How are geforce cards different? Rulers and markings of NVIDIA video cards
Ilya 2938
In a modern PC, the video card is as important a component as the processor or RAM. The cost of graphics accelerators can vary from a couple of thousand rubles to the same amount, but in dollars. Here we look at modern proposals in price category up to 6 thousand rubles.
Since this is a practical guide for users, we will not delve into the theory, but will consider only the main characteristics of graphics accelerators. Don't forget about.
 |
compyou.ru | RUB 9,750 |
The main component of a video card is the graphics processor. On the market in this moment GPUs are produced by only two manufacturers - NVIDIA and AMD, each of them specializes in its own area of application.
If you're a video game fan, don't hesitate to grab a card with an NVIDIA processor. Thanks to their PhysicX, CUDA and Pure Video HD technologies, which are supported at the hardware level, these video cards provide a completely different level of development game world than their competitors.
In turn, AMD video cards will please those whose profile is working with graphics or video editing - here AMD Radeon can attract buyers with an optimal price/quality ratio.
As for other technical criteria, in the budget range the difference in indicators such as bus width or memory capacity is so insignificant that focusing on it seems like a waste of time. The same applies to video card connection interfaces, which are unlikely to change in the next few years, but for those who are planning to connect their PC to a TV high definition, you should pay attention to the presence of an HDMI port.
Let us, perhaps, dwell on such a specific criterion as the cooling system. Few people think about this when purchasing, but overheating of a video card is one of the main reasons for graphics accelerators to fail.
Before purchasing, be sure to check that in addition to a banal fan, the video card has a radiator installed for uniform heat dissipation. A little thing like this can later save your video card in moments highest load GPU(I’m telling you as a person who has already buried one burnt “vidyukha”).
 |
Player.ru | RUB 18,705 |
The packaging of video cards has probably not changed much since their appearance on the market. The only thing worth clarifying is the ability to connect video cards in “paired” mode ( SLI technology for NVIDIA and Crossfire for AMD respectively). Provided in advance, this opportunity will allow you to further increase the performance of your PC without special costs by purchasing a similar video card. When purchasing, you should also check the availability of power cables, data transmission, as well as a disk with drivers and other software.
However, let's move on to specific examples. From all the piles of proposals that are now on the market, it is not easy to find something worthwhile, but we, guided by the facts stated above, will try to identify the most rational proposals.
When choosing products in the price category up to 6,000 rubles in the NVIDIA line, you should especially pay attention to the Titanium line, usually designated by the small suffix Ti. This card features excellent performance at a very reasonable price. If you're going to try everything modern news gaming industry and do not intend to completely empty your wallet, then the NVIDIA 650Ti model is your choice.
 |
Player.ru | RUB 3,494 |
Well, if entertainment is not your profile and you are looking for an inexpensive video card for working with graphics and video editors, then you should take a closer look at video cards based on the AMD Radeon 6770, but in this case, pay special attention to the cooling system of the video card - these models have an unpleasant tendency overheat, especially models with factory overclocking.
The video card market is constantly evolving, which means your choice will constantly increase. It’s easy to get lost in such variety, but when choosing such an important PC component as a video card, you shouldn’t forget about why you still need it. Before purchasing, consider whether it is worth pursuing the latest trends, or you just need a good workhorse, which, however, if chosen correctly, can take you through the worlds of the latest video games.
tell friends
The classification of NVidia GeForce video cards uses a system of letter and numeric indices. The “GeForce” line is divided into many series, designated by a three or four-digit number, and the series, in turn, are determined by a set of video accelerators with different powers, which are marked with complex abbreviations, usually starting with “G”. For example, the following can be said about the NVidia GeForce 8600 GT video card: it belongs to the GeForce 8600 series product line, the power index is GT.
Differences in GTX video cards and GT lie in many parameters. Of course, their parameters are not constant, since they depend on the series of the video card, but there are some aspects in which you can put a “more” or “less” sign between them.
There is such a characteristic of video cards as bus width - the size of information processed by it in one clock cycle is directly proportional to this value. Width GT allows you to process 128 bits in 1 clock cycle.
Efficiency is a parameter that reflects the performance of a video accelerator per 1 Watt of electricity consumed, in other words, an indicator of the environmental friendliness of the card. Green efficiency is expressed as a percentage. For GT cards it rarely reaches half of what is possible.
The price-quality ratio can also be expressed as a percentage. For GT video cards, its average value is approximately 60.
And finally, the comparative performance index (calculated by relating the card's performance index to its maximum achieved value. Its maximum value for GT cards is 1200 units.
Power Index GTX speaks of the technological superiority of the video adapter. The command processing speed for the GTX reaches 512 bits, a pretty decent value by modern standards.
Both efficiency and price-quality ratio in percentage terms can reach a maximum in modern maps GTX.
The comparative performance index of the GTX reaches 8000.
Conclusions website
- GTX allows you to process your work 2 or 4 times in one clock cycle larger volume information than GT video cards
- Efficiency GTX cards exceeds this figure for GT, which makes them more environmentally friendly
- The price/performance ratio for the GTX is better than that for the GT
- The performance of GTX cards is superior to that of GT.
Often, before choosing, it is difficult to understand its positioning in the line, as well as its features and performance. This article is intended to highlight this issue and tell you about the main lines NVIDIA video cards, their generations, purpose, labeling and performance.
Introduction
This material will not consider cards produced before 2010 and Fermi microarchitectures, since they have already lost their relevance today. The only exceptions are the top solutions for their time, but even these are now just average and are not sold anywhere. Also, the ION line will not be considered here, due to the fact that at the moment computers with these cards are not for sale.
For search useful information For video cards, we recommend using their website.
If you are interested this information, then you can look at similar articles about and, you may also be interested in:
Rulers
GeForce
This family is the most basic one from NVIDIA. Its representatives are installed both in powerful gaming PCs and in simple office laptops. Video cards from this family satisfy 90% of the needs of ordinary consumers. The remaining families are created for enthusiasts, for professionals and the corporate segment, or even for tasks that are quite unusual at first glance.
Generations
The generation and microarchitecture of the video chip is reflected in its code name. So:
- G.F. Fermi
- GK–Kepler
- GM–Maxwell
- GP-Pascal
You can read about the first cards released on Pascal at the corresponding links: , and now they have already arrived.
But several amendments need to be made to this table:
| Models | Microarchitecture |
|---|---|
| 605 | Fermi |
| 610 | Fermi |
| 620 | Fermi |
| 630* | Fermi |
| 640* | Fermi |
| 645 | Fermi |
| 730* | Fermi |
| 750 | Maxwell |
| 750 Ti | Maxwell |
| 640MLE* | Fermi |
| 670M | Fermi |
| 675M | Fermi |
| 710M | Fermi |
| 720M | Fermi |
| 820M | Fermi |
| 870M | Kepler |
| 880M | Kepler |
| 920M | Kepler |
* - means that an exception exists for some modifications of these video cards.
- GT – this letter combination reflects video cards low level performance, they cannot be considered as gaming.
- GTX – this index denotes video adapters of medium and high level, which are good for games.
- M – mobile video card (they are much weaker than their brothers without this letter)
- X – marking of a more powerful video card for mobile solutions
- LE – this is the version of the card with a lower clock frequency for mobile adapters
- Ti – designation of a more powerful version of desktop cards
It is worth noting that the more productive version differs not only in overclocking, but also in kernel components (unified shader units, texturing units, rasterization units).
Perhaps, starting with the Pascal generation, mobile video cards will no longer be equipped with the letter M, since they use almost the same chips.
The numbers following the generation indicate the position of the model in the line.
Interesting fact: 90 means 2 80 chips in SLI mode (work in pairs).
TITAN
This is a sub-line of GeForce, because they have the GTX index. First you need to understand the positioning of this line. These are the fastest and most expensive video cards at the moment. But this price is really too high for this level of performance. The thing is that they are also positioned as powerful professional video cards for mathematical calculations and FP 64 calculations (double precision floating point calculations). This is a kind of SUV in the world of video cards - you can work and play. The exception is the Titan X, which lacks stars in FP 64 computing and is essentially just a very expensive video card with a huge amount of video memory.
In this line at the beginning of 2016 there are only 5 video cards and almost all of them are in reference design (versions from third-party manufacturers).
TITAN, TITAN Black Edition and TITAN Z belong to Kepler, TITAN X – Maxwell, also available in Pascal (differences in prefixes: the first has the full name NVIDIA GeForce GTX TITAN X, and the second one simply has NVIDIA TITAN X).
You can read about all models on the website.
Quadro
This family is intended for professional use. These cards are very well suited for complex 3D applications and computational simulations. These cards render real movies with special effects. These cards are not suitable for gaming. Even the most expensive solutions will be inferior to average gaming solutions GeForce video cards. The thing is that these video adapters are designed for double-precision floating-point calculations (FP 64), while games need single-precision floating point (FP 32). But in these more precise calculations and applications using OpenGL drivers the superiority of Quadro is simply colossal, because even cheap Quadros (although they are not that cheap) are the most powerful gaming video cards (with the exception of some Titans). If the application does not have any specific optimization for the capabilities of Quadro cards, then the result is decided by the number of stream processors and throughput memory, what do you have gaming video cards full order.
We will not touch on cards up to the Fermi microarchitecture.
The first letter indicates the microarchitecture of the chip:
- she is not there – Fermi
- K–Kepler
- M – Maxwell
There are also letter indices at the end of the model name:
- M – designation of a mobile video card
- D – another set of outputs. In the case of the K2000, instead of two DisplayPort ports and one DL-DVI, the D version has two DL-DVI outputs and one mini-DisplayPort.
The numbers indicate the position of the video card model in the lineup (bigger is better).
Tesla
It has long been known that video cards (GPUs) perform mathematical calculations much faster than processors (CPUs). The whole point is that in these operations great importance The number of cores and the parallelism of calculations play a role. Video chips have many more cores than CPUs. If we take CUDA, then there can be up to 3072 of them in one video card! This feature is related to the role of the video card in the computer - it needs to do a lot simple actions in parallel and in a very short time. Tesla is a family created specifically to speed up mathematical calculations. Such cards cope well with both FP 32 and FP 64 calculations. They are used in research centers and on servers, because they will do more per unit of energy consumed useful work, rather than the processor. Interesting fact: cards of this line do not have video outputs. The first letter means generation
- K–Kepler
- M – Maxwell
The numbers are an indicator of the chip's position in the lineup (bigger is better). Here we will not analyze letter indices and marking details. Our goal is to introduce you to this family and tell you a few words about it. There is quite a bit of information about the entire family due to its use only in narrow areas and difficulty in acquiring.
Interesting fact: There is such an NVIDIA Quadro M6000 video card with 24 GB!
NVS
This family is created for the corporate segment. Previously, it was part of the Quadro family and was also designated by the letters “NVS”. These video chips are designed for business applications (financial, corporate, ECAD), multi-monitor solutions. For example, they are used for digital signage. Their features are a large number of display ports on some models and a very low total support cost (TCO). They do not shine with performance and they use not so fast DDR3 memory. Heat dissipation does not exceed 70 W. For comparison, in the most powerful model NVIDIA NVS 810 has only 512 CUDA cores, 68 W TDP and 4 GB DDR3 memory, but as many as 8 Mini DisplayPort 1.2 outputs.
All information about current models you can find out.
Tegra
A family of systems on a chip (SoC) for mobile devices (there is information about SoC on our website). As part of it, the first dual-core and quad-core solutions were presented. At the time of their release, they were top-end solutions in terms of graphics, but in the processor part things are going quite well. At the moment they have their own development of Denver cores, instead of the “classic” Cortex. There are two versions of Tegra K1:
- 2 Denver cores
- 4 Cortex-A15 cores
Tegra K1 was built on the Kepler microarchitecture, and Tegra X1 was built on Maxwell. Oddly enough, Tegra X1 uses 4 Cortex-A-53 cores and 4 Cortex-A-57 cores (big.LITTLE technology). The advantage is that there are exclusive projects and ported computer games, made only for Tegra-based devices, due to their power and company connections. Nvidia also has its own tablets and portable consoles, where some interesting technologies. For example, broadcasting games from a PC to your screen mobile device based on Tegra. Tegra-based devices are a good help for mobile gaming.
Tegra 2 became the first 2-core chip for mobile devices.
Tegra 3 repeated the success of the previous chip, but with 4 cores.
Tegra K1 switches to microarchitecture graphics core Kepler and 28 nm and comes very close in performance to PS3 and XBOX 360.
Tegra X1 uses big.LITTLE technology, switched to Maxwell microarchitecture and 20 nm process technology. Became the first SoC to achieve 1 teraflops of FP 16 floating point performance. He spent 10 W to demonstrate the Unreal Engine 4 “Elemental” demo, Xbox One– 100 W, and the top-end PC of 2012 – 300 W. This does not mean that it can compare with the top PC of 2012, but only demonstrates a huge increase in the efficiency of video chips.
About others Interesting Facts You can learn about GPUs at .
Conclusion
We hope that our article was clear and interesting to you, and also helped you understand the lines and markings of video cards from NVIDIA. If you have any questions or inconsistencies, then first look at the Introduction; if the problem is not resolved and questions remain, then you are welcome to comment!