions and a secret key, which will ensure the miner receives a reward of 25 bitcoins at a time. Since the computation speed directly depends on the number of execution units, it turns out that GPUs are much better suited for this type of task than CPUs. The greater the number of calculations performed, the higher the chance of getting bitcoins. It even came to the construction of entire farms from video cards.
You have decided to buy a computer. Walk along the shopping arcade, look at the price tags, get acquainted with the characteristics. And the question arises: what is a GPU? Often you see this combination of letters, but you don't see the meaning. Let's try to explain.
GPU - what is it, and how is it different from a CPU
GPU stands for "graphics processing unit", or graphics processor. It is a separate device for a game console, computer, camera. Responsible for rendering graphics, performs it. The GPU copes with this task remarkably, due to the pipeline architecture specially designed for these purposes. Modern GPUs are much better at handling graphics than their counterparts, classic central processing units (CPUs).
Currently, the GPU is used as a 3D graphics accelerator, but in exceptional cases it can be used for computations. The following distinguishes the GPU from the CPU:
- architecture: it is aimed to the maximum at high speed of calculating complex graphic objects and textures;
- relatively low set of commands.
The colossal computing power is explained precisely by the peculiarities of the architecture. Along with modern CPUs containing multiple cores (2/4/8, which was already considered a breakthrough), the GPU was originally designed as a multi-core structure. There are hundreds of cores here!
The difference in architecture also explains the difference in the principle of operation. If the CPU architecture is designed for sequential data processing, then the GPU was originally designed to work with computer graphics, therefore it is designed for massive, but parallel computations.
Each of these architectures has its own advantages. The CPU is much better at performing sequential tasks. For huge amounts of processed information, the GPU has an advantage. The main condition is that parallelism must be observed in the task.
Now you know a lot about GPUs, what a GPU is, and you can even tell your friends.
The motherboard contains many important components of the computer, which bear their unique names: CPU, GPU, HDD, SSD, RAM, and so on. Each of these abbreviations has its own interpretation, but at the moment it matters, what is it - a GPU?
There is a similar name to this term - it is CPU. Many inexperienced users confuse these names, which is incorrect. To begin with, it is worth explaining that the CPU is the central processing unit, which is the brain of the entire system. This abbreviation stands for Central Processor Unit.
However, it is worth knowing that a GPU is also a processor, only a graphics solution. Its task is to process and display the image. The full name of the abbreviation looks like this - Graphic Processing Unit.
Thanks to these explanations, it can be understood that the GPU is not a central processing unit that only processes data of a graphical type. It obeys the protocols of the central processor and, unlike it, has its own logical device. Just like the main processor, the graphics processor has cores, only there are not dozens of them, but thousands. Such a large number of cores are needed to receive and process data associated with drawing and temporary numerous tasks.
Now that you already have a general idea that the GPU is a graphics processor and its task is to process graphics data, you can go on to enumeration.
Currently, there are two types of integrated graphics processors - integrated into the motherboard and integrated into the processor.
In the first version, the GPU chip is soldered directly to the motherboard's PCB, and few people know that this is a GPU. It looks like an ordinary black chip, which has the brand name, serial number and a combination of numbers that indicates some parameters. Since such graphics solutions do not have their own memory size, they borrow this parameter from the RAM, using its size.
In the case of a chip built into the processor, it is difficult to see it; it will only work when parsing the central processor itself. Almost all new generation processors have an additional core called the graphics core. At the same time, the price of the processor does not grow much, but it eliminates the need for a discrete video card.
Integrated graphics processors save tens of percent on power consumption, which has a positive effect on heat dissipation. However, there are significant drawbacks, and one of them is poor performance. These economical graphics are well suited for office and low-power applications.
GPU in a computer - what is it and how to identify it? If previously two types of integrated graphics processors were presented, then further you can consider the option of a discrete video card. Based on this, it can be understood that GPU is only a designation for a processor, one of the details of which is a video card. However, this detail is the most important. Also on the video card are memory chips, capacitors, power connector or connectors, a protective casing, a radiator and a cooler.
The difference between an integrated and discrete video card is that the second one is much more powerful and efficient than the built-in version. First, it has its own amount of memory, which directly affects the speed of rendering objects. Secondly, its parameters include an expansion bus, the bit size of which allows you to increase the bandwidth for data transmission.
These graphics adapters require additional power to simply start up and display quality images. Despite all the power, there are office options for discrete video cards that differ little from their integrated counterparts. Game options are more powerful in structure and potential, but consume much more energy.
Temperature regime
For better functioning, you need to know what a GPU is in a computer and its temperature. How do I cool the embedded and discrete GPUs? To cool the integrated GPU, just place the fans in the case, and the discrete options have their own cooling system. Depending on how many fans are above the chip, it will be clear how well the chip cools.
The cooling system of the video card is quite simple - the chip, with the help of the thermal paste applied to it, comes into contact with the heat sink tubes, they go to the radiator, which is cooled with the help of a cooler.
The operating temperature of the chip is no more than 70 degrees, a further increase in temperature can be considered overheating. In order to prevent overheating of the video card, it is enough to clean the video card from dust in a timely manner, while changing the thermal paste. In order to find out the current state of the temperature in the video card, it is enough to run the appropriate programs, for example, AIDA 64. There you can see the temperature not only of the graphics adapter, but of the entire system.
