Hello dear users and lovers of computer hardware. Today we will speculate on what is integrated graphics in a processor, why is it needed at all, and whether such a solution is an alternative to discrete, that is, external video cards.

In this article, you will learn:

From an engineering standpoint, the integrated graphics core commonly used in their products by Intel and AMD is not a graphics card per se. It is a video chip that has been integrated into the CPU architecture to fulfill the basic duties of a discrete accelerator. But let's deal with everything in more detail.

History of appearance

Companies first began embedding graphics in their own chips in the mid-2000s. Intel began development with Intel GMA, but this technology showed itself rather poorly, and therefore was unsuitable for video games. As a result, the famous HD Graphics technology is born (at the moment, the latest representative of the line is HD graphics 630 in the eighth generation of Coffee Lake chips). The video core on the Westmere architecture made its debut, as part of the Arrandale mobile chips and the desktop ones - Clarkdale (2010).

AMD took a different route. The company first bought out ATI Electronics, a once-cool graphics card maker. Then she began to pore over AMD's own Fusion technology, creating her own APUs - a central processing unit with an integrated video core (Accelerated Processing Unit). The first generation chips made their debut as part of the Liano architecture, and then Trinity. Well, the graphics of the Radeon r7 series for a long time were registered in the composition of laptops and netbooks of the middle class.

Advantages of embedded solutions in games

So. What is an integrated card for and what are its differences from a discrete one.

We will try to make a comparison with an explanation of each position, making everything as reasoned as possible. Let's start with such characteristics as performance. We will consider and compare the most relevant solutions at the moment from Intel (HD 630 with a graphics accelerator frequency from 350 to 1200 MHz) and AMD (Vega 11 with a frequency of 300-1300 MHz), as well as the advantages that these solutions provide.
Let's start with the cost of the system. Built-in graphics allow you to save a lot on the purchase of a discrete solution, up to $ 150, which is critical when creating the most economical PC for office and use.

The frequency of the AMD graphics accelerator is noticeably higher, and the performance of the adapter from the red ones is significantly higher, which indicates the following indicators in the same games:

The game	Settings	Intel	AMD
PUBG	FullHD, low	8-14 fps	26-36 fps
Gta v	FullHD, medium	15-22 fps	55-66 fps
Wolfenstein ii	HD, low	9-14 fps	85-99 fps
Fortnite	FullHD, medium	9-13 fps	36-45 fps
Rocket league	FullHD, high	15-27 fps	35-53 fps
CS: GO	FullHD, maximum	32-63 fps	105-164 fps
Overwatch	FullHD, medium	15-22 fps	50-60 fps

As you can see, Vega 11 is the best choice for inexpensive "gaming" systems, since the adapter's performance in some cases reaches the level of a full-fledged GeForce GT 1050. And in most online battles it shows itself perfectly.

For now, only the AMD Ryzen 2400G comes with this graphics, but it's definitely worth checking out.

Option for office tasks and home use

What are the most common requirements for your PC? If you exclude games, you get the following set of parameters:

• watching movies in HD quality and videos on Youtube (FullHD and in rare cases 4K);
• work with the browser;
• listening to music;
• communication with friends or colleagues using instant messengers;
• Application Development;
• office tasks (Microsoft Office and similar programs).

All of these items work fine with the integrated graphics core at resolutions up to FullHD.
The only nuance that must be taken into account without fail is support for video outputs by the motherboard on which you are going to install the processor. Check this point in advance so that there are no problems in the future.

Disadvantages of integrated graphics

Since we figured out the pros, you need to work out the disadvantages of the solution.

• The main disadvantage of such an undertaking is productivity. Yes, you can play with a clear conscience more or less modern toys at low and high settings, but graphics lovers will definitely not like this idea. Well, if you work with graphics professionally (processing, rendering, video editing, post-production), and even on 2-3 monitors, then the integrated video type will definitely not suit you.

• Moment number 2: lack of its own high-speed memory (in modern cards these are GDDR5, GDDR5X and HBM). Formally, a video chip can use at least 64 GB of memory, but where does all of it come from? That's right, from the operational. This means that it is necessary to build the system in advance in such a way that there is enough RAM for both work and graphics tasks. Keep in mind that the speed of modern DDR4 modules is much lower than that of GDDR5, and therefore more time will be spent on data processing.
• The next drawback is heat dissipation. In addition to its own nuclei, another one appears in the process, which, in theory, warms up no less. It is possible to cool all this splendor with a boxed (complete) turntable, but get ready for periodic underreporting of frequencies in especially complex calculations. Buying a more powerful cooler solves the problem.
• Well, and the last nuance - the impossibility of upgrading the video without replacing the processor. In other words, in order to improve the on-board video core, you literally have to buy a new processor. Dubious benefit, isn't it? In this case, it is easier to purchase a discrete accelerator after a while. Manufacturers like AMD and nVidia offer great solutions for all tastes.

Outcomes

Embedded graphics are great in 3 cases:

• you need a temporary video card, since there was not enough money for an external one;
• the system was originally conceived as superbudgetary;
• you are creating a home media station (HTPC) that focuses on the embedded kernel.

Hopefully one less problem in your head, and now you know what manufacturers create their APUs for.

In the next articles, we'll talk about terms such as virtualization and more. Stay tuned to keep up with all the trending topics related to iron.

Tired of long searches for a new processor, viewing numerous reviews on forums and flipping through catalogs, the user can finally go to the website of the largest online store in Ukraine "Electronic World" at http://elmir.ua. Of course, he will be amazed not only by the fact that delivery to Kiev, Kharkov and other cities is possible, not only by low prices, but also by the wealth of choice that the store provides.

Looking through all these wise processor specs, the user may notice that some of them include an option such as an integrated GPU. At the same time, this parameter may be absent for other processors. What is it and why might it be needed?

Integrated GPU

The fact is that some manufacturers, among other things, build a special graphics accelerator into their processors. Or the so-called graphics core. For example, if you buy an amd a6 processor, then the graphics core will be found in it. In the rest, it may not be there.

The role of the graphics core - GPU - is exactly the same as that of any video card. It processes the image and displays it on the screen, however, buying a separate video card can be avoided, for example, in order to reduce the cost of the entire system as a whole.

However, does this mean that in this case you can refuse a discrete video card altogether? The built-in graphics core with a relatively high performance can really be used not only in office systems, but also in entry-level gaming systems. However, in any case, the GPU power is often much lower than that of a single video card.

When you may need it

The purchase of a system with a built-in video accelerator seems more rational at first glance. After all, the cost of a good gaming video card is sometimes several times higher than the cost of such a processor. However, don't jump to conclusions. A GPU in a processor can be useful when:

• the user collects an office system, which is required only to work with texts, spreadsheets and surf the Internet;
• a graphics core worthy of performance will replace a discrete graphics card for not too demanding gamers who are not interested in the latest gaming innovations;
• the user wants to build a system with two graphics cards - built-in and discrete. In this case, one graphics chip will work during the launch of "heavy" applications, and the second - for example, built into amd a6 - will be included in the work when you need to handle the needs of the operating system or office applications. This will achieve a balance between performance and power consumption.

Problems registering on the site? CLICK HERE ! Do not pass by a very interesting section of our site - visitors' projects. There you will always find the latest news, anecdotes, weather forecast (in the ADSL newspaper), a TV program of terrestrial and ADSL-TV channels, the freshest and most interesting news from the world of high technologies, the most original and amazing pictures from the Internet, a large archive of magazines in recent years , delicious recipes in pictures, informative. The section is updated daily. Always the latest versions of the best free programs for everyday use in the Necessary programs section. There is almost everything you need for your daily work. Start gradually abandoning pirated versions in favor of more convenient and functional free counterparts. If you still do not use our chat, we highly recommend you to get acquainted with it. You will find many new friends there. It is also the fastest and most efficient way to contact project administrators. The Antivirus Updates section continues to work - always up-to-date free updates for Dr Web and NOD. Didn't have time to read something? The full content of the creeping line can be found at this link.

AMD Trinity for desktop. Part 1. Graphics core

Announcement: High hopes were pinned on APU Llano, but they were only partially justified - in the laptop segment. AMD has not lost hope: the new Trinity APUs are already out for mobile platforms, and now they are also available for desktops. We have tested the second generation of desktop APUs and in this review we will talk about both their architecture and graphics performance.

There is no doubt that AMD is not the supplier of the fastest processors for personal computers today. And this situation did not develop yesterday. Since Intel moved from the Pentuim 4 to a variety of Core processors, AMD's offerings have slipped into second place. In fact, all of today's processor products of this company are either budgetary or some highly specialized solutions that are of little interest to a wide range of users, who put high performance at the forefront. However, the low performance indicators of the manufactured processors, as well as the decline in market share, are not at all a reason to put an end to the results of the work of AMD's processor division.

The engineers of this company are famous for being able from time to time to come up with some original ideas that allow AMD not only to maintain its market position, but also to have a significant impact on the entire industry as a whole. You don't have to go far for examples of such ideas: 64-bit extensions of the x86 microarchitecture, multi-core design of the CPU, integration of the memory controller and the north bridge of the chipset into the processor - all these solutions were first developed and implemented by AMD, and not the current leader in processor construction.

That is why we continue to closely monitor what innovations are ripening in the depths of AMD. And it seems that by now the company has once again groped for a fruitful vector of development, which is capable of giving a positive impetus not only to itself, but to the entire processor market as a whole. This vector - APU (Accelerated Processing Unit, "accelerated processing unit") - an ideology that provides for the combination of traditional computational cores with a powerful graphics core on one semiconductor chip. Moreover, not a simple neighborhood, but a symbiosis - the possibility of combining their resources to solve common problems.

The APU class includes several different AMD offerings released back in 2011. Of greatest interest among them are the A-series hybrid processors, codenamed Llano, which serve as the basis for the Lynx and Sabine platforms and are aimed at a wide range of desktop and mobile systems. Despite the fact that these processors and platforms serve only as a "trial balloon", since they are only used to test the principles of APUs, they were quite warmly received by the market. Llano was especially in demand in the mobile segment, which was immediately reflected in the increase in the presence of AMD products in modern laptops. And this is really visible to the naked eye. If a couple of years ago, AMD mobile platforms were found in very few offers, today it is not difficult to buy a laptop based on a processor from this manufacturer. In any computer store, you can easily find a huge number of offers equipped with AMD APUs.

However, the increased interest in AMD processors seen in the mobile computer market did not arise at all because of their hybridity. Rather, it should be understood as a side effect. In reality, the fact is that a sufficiently powerful graphics core, combined with computational cores that are acceptable by the standards of mobile solutions, is exactly what Intel's product range is lacking. And if we take into account the very affordable prices set by AMD for its APUs, then it is absolutely not surprising that they fit perfectly into inexpensive laptops, thereby giving them the opportunity to assemble modern computers without installing discrete video accelerators in them and the additional costs associated with this. ...

As a result, the concept of APU itself was popular with the people. Its preachers from AMD, communicating with software developers, were able to rely on relevance and prevalence, and in the end, real programs appeared at the disposal of users, designed to fully utilize the resources of hybrid processors. The May update of the A-series of AMD mobile processors with the Trinity design, which increased the performance of both the computing and graphics parts of the APU, became an additional argument in favor of the viability and attractiveness of the concept. So in the future, the share of laptops with the AMD Vision logo will only increase.

A completely different story happened with AMD desktop APUs. The demands of desktop users are significantly different from those of laptop owners, and they were not particularly interested in the APU topic from the very beginning. The driving force behind the penetration of the first generations of hybrid processors into laptops was quite powerful graphics, but when using it in desktop computers, this epithet must be abandoned. The fact is that desktops are characterized by much higher screen resolutions, in which AMD A-series processors do not develop an acceptable level of 3D performance. In other words, from the point of view of desktop users, the graphics core of Llano processors is qualitatively little different from the integrated graphics of Intel's offerings: both options are almost equally bad for an entry-level gaming system. The processing power of the AMD APUs is significantly lower than that of Intel processors, and this closes Llano's path to a whole range of home or office systems. Even as the heart of the media center, AMD's APUs have little chance of competing offerings. In this case, too high heat dissipation and the lack of means to accelerate the encoding of high-resolution video content let them down.

However, the most ambitious obstacle on the way of Llano to desktop computers was the Socket FM1 platform, specially designed for them, with completely unclear prospects. It is impossible to install any other processors, except for Llano, and this makes it a “thing in itself”, on the one hand, not prone to a subsequent upgrade, and on the other, with a very limited lifespan. It is quite natural that it is almost impossible to interest a solution with such a combination of characteristics of desktop users, because the market is flooded with competing LGA1155 offers for every taste and wallet with a much longer life cycle.

But giving the market of integrated desktop processors to the power of a competitor, which, seeing the perspective of the APU concept, hastily increases the capacity of its own graphics cores, is clearly not included in AMD's plans. Therefore, about a year after the appearance of Llano, the company is ready to offer the second generation of desktop A-series processors, revised and revised. The design of the new desktop APUs is not specialized or utilitarian. This is Trinity, and it has already been tested on mobile systems, where it has been successfully used since the beginning of the summer. However, for desktop systems, the frequencies of the computing and graphics components have been seriously increased, which allows the manufacturer to assure the public that the fresh APUs, unlike their predecessors, should appeal to many desktop users, including enthusiasts.

In general, we are almost ready to believe in AMD's words: at least in terms of design, Trinity is definitely better than Llano. As we have already seen with the example of mobile APUs, the computational cores used in Trinity, which are based on the Piledriver microarchitecture, work faster than the Husky cores from Llano, whose microarchitecture roots go back to the distant past. The performance of the graphics core has also significantly improved, the structure of which has been radically redesigned. And most importantly, a new Socket FM2 platform is now offered for Trinity desktop processors, which should be devoid of all the old flaws. AMD is ready to guarantee its stability for the next several years, and the model range of processors in a compatible performance will include a wide range of offerings of different levels.

In other words, if we compare Trinity and Llano, then the new processors are obviously better. However, are they good enough to effectively push the APU concept to desktop systems, whose users are still very skeptical about such solutions? In our material, we will try to partially answer this question, for which we will thoroughly test the graphics component of the new generation desktop hybrid processors and try to understand whether its power is enough for use in entry-level gaming systems.

Unfortunately, we have to postpone a detailed consideration of the second part of Trinity - computing cores - for some time. However, this is not our fault. The fact is that AMD has not yet officially announced its new A-series processors for desktop systems. Therefore, our hands are partially bound by non-disclosure obligations, so this article will be followed by a second one, which includes tests of a different kind. However, no one forbids us to operate with the available information about the Trinity microarchitecture, so first, let's analyze what work AMD engineers have done to make the new APUs a reality.

Trinity design

In accordance with the original concept, any APU consists of three main parts. In this regard, Trinity does not bring any changes: the new generation of APUs include processor cores, an integrated graphics accelerator and a small but very important component - the unified northbridge. It is he who turns the sum of dissimilar cores into a single system and, including the DDR3 SDRAM controller, is responsible for the interaction of the computing and graphics cores with each other and with the system memory, ensuring the possibility of their joint work with the same data.

In general, the general structure of Trinity has remained exactly the same as that of Llano, but at a lower level, all components have been reworked. At the same time, all the changes were made in such a way as not to inflate the semiconductor crystal: AMD's production technology has not been updated, the company continues to use the 32nm Globalfoundries process with SOI, and the manufacturer is not going to raise the cost of APUs positioned as fairly affordable proposals. As a result, the area of ​​the Trinity crystal compared to Llano has increased by only 8 percent - up to 246 mm 2. The number of transistors also changed very slightly and reached 1.303 billion pieces (it was - 1.178 billion). Moreover, even the division of the transistor budget between computing and graphics resources has not changed much: they occupy approximately the same area on the chip in both cases.

Nevertheless, talk about the similarity of Llano and Trinity can end there. Computing cores, for example, have changed dramatically with the release of a new generation of APUs. Now, hybrid processors are based on (and will be used in the future) the Bulldozer microarchitecture, and more specifically, its second generation - Piledriver. Trinity dual-core and quad-core processors include one or two conditionally called dual-core modules, which, recall, contain two sets of executive devices and can process two threads simultaneously, but at the same time have a common cache memory module, an instruction fetch unit, and their decoder and a floating point block. At the same time, in Trinity, in comparison with FX class processors based on the Bulldozer microarchitecture without integrated graphics, not only the number of cores is reduced, but also there is no third-level cache.

But the second generation Bulldozer microarchitecture used in the new APUs, which has not yet been represented in any other processor family, offers a number of small improvements aimed at increasing performance, reducing leakage currents and ensuring stability at high clock speeds. The front end of the pipeline has received a more accurate branch predictor, as well as a larger instruction window. The executive devices gained an improved scheduler, and they themselves learned to execute individual instructions a little faster, for example, integer and real-number division. In addition, the developers talk about increasing the L1 TLB capacity and improving the arbitration and prefetching algorithms for L2 cache data. All this is estimated at approximately 25 percent superiority (according to AMD calculations) of Trinity processors over Llano in computing performance.

The unified north bridge has also been drastically changed. First of all, engineers revised the system of priorities for access to shared memory, giving priority to computational cores, which, as practice shows, generate a relatively small part of requests. In addition, AMD has taken care of support for new types of memory, including DDR3-1866 in standard mode or DDR3-2400 when overclocked. The internal data buses were expanded, in particular, the graphics core got the ability to work with the memory controller via the 256-bit dedicated Radeon Memory Bus, and outside the chip, all connections now use the PCI Express protocol, which replaced Hyper-Transport.

However, the most interesting are the changes that have occurred with the graphics core. The fact is that without a significant increase in the transistor budget and without a radical revision of the architecture, AMD managed to significantly increase its performance, that is, in fact, to increase the density of useful blocks in the GPU by eliminating some surplus. This find, perhaps, deserves a separate discussion, especially since it is the graphics integrated into Trinity that are in the focus of our attention today.

Graphic core Devastator

The most intriguing fact about the design of the Devastator - which is the codename for the GPU built into the Trinity processors - is that it is based on the VLIW4 architecture. Considering that the Llano graphics core was based on the VLIW5 architecture, such a move by AMD seems somewhat strange, and we would rather expect to see the CGN architecture in Trinity, which is typical for the latest versions of discrete accelerators. However, in fact, it is VLIW4 that allows you to increase the specific efficiency of the graphics core, which is artificially limited by the number of transistors. AMD has already done this trick with its own Radeon HD 6900 series graphics cards, and then its results were more than satisfactory.

The bottom line is that the VLIW5 grouping of ALUs of five per streaming VLIW processor turns out to be not very effective, and one of the ALUs is simply idle in a large number of cases. Therefore, the VLIW4-layout of the Devastator, which assumes the presence of four ALUs in the VLIW stream processor, entails a more rational use of available resources. Of course, the downside is a decrease in the total number of executive devices and a decrease in the theoretical peak performance of the core, but the practical specific performance per square millimeter is growing. And for a die of a hybrid processor, on which, in addition to the graphics core, there are computational cores, this is the most correct way of optimization.

In total, the Trinity graphics core provides six SIMD engines, each of which consists of four texture units and sixteen VLIW stream processors. In total, this gives the presence of 384 ALUs in the core, and this is 16 pieces less than the Sumo graphics core of the Llano processors had at the disposal. However, simple arithmetic is not entirely appropriate here, the Devastator ALUs are usually more loaded with work than their predecessors, and, in addition, the relative simplicity of VLIW stream processors allows the graphics core to be set at higher clock speeds. For example, while in the older version of Llano the graphics worked at 600 MHz, in Trinity the video core speed can reach 800 MHz.

Considering that Devastator has 24 texture units (4 TMUs for each SIMD engine) and 8 raster operations (ROPs) at its disposal, we can conclude that this graphics core actually represents about one quarter of the GPU of the Radeon HD 6970 class. That, even taking into account the correction for a slightly lower operating frequency and the absence of a dedicated high-bandwidth memory bus, is very good. In other words, AMD is not disingenuous when it says that Trinity processors are equipped with integrated graphics of the "discrete" class. Indeed, you can expect very good 3D performance from the new generation APUs.

It is hardly surprising that the Trinity graphics core is compatible with the modern DirectX 11, OpenCL 11 and DirectCompute 11. These features were available in the Radeon HD 6900 video cards based on the same architecture, and in the predecessors of Trinity, the Llano processors. But at the same time, the new embedded graphics inherited some features of very modern solutions, in which the CGN architecture found its place. In particular, Devastator has an improved tessellation unit, as well as support for all current types of full-screen anti-aliasing: SSAA, EQAA and MLAA.

Special attention in the Trinity graphics is paid to media capabilities relevant to hybrid processors. The graphics core has a specialized unit AMD HD Media Accelerator borrowed from the latest versions of the GPU, which includes engines for hardware video decoding (UVD3) and hardware encoding of video content in H.264 format (VCE). The latter feature is very important for Trinity's successful competition with Intel's APUs, which have long received Quick Sync technology for high-speed high-definition video transcoding. Now there is something similar in AMD processors, but at the moment we have not been able to make sure that the VCE engine is working due to problems with its support in drivers and in existing software.

Introducing its new hybrid processor to the desktop market, AMD also thought about so that its users do not feel deprived compared to the owners of discrete graphics cards in terms of monitor connectivity. This is expressed in the fact that up to four independent displays can be connected to an integrated system with a Trinity processor simultaneously, while all types of connections are supported: analog - VGA - and digital - DVI, HDMI and Display Port 1.2, as well as four independent audio streams. True, the number of physical outputs is limited to three, and to connect four displays, you will need to connect a pair of monitors with a "chain" via Display Port.

Even more impressive, Trinity graphics also support Eyefinity technology. Of course, in order to find some game that can work with an acceptable FPS level on three or four monitors connected to the Devastator, you have to work hard, but the very existence of such a possibility speaks of the attention with which AMD developers approached equipping the second generation APU before its introduction to the mass market.

Trinity lineup

Speaking about the graphics core of Trinity desktop processors, it is necessary to touch upon the composition of their model range. The fact is that different representatives of the A-series with the Trinity design can be equipped with different variants of the Devastator core. Their differences are formed in a standard way: trying to introduce segmentation of their products into different price categories, the manufacturer in the lower modifications disables one or more SIMD engines. As a result, only the older APU modifications have the set of resources described in detail in the previous section, which includes 384 actuators.

The Trinity model nomenclature is as follows. The fastest models with a full-fledged Devastator core, which has the marketing name Radeon HD 7660D, belong exclusively to the new flagship A10 series. All other modifications with graphics cores with a reduced number of stream processors and lower frequencies belong to the "simpler" A8, A6 and A4 series, replacing processors with the old Llano design.

The complete lineup of APUs based on the Trinity design is shown in the table:

Trinity APU Specifications
Model number	A10-5800K	A10-5700	A8-5600K	A8-5500	A6-5400K	A4-5300
Integrated graphics	HD 7660D	HD 7660D	HD 7560D	HD 7560D	HD 7540D	HD 7480D
TDP, W	100	65	100	65	65	65
Number of unified shader processors	384	384	256	256	192	128
GPU frequency, MHz	800	800	760	760	760	723
Number of Cores	4	4	4	4	2	2
CPU frequency, GHz (base / turbo)	3,8 / 4,2	3,4 / 4,0	3,6 / 3,9	3,2 / 3,7	3,6 / 3,8	3,4 / 3,6
L2 cache, MB	4	4	4	4	1	1
Maximum memory frequency	DDR3-1866	DDR3-1866	DDR3-1866	DDR3-1866	DDR3-1866	DDR3-1600

Even the version of the graphics core installed in the A8-class processors is theoretically more than 35 percent slower than the full-fledged Devastator. What can we say about the even slower A6 and A4. This means that the A10-5800K and A10-5700 processors are primarily of interest for use as a gaming solution. It is them that you can try to imagine in entry-level gaming systems, devoid of a discrete video card. Processors of the lower series, perhaps, are very poorly suited for universal gaming computers, so they are recommended to be used in multimedia centers or in home entertainment systems that are not aimed at running resource-intensive 3D gaming applications.

That is why in this material we focused on testing the oldest hybrid processor - A10-5800K, with a built-in Radeon HD 7660D graphics core. This processor has at its disposal two Piledriver modules, due to which it is recognized by diagnostic utilities and the operating system as a quad-core. However, we also note the existence of an alternative opinion, according to which this processor is dual-core, but with the ability to execute four threads. Actually, this opinion, although it contradicts the statements of AMD itself, just more accurately reflects the positioning of the A10-5800K. At its cost, this APU falls into the same price category as Intel's Core i3, which, as you know, are dual-core, but with support for Hyper-Threading technology.

The operating frequency of the processor in question, taking into account its support for Turbo Core 3.0 technology, should range from 3.8 to 4.2 GHz. In practice, however, we have seen that under load, the A10-5800K spends most of its time in an intermediate state - at a frequency of 4.0 GHz.

The Radeon HD 7660D graphics core built into the A10-5800K operates at 800 MHz, and when there is no 3D load, it drops to 300 MHz. Despite the fact that AMD promised the operation of the turbo mode for the graphics core, in reality, its frequency does not rise above the 800 MHz specified in the specifications.

How we tested

As part of this material, we set ourselves the goal of examining the graphics core performance of new AMD APUs and, based on the results obtained, answer the question: can the most modern processors with integrated graphics be used as part of entry-level gaming systems without adding discrete graphics cards.

In testing, the AMD A10-5800K processor with Radeon HD 7660D graphics core was contrasted with other integrated chips on the market that have 3D graphics with an acceptable level of performance. Firstly, these are AMD Llano, although they are outdated with the advent of Trinity, but still relevant, presented in our tests by the older processor of this family, AMD A8-3870K with the Radeon HD 6550D video core. Secondly - representatives of the Intel Ivy Bridge family, the maximum version of the graphics core of which, HD Graphics 4000, has promising (according to its developers) 3D performance. Intel graphics defended the dual-core processor Core i3-3225. We chose it, and not a quad-core of the Core i5 family, since AMD's APUs are positioned as an alternative to Intel's dual-core processors by the manufacturer itself. In particular, according to preliminary data, the cost of AMD A10-5800K will be about the same as that of the younger members of the Core i3 family.

In addition, we should not forget about the findings of our past research, showing a higher specific efficiency of the cores of Intel processors. Quad-core processors with Sandy Bridge microarchitecture quite successfully withstood the eight-core Bulldozer processors, and it is unlikely that with the release of new generations of Ivy Bridge and Piledriver microarchitectures, this situation has somehow changed. This can be confirmed by the relative results of the SYSmark 2012 test, which show the generally used performance of processors.

Although the AMD A10-5800K received a noticeably higher performance than the AMD A8-3870K, it lags behind the Core i3-3225 and Core i3-2125 processors, not to mention its significant loss in computing performance to the four-core Core i5-3330. So the opposition of AMD's quad-core APUs in graphics tests to a dual-core Core i3 is quite justified. In addition, the differences in the graphics performance of the most powerful Intel Core i7 and the Core i3 we chose boil down to a 100-MHz difference in the frequency of the integrated video core: 1.05 GHz for our test subject versus 1.15 GHz for the flagship processor for Socket LGA1155. So, no other Intel processor will be able to show a fundamentally better result than the Core i3-3225 in graphics tests.

In order for us to be able to judge the performance level of the integrated graphics cores of modern processors relative to discrete graphics cards, a variant equipped with external graphics was also added to the number of tested configurations. The reference point was the video card Radeon HD 6570, the cost of which today in the version we use with GDDR5 memory is about $ 70. It was tested on a system with an A10-5800 processor.

As a result, the following hardware and software components were used in the tests:

• Processors:
  • AMD A10-5800K (Trinity, 4 cores, 3.8-4.2 GHz, 4 MB L2, Radeon HD 7660D);
  • AMD A8-3870K (Llano, 4 cores, 3.0 GHz, 4 MB L2, Radeon HD 6550D);
  • Intel Core i3-3225 (Ivy Bridge, 2 cores + HT, 3.3 GHz, 3 MB L3, HD Graphics 4000).
• Motherboards:
  • ASUS P8Z77-V Deluxe (LGA1155, Intel Z77 Express);
  • ASUS F2A85-V Pro (Socket FM2, AMD A85);
  • Gigabyte GA-A75-UD4H (Socket FM1, AMD A75).
• Video card: AMD Radeon HD 6570 1 GB GDDR5 128-bit.
• Memory: 2 x 4 GB, DDR3-1866 SDRAM, 9-11-9-27 (Kingston KHX1866C9D3K2 / 8GX).
• Disk subsystem: Crucial m4 256 GB (CT256M4SSD2).
• PSU: Corsair AX1200i (80 Plus Platinum, 1200W).
• Operating system: Microsoft Windows 7 SP1 Ultimate x64.
• Drivers:
  • AMD Catalyst 12.8 Driver;
  • AMD Chipset Driver 12.8;
  • Intel Chipset Driver 9.3.0.1019;
  • Intel Graphics Media Accelerator Driver 15.26.12.2761;
  • Intel Management Engine Driver 8.1.0.1248;
  • Intel Rapid Storage Technology 11.2.0.1006.

When testing the platform based on the AMD A10-5800K processor, the operating system patches KB2645594 and KB2646060 were installed to adapt the scheduler behavior to the Bulldozer microarchitecture.

The main emphasis in this testing was quite naturally placed on gaming applications of the integrated processor graphics. Therefore, the bulk of the benchmarks we used are games or specialized gaming tests. Moreover, if we take into account the goals set, we were primarily interested in the performance of various graphic solutions in the de facto standard for desktop systems Full HD-resolution 1980x1080. Therefore, most of the tests were carried out in it with a low or medium level of image quality.

3D performance

The 3DMark test results are very popular for assessing the weighted average gaming performance of video cards. Therefore, we turned to 3DMark in the first place. First, let's take a look at the performance in the Vantage version, which uses DirectX version 10.

The significant progress that has occurred with AMD's APUs in the transition from the Sumo graphics core to the new Devastator design is immediately evident. The advantage of the Trinity processor over the flagship of the Llano family is about 40 percent. As a result, the system based on the A10-5800K approaches the graphics performance of the platform with a discrete AMD Radeon HD 6570 graphics card.

A more recent version of 3DMark is focused on measuring DirectX 11 performance. Previously, Intel processors could not take part in such tests, leaving AMD's APUs alone, but the Intel HD Graphics 4000 graphics core implemented in Ivy Bridge finally received support for all modern software interfaces, so the Core i3-3225 processor is also present on this diagram.

3DMark 11 came up with an extremely interesting result. According to this benchmark, the graphics core built into the A10-5800K was able to bypass the discrete Radeon HD 6570. This is an excellent illustration of the high efficiency of the VLIW4 architecture used in Devastator. Recall that the Radeon HD 6570 video card is based on the 800MHz Turks graphics processor with the VLIW5 architecture and at the same time has 480 stream processors versus 384 in the Devastator. However, a larger number of executive devices, as we see, does not always translate into best practical indicators, from which we can conclude that the choice for Trinity VLIW4 design is a very correct decision.

Aliens vs. Predator (2010)

Despite the fact that in the synthetic benchmark 3DMark 11, the graphics core of the A10-5800K processor was able to overtake the discrete video card Radeon HD 6570, in a real gaming application - Aliens vs. Predator - the situation is completely different. Here the discrete video accelerator is seriously ahead of any version of integrated graphics, including the Radeon HD 7660D. It is obvious that the weak point of any processor video accelerators is the memory bus, which clearly has insufficient bandwidth. It should be noted, however, that we are comparing the Radeon HD 7660D here with the Radeon HD 6570 equipped with high bandwidth GDDR5 memory. But if a "simple" discrete video card with DDR3 SDRAM was used in the tests, then it would probably have been defeated by the Devastator core.

Batman: arkham city

The difference in performance between the old and new graphics cores used in AMD's APUs in Batman: Arkham City is about 30 percent. So from the point of view of graphics performance, the transition from Llano design to Trinity design is a completely justified decision, bringing tangible dividends. At the same time, such a step was made not at all due to heightened competition with Intel: even the newest and fastest GPU of the microprocessor giant looks very dull against the background of AMD's proposals. Obviously, AMD is aiming at signing a death sentence for budget graphics cards with DDR3 memory, such as the Radeon HD 6570 or GeForce GT 630.

Battlefield 3

Of course, the Radeon HD 7660D is not at all the same as a high-end or mid-range discrete graphics card. The performance of this solution is significantly lower. However, as we can see, the new integrated graphics core from AMD allows you to play quite decently the most modern games in Full HD-resolution, including Battlefield 3. Sometimes this requires setting low quality settings, but the average number of frames per second is at an acceptable level. Doesn't demonstrate Radeon HD 7660D and obvious drawdowns. For example, when tested in Battlefield 3, the minimum instant performance with low quality settings was quite decent, albeit not quite playable, 18 frames per second.

Borderlands 2

Even the newest first-person shooter Borderlands 2 runs without any problems on the A10-5800K. Of course, you will have to forget about the "niceties", but the fresh APU from AMD, unlike Intel processors with integrated graphics, makes it possible to play Borderlands 2 in 1920x1080 resolution without installing a discrete video accelerator.

Car racing games are usually not very graphics intensive. The behavior of F1 2012 is typical in this regard - this game runs on integrated systems with good performance even when choosing Full HD-resolution and high image quality. At the same time, although the advantage of the Radeon HD 7660D over the graphics from the Llano processor is close to 35 percent, the discrete Radeon HD 6570 still shows a slightly higher result. However, compared to the graphics core of competing processors, Intel HD Graphics 4000, any of AMD's integrated offerings look great. In F1 2012, the A10-5800K processor outperforms the Core i3-3225 by about 60 percent.

Far cry 2

We are deliberately not leaving Far Cry 2 out of the test suite. The presence of this four-year-old shooter allows you to see firsthand that in the games of the previous generation, the modern APU of the Trinity class works with simply outstanding performance. For example, in Far Cry 2, for example, we were able to set the resolution to 1920x1080 with the maximum available image quality and at the same time got an average of more than 30 frames per second. At the same time, the minimum FPS recorded in testing was quite acceptable 23 frames per second.

Sleeping dogs

Unfortunately, in the most modern of our selected games, the graphics core of the A10-5800K processor again demonstrates its inability to withstand the full-fledged Radeon HD 6570 video card, lagging behind it by about 10-15 percent. The source of the APU problem is clear - it would benefit from higher bandwidth memory. That is why the proliferation of solutions like Trinity can greatly revive the DDR3 SDRAM market. In common applications, the speed of operation depends on the memory frequency quite subtly, but for systems with integrated graphics, a fast memory subsystem can be of fundamental importance. However, we will pay more detailed attention to this issue.

Sniper elite v2

The Devastator core in the Radeon HD 7660D version is the fastest available on the market for embedded GPUs. The results obtained in the Sniper Elite V2 benchmark confirm this once again. The new version of the integrated graphics core, developed by AMD, outperforms the previous Sumo by 26 and 43 percent, depending on the image quality settings. As a result, the superiority of the Radeon HD 7660D over Intel HD Graphics 4000 reaches double the value. In other words, in terms of GPUs built into the processor, AMD continues to significantly outperform its competitor. Moreover, to the progress made by Intel with the release of the Ivy Bridge microarchitecture, AMD found an equally impressive answer - Trinity. So that the current APUs of both companies again fall into completely different weight categories.

Cinebench R11.5

All the games we tested on are DirectX applications. However, we also wanted to see how accelerators cope with work in OpenGL. Therefore, to purely gaming tests, we have added a small study of performance when working in the professional graphics package Cinema 4D.

The balance of power is quite typical. Trinity's performance level in an OpenGL application does not qualitatively differ from its speed in gaming DirectX tasks. The Radeon HD 7660D accelerator integrated into the AMD A10-5800K processor is ahead of its predecessor and Intel's competitor, but lags behind the discrete Radeon HD 6570 graphics card. so absurd. Moreover, in the assortment of AMD there are even corresponding offers - "professional" Trinity processors, sold under the FirePro trademark.

GPGPU performance

AMD is relentlessly emphasizing that its Llano and now Trinity processors are APUs. This means that their architecture is optimized for solving problems of various classes by using not only traditional x86 cores, but also graphics core stream processors - they must work together. For the successful functioning of such a community of fundamentally different computing resources, of course, specialized software is required. And if a year ago it sounded like a verdict on the APU concept, now the situation has begun to actively change. Developers of a number of popular software products began to make concrete attempts to take advantage of hybrid solutions. Today, there is information that the computing capabilities of the graphics core may involve current or future versions of programs such as Adobe Flash 11.2, Adobe Photoshop CS6, GIMP, ArcSoft MediaConverter 7.5, CyberLink MediaEspresso 6.5, Handbrake and WinZip 16.5.

As part of this material, we do not yet have the right to resort to testing the Trinity processor in such software, nevertheless, we can evaluate the practical performance of the Devastator graphics core on a GPGPU load created through the OpenCL and Microsoft DirectCompute APIs. For this we used the SiSoftware Sandra 2012.10.18.74 test suite.

The computational performance of the Devastator graphics core looks very good. The use of the VLIW4 architecture in its basis allows achieving high efficiency of general-purpose computing, as a result of which the Radeon HD 7660D noticeably outperforms not only the previous version of the graphics accelerator from Llano and Intel's graphics core Intel HD Graphics 4000, but also the discrete graphics card Radeon HD 6570. in applications that support OpenCL, you can expect high levels of performance from Trinity.

The situation is similar in the cryptographic test. In other words, by placing high-performance graphics with VLIW4 architecture in new hybrid processors, AMD was striving to solve a very specific problem - to demonstrate the usefulness and prospects of combining general-purpose x86 cores and streaming graphics cores. Considering that software makers are starting to try hybrid processors in business, this is a very timely move. At this stage, AMD should not only demonstrate the potential of new approaches, but also prove their advantage in practice.

conclusions

The days when it was necessary to approach integrated graphics from the position of “just to work” are long gone. Since the introduction of graphics cores into central processors, AMD and Intel have been actively expanding their power, displacing budget graphics cards from the market and giving their processors new use models. In this race of integrated GPUs, AMD is leading the way, with the fastest GPUs from the Ivy Bridge processors so far not beating even Llano graphics, let alone the new Trinity. However, this state of affairs was not an excuse for AMD to slow down the pace of innovation. This company is fighting not with a specific competitor's product, but for changing the attitude towards hybrid processors in principle. This requires not a simple superiority over alternative products in benchmarks, but its other quality.

It is very likely that the new Trinity desktop processors that we met today are the very necessary qualitative leap. The AMD A10-5800K is not just a hybrid processor with the fastest graphics core to date. The important thing is that the speed of this core is already sufficient to provide acceptable performance in almost any modern 3D games in Full HD resolution. Of course, in this case, you have to set not the maximum quality settings, but the fact remains: Trinity looks quite decently on a par with discrete 3D-accelerators of the lower level, costing about $ 60-70, which a new hybrid processor can easily replace. In fact, today we can say that accelerators such as the Radeon HD 6570 and GeForce GT 630 with the Trinity distribution can be sent to a landfill, at least this applies to their DDR3 modifications.

Today we got acquainted only with the graphics component of the new promising AMD project. And this component is his strong point. In terms of general performance, Trinity probably won't be as impressive as it gets. Even the 25% speed increase promised by AMD itself is clearly not enough for the A10-5800K, like other products in the family, to be able to perform on an equal footing with Intel's Ivy Bridge generation processors. Of course, we can count on the fact that AMD will be able to push the APU concept, and the hybrid offerings of this manufacturer will receive a noticeable increase in performance due to the computing resources of the graphics core. However, if this does happen, it will obviously not happen very soon. Therefore, for now, you have to keep in mind that Trinity also has a weak side.

What is the bottom line? Think about it, most Intel desktop processor buyers, by and large, don't give a damn about their graphics performance. They are ready to put up with any level of it, since they are attracted by the high speed of x86 cores. Trinity, on the other hand, may well win the favor of consumers by going from the other side. If this APU offers an alluring level of 3D performance, is it worth worrying so much about the slower speed of the x86 cores than the competitor? The answer to this question, judging by the available data, may well be negative: for most typical tasks, the available Trinity performance is probably quite enough.

However, let's not rush to final conclusions and wait until the embargo on the publication of the full test results is lifted. While you are reading these lines, work on the continuation of the material is already underway.

3 Great processor for gaming 4 Best price 5

Computers have entered our lives so tightly that we already consider them to be something elementary. But their structure cannot be called simple in any way. Motherboard, processor, RAM, hard drives: these are all integral parts of a computer. You cannot throw out this or that detail, because they are all important. But the most important role is played by the processor. It is not for nothing that it is called “central”.

The role of the CPU is enormous. He is responsible for all calculations, which means that it depends on him how quickly you will complete your tasks. It can be surfing the web, drafting a document in a word processor, editing photos, moving files, and much, much more. Even in games and 3D modeling, where the main load falls on the shoulders of the graphics accelerator, the central processor plays a huge role, and with an incorrectly selected "stone", the performance of even the most powerful video card will not be fully revealed.

At the moment, there are only two major processor manufacturers in the consumer market: AMD and Intel. We will talk about them in the traditional rating.

The best inexpensive processors: budget up to 5000 rubles.

4 Intel Celeron G3900 Skylake

Most Affordable Intel Processor
Country: USA
Average price: 4 381 ₽
Rating (2019): 4.5

The rating is opened by an extremely weak Celeron processor. The G3900 model has two cores of the previous generation - Skylake, which, together with the 2.8 GHz frequency, gives the lowest performance result. In synthetic tests, the processor shows a result about half that of the Core i3. But the price here is also quite budgetary - 4-4.5 thousand rubles. This means that this processor is perfect for assembling, for example, a simple office computer or a multimedia system for the living room. In general, this model cannot be called bad. Still, the 14 nm process technology provides good energy efficiency, and the HD Graphics 510 graphics core is suitable for casual games.

Advantages:

• Lowest price in class
• Perfect for office PC or HTPC

Flaws:

• Does not support Hyper-Threading Technology

3 AMD Athlon X4 845 Carrizo

Best price
The country:
Average price: 3 070 ₽
Rating (2019): 4.5

Athlon processors belong to the budget class, which is clearly seen from the cost of the bronze medalist. But for a little over three thousand rubles, you will get a very interesting stone. There are 4 cores (2 logical cores for each physical core), made using a 28 nm process technology. Due to this, the power consumption is low, and the heat dissipation is quite low for AMD - only 65 W. True, you don't have to rejoice at this because of the locked multiplier - you won't be able to overclock the processor. Also, the disadvantages include the lack of an integrated graphics core, which means that when assembling an office PC or a multimedia system, you will have to buy a video card separately.

Advantages:

• Lowest price in class
• Excellent performance at this cost

Flaws:

• Lack of built-in graphics core
• Multiplier not unlocked

2 AMD FX-6300 Vishera

The only 6-core processor in its class
The country: USA (Produced in Malaysia, China)
Average price: 4 160 ₽
Rating (2019): 4.6

AMD's FX-6300 is the only processor in the six-core category. Unfortunately, there is no reason to hope for high power in the budget class - the model is based on the 2012 Vishera core. In normal mode, the cores operate at a frequency of 3.5 GHz, but, like many AMD CPUs, it overclocks perfectly. Yes, the performance, judging by user reviews, is sufficient even for games, but there are still enough disadvantages.

One of the main ones is high energy consumption. Due to the inexpensive 32nm process technology, AMD is very hot and consumes a lot of electricity. Also note the lack of support for modern DDR4 RAM. Because of this, the processor can be advised not for assembling a new PC, but for updating an old one without replacing the motherboard and other components.

Advantages:

• 6 cores. Perfect for performing several simple tasks at the same time.
• Good overclocking potential
• Low cost

Flaws:

• Poor energy efficiency
• Obsolete platform

At the moment, there are only two players on the processor market - Intel and AMD. But the choice doesn't get any easier. To facilitate the decision to purchase a CPU from one manufacturer or another, we have highlighted for you several main pros and cons of the products of these companies.

Company	pros	Minuses
	Programs and games are better optimized for Intel Lower power consumption Performance tends to be slightly higher Higher cache frequencies	Work efficiently with no more than two resource-intensive tasks Higher cost When you change the line of processors, the socket also changes, which means the upgrade is more difficult
	Lower cost Better price-performance ratio Better work with 3-4 resource-intensive tasks (better multitasking) Most processors overclock well	Higher power consumption and temperatures (not entirely true with recent Ryzen processors) Worse program optimization

1 Intel Pentium G4600 Kaby Lake

Better performance
Country: USA
Average price: 7 450 ₽
Rating (2019): 4.7

It is the good old Pentium that we can recommend for purchase in this category. This processor, like the previous participants, is made using a 14 nm process technology, socket LGA1151. Belongs to one of the latest generations - Kaby Lake. There are, of course, only 2 cores. They operate at 3.6 GHz, which is about 18-20% behind the Core i3. But this is not much, because the price difference is twofold! In addition to the core frequency, the relatively low power is due to the small size of the L3 cache - 3071 KB.

In addition to the excellent price-performance ratio, the advantages of this CPU include the presence of an integrated graphics core Intel HD Graphics 630, which is more than enough for comfortable use of a PC without a discrete graphics card.

Advantages:

• Great value for this performance
• Generation Kaby Lake
• Good on-board graphics core

The best processors of the middle class: budget up to 20,000 rubles.

5 Intel Core i3-7320 Kaby Lake

Most Affordable Processor with Integrated Graphics
Country: USA
Average price: 12 340 ₽
Rating (2019): 4.6

Let's open the rating with the most affordable i-core processor. The model is extremely difficult to call excellent in terms of price / quality ratio, because the cheaper ryzen 3 shows even slightly better results in synthetic tests. Nevertheless, the model that opens the TOP-5 can be safely chosen not only for an office system, but also for a gaming computer.

There are only two physical cores, but these are modern 14 nm chips of one of the latest generations - Kaby lake. The frequency is 4100 MHz. This is a very shameful indicator. In addition, there is the possibility of overclocking. Considering the excellent energy efficiency and low heat dissipation - even with a complete cooler in idle, the temperature is kept at 35-40 degrees, under load up to 70 degrees - you can painlessly increase the frequencies. Unlike competitors from AMD, the Core i3 has an integrated graphics core, which allows it to be used in an office system without a discrete graphics card. But keep in mind that it officially only works on Windows 10.

Advantages:

• Integrated graphics
• Overclocking capability
• Low temperatures

Flaws:

• Poor performance for a given cost

4 AMD Ryzen 3 1200 Summit Ridge

Best price
The country: USA (Produced in Malaysia, China)
Average price: 6 917 ₽
Rating (2019): 4.7

Ryzen 3 is AMD's youngest low-cost new line of processors, designed to re-impose the fight on Intel. And the 1200 does the job just fine. For 7 thousand rubles, the buyer gets a 4-core processor. The factory frequencies are low - only 3.1 GHz (in the increased performance mode of 3.4 GHz), but the multiplier is unlocked, which means that enthusiasts can easily make the "stone" a little faster.

Switching to new chips not only improved performance, but also reduced power consumption, and also allowed temperatures to be reduced to acceptable values. Due to the lack of an integrated graphics chip, we can only recommend this processor for budget gaming builds. The performance is only slightly higher than that of the previous participant.

Advantages:

• Unlocked multiplier

Flaws:

• No onboard graphics chip

3 Intel Core i5-7600K Kaby Lake

Great processor for gaming
Country: USA
Average price: 19 084 ₽
Rating (2019): 4.7

Let's start with the fact that the i5-7600K is by no means an outsider. Yes, in terms of performance, it is slightly worse than the mastodons, which you will see below, but for most gamers it will be enough with a head. The processor has four Kaby Lake cores clocked at 3.8 GHz (in reality up to 4.0 GHz with TurboBoost). There is also a built-in graphics core - HD Graphics 630, which means that you can play even demanding games at the "minimum". With a normal video card (for example, GTX 1060), the processor reveals itself completely. In most games at FullHD resolution (these are the monitors most gamers have) and high graphics settings, the frame rate rarely drops below 60 fps. Do you need something else?

Advantages:

• Best price
• Sufficient power for most gamers
• Excellent graphics core

2 AMD Ryzen 5 1600 Summit Ridge

Best price / performance ratio
The country: USA (Produced in Malaysia, China)
Average price: 11 970 ₽
Rating (2019): 4.8

The second line of the TOP-5 mid-range processors is occupied by one of the best processors in terms of price / performance ratio. With an average cost of only 12,000 rubles, in synthetic tests Ryzen 5 is able to compete with the well-known Intel Core i7-7700K at standard settings (in PassMark 12270 and 12050 points, respectively). This power is due to the presence of six Summit Ridge physical cores, made using a 12 nm process technology. The clock speed is not a record - 3.6 GHz. The possibility of overclocking is present, but in the reviews, users claim that at frequencies above 4.0-4.1 GHz, the processor behaves unstable and heats up a lot. With the factory settings in idle, the temperatures are kept at 42-46 degrees, in games 53-57 when using the standard cooler.

Also, high performance is due to large cache volumes of all levels. The CPU supports the modern DDR4-2667 standard, which makes it possible to create excellent computers based on this processor for playing at medium-high settings in FullHD.

Advantages:

• Excellent price / performance ratio
• Heats up a little

Flaws:

• Low overclocking potential

1 AMD Ryzen 7 1700 Summit Ridge

Most powerful processor in its class
The country: USA (Produced in Malaysia, China, China)
Average price: 17 100 ₽
Rating (2019): 4.8

As expected, the top-of-the-line Ryzen 7 processor has the best performance in its class. Once again, one cannot help but recall the cost - for 17 thousand rubles we get power at the level of the top Core i7 of previous years. The processor includes eight cores, split into two clusters. The standard clock speed is only 3.0 GHz, the Ryzen 7 is guaranteed to overclock to 3.7, and with a little luck, up to 4.1 GHz.

Like the previous representatives of the line, the leader is made according to the 12 nm process technology, which allows economical energy consumption. The situation with heat dissipation is good - in stress tests the temperatures are kept at the level of 70-75 degrees.

Advantages:

• High performance
• There is a possibility of overclocking
• Fresh platform that will be supported for at least 4 years

The best top processors

3 Intel Core i7-7700K Kaby Lake

Most popular top processor
Average price: 29 060 ₽
Rating (2019): 4.6

Most recently, the i7-7700K was the top processor in the Intel lineup. But technologies are developing extremely quickly, and in 2018 it is difficult to recommend this particular chip for purchase. In synthetic tests, the model clearly lags behind its competitors - in PassMark the CPU gains only 12 thousand points, which is comparable to modern mid-range processors. But these indicators are achieved at standard settings, when 4 physical cores operate at 4.2 GHz, and the CPU can be easily overclocked to even higher frequencies, thereby increasing performance.

Yes, the bronze medalist lags behind the competitors, but it costs at least half the price, and given the popularity it is quite possible to find a good used processor. Also, the high prevalence and long-standing presence on the market allows you to find an affordable motherboard with an LGA1151 socket. In general, we have before us an excellent base for a powerful gaming system at a relatively low cost.

Advantages:

• Good price for this class
• High performance
• Great overclocking capabilities
• High popularity

Flaws:

• Not quite relevant in 2018

2 Intel Core i9-7900X Skylake

The most powerful processor in the Intel line
Country: USA
Average price: 77 370 ₽
Rating (2019): 4.7

Until recently, Intel's top lineup was the Core i7 series. But modern realities demand more and more power. If you are not familiar with solutions, take a look at the Core i9-7900X. The processor is able to enter the TOP-10 of the most powerful CPUs already at a standard clock frequency. For example, in PassMark, the model scores almost 22 thousand points, which is twice as much as the bronze medalist of the rating. At the same time, in the reviews, users talk about trouble-free overclocking to 4.2-4.5 GHz in the presence of high-quality air cooling. Temperatures do not exceed 70 degrees under load.

This high performance is due to the use of 10 cores, made using a 14 nm process technology. The model supports all the necessary modern standards and commands, which allows it to be used for any task.

Advantages:

• Highest performance
• Excellent overclocking potential
• Acceptable temperatures

Flaws:

• Very high cost
• No solder under the lid.

1 AMD Ryzen Threadripper 1950X

The leader of the rating is insane in everything - from the price of 65 thousand rubles to incredible performance. In terms of power in synthetic tests, the model slightly outperforms the previous participant. At the same time, the internal structure is significantly different. Threadripper uses 16 (!) Cores. The clock speed is comparable to the Core i9 - 3400 MHz - but the overclocking capabilities are more modest. Stable "stone" operates at a frequency of 3.9 GHz, with an increase in rates, the necessary stability is lost.

Such a large number of cores shows itself well in all tasks. But using a monster for games is not entirely reasonable - not all projects can reveal its potential. AMD is useful for professional video editors, 3D designers, and more. - in professional software, an increase in cores gives a tangible increase in render speed.

Advantages:

• Relatively low price tag
• High power
• Excellent performance in professional programs

Processors with integrated graphics have been fighting for a place in the sun for a long time and with varying success. However, initially, no one imagined that graphics cores located on the same semiconductor chip with a CPU would be able to compete with discrete graphics cards. Nevertheless, as semiconductor technologies have improved, manufacturers have learned to build fully-fledged graphics accelerators into processors that can accelerate both 3D graphics, and high-definition video playback, and video transcoding. All of this has become a completely natural and timely response to the changes in the typical environment in which the average computer user lives. Three-dimensional graphics are used everywhere today, even on the Internet, and it is impossible to pass by video content with all the desire.

In addition, games have acquired serious importance, which have become a full-fledged and popular form of mass leisure. The segment of computer entertainment continues to grow at a rapid pace, but not all popular games make serious demands on the power of graphics accelerators. Among other things, network multi-user projects can boast of wide distribution, the needs of which, given the current level of technology development, may well be satisfied not only by traditional graphics cards, but also by integrated 3D accelerators. Therefore, the following statistics are not surprising: almost a third of personal computers sold now do not have a discrete graphics accelerator at all. Moreover, a significant proportion of such systems are home computers purchased for entertainment.

The power of the graphics core that can be built into the processor is limited by two factors: the size of the GPU semiconductor crystal and its heat dissipation. However, with the development of new production technologies and the introduction of modern graphics architectures, the scope of possibilities is gradually expanding. Now, with the widespread introduction of technical processes with 14-nm standards, it has become possible to combine a graphics accelerator with a central processor, which occupies about 100 mm 2 on a chip. This is comparable to the area occupied by the GPU of current discrete graphics cards in the price category "under $ 100". Thus, it all comes down to the fact that modern processors with integrated graphics should be able to reach at least the performance level of the GeForce GT 1030.

And these calculations do not lie. The senior member of the Raven Ridge family (this is the codename AMD named its new project - a Ryzen processor with an integrated graphics core of the Vega generation) promises a theoretical peak performance of 1.76 teraflops, which is comparable to not only the GeForce GTX 1030, but also the GeForce GTX 1050! However, you need to understand that in practice, the graphics performance of the Raven Ridge, like any other processor with integrated graphics, is significantly constrained by the memory bandwidth. While budget discrete graphics cards get their own dedicated memory with bandwidth in excess of 50-100 GB / s, integrated graphics are forced to be content with a shared dual-channel memory controller with the processor, which usually offers significantly worse bandwidth, spiced up with higher latencies.

In some situations, developers solve this problem by adding additional buffer memory to the processor with integrated graphics. For example, the sensational Kaby Lake-G with Radeon RX Vega M graphics will contain its own 4 GB HBM2 video memory. Or another example: the most powerful Intel processors with an integrated video core that have been released so far, Skylake-R, are equipped with a 128MB eDRAM-based victim cache of the fourth level.

However, in the case of the Raven Ridge, this approach does not work. Additional buffer memory increases the cost of the final product, and AMD's strategy is to launch an attack on the lower market segment with its new offerings, offering a good option to those users who build systems from inexpensive CPUs and budget GPUs. Therefore, in Raven Ridge, the bet is made on the intensification of the capabilities of system memory. For the new processor with an integrated video core, AMD engineers have optimized the existing DDR4 memory controller, added support for faster frequency modes and reduced latency. As a result, the company has got a very interesting product that has no close analogues in its market niche.

With the launch of the new Raven Ridge integrated processors, AMD continues its solid return to the CPU market last year as a full-fledged participant. The Zen microarchitecture has already proven its viability as a foundation for performance chips, but now it should serve as the basis for low-cost mainstream integrated processors that AMD has been able to package its current best graphics architecture, Vega. As AMD itself expects, with such a step it will be able to easily "transplant" to its devices those users who until now have been content with discrete graphics cards with a price of less than $ 100. The goal is somewhat ambitious, but considering the steps taken to achieve it, it is quite real.

In addition, it was very fortunate that Raven Ridge came to the rescue at a very difficult time. A shortage of discrete graphics accelerators provoked by crypto enthusiasts is raging on the market, as a result of which even an entry-level video card can be bought today only at a noticeably inflated price. And this means that Raven Ridge can become a kind of "magic wand" for those users who do not want to pay exorbitant prices for a video card and are either willing to be content with integrated solutions, or can afford to wait out the troubled times with their help. In general, the interest in Raven Ridge is huge for many reasons.

Raven Ridge Formula: Zen + Vega

In order to understand what Raven Ridge is, how AMD was able to put together two of its cutting-edge developments, and why it required almost a year of additional engineering efforts, just look at what the semiconductor crystal of the new hybrid processors looks like. Here it is:

You will probably remember that at the heart of all Ryzen processors released to date is a Zeppelin semiconductor crystal, which is assembled from two CCX (Core Complex) modules and the necessary strapping. Each such CCX module has four computational cores with the Zen microarchitecture and a shared L3 cache of 8 MB. The modules are interconnected with each other and with "extra-core" controllers through a special Infinity Fabric bus, which is an improved version of HyperTransport. Thus, all Ryzen without integrated graphics, regardless of how many cores are available to the user, are based on a single eight-core die with an area of ​​about 218 mm 2, including about 4.8 billion transistors.

It is clear that additionally expanding such a large crystal with a graphics core is difficult from a production point of view. Therefore, in order to release Raven Ridge, AMD engineers had to design a different crystal based on the cores with the Zen microarchitecture. In it, the graphics core took the place of the second quad-core CCX module. As a result, the Raven Ridge die area remains almost the same - it is 210 mm 2, and the number of transistors has grown slightly - to 4.94 billion.

"Drive" Raven Ridge into such a framework was by no means a small amount of blood. AMD engineers intended to combine a fairly productive version of the Vega graphics core with the Zen computing cores. Past APUs of the company, codenamed Bristol Ridge, were equipped with an integrated graphics core with GCN 1.3 architecture (for example, it was also used in R9 Fury graphics cards) and in the maximum versions had a set of 512 stream processors. In Raven Ridge, which were initially positioned by AMD as products of a fundamentally different level, the power should have increased by a noticeable amount, so a very large GPU with 11 computing units (CU) was inscribed in the new semiconductor crystal, which in total corresponds to an array of 704 stream processors (SP).

As a result, it was not possible to leave one old CCX borrowed from Zeppelin intact in Raven Ridge, providing the integrated processor with four processing cores and an 8-megabyte L3 cache. In pursuit of cost reduction, engineers had to cut it somewhat. As a result, the volume of the L3 cache memory located in the Raven Ridge CCX module has been halved - to 4 MB. True, its associativity has not changed at the same time, which means that one should not count on a serious change in the speed characteristics of the L3 cache.

Nevertheless, a fourfold reduction in the total volume of the third level cache memory compared to the "big Ryzen" had an effect on its performance: latencies decreased slightly. Below, all this is demonstrated on the graphs, which show the practically measured latency of the memory subsystem of a quad-core Raven Ridge and a quad-core Ryzen 5 1500X processor, brought to a single clock speed of 3.8 GHz.

The L3 cache latency in Raven Ridge has decreased by about 5 clock cycles. They were won back by simplifying the algorithms of work, which now do without maintaining the coherence of parts of the cache memory located in different CCXs.

Along the way, one more curious detail is revealed: a noticeable acceleration in Raven Ridge was also received by the second-level cache. Its latency dropped from 17 to 13 clocks, although the manufacturer did not advertise this change anywhere.

Pointing to the change in the cache memory subsystem, AMD promises that reducing the amount of L3 cache in new processors should not negatively affect performance. Compensating for the negative vector is not only the reduction in latencies, but also the fact that the Raven Ridge does not have to suffer from the relatively slow inter-core connections between CCXs, made by the Infinity Fabric bus operating at the same frequency as the memory controller. Indeed, in the new processor design there is only one CCX-module, and this internal bus connects it with the graphics core and other "extra-core" components, but the exchange of data between the computational cores is in no way concerned.

This can be clearly seen if we compare the practically measured latencies during inter-core data exchange between the Raven Ridge and the Ryzen 5 1500X. Here Raven Ridge wins noticeably - for a quad-core processor, the design with one CCX looks more optimal.

In addition to the caching improvements in Raven Ridge, the memory controller has also been optimized. First, it added official compatibility with DDR4-2933 modules, making the Raven Ridge the first processor on the market to support such a fast JEDEC specification. Second, all other things being equal, the Raven Ridge is more memory efficient than its predecessor Ryzen. Tests indicate a not too dramatic, but still observable with the naked eye, a decrease in latency.

True, here you can see a decrease in the practical bandwidth, but this effect should rather be attributed to the "dampness" of the BIOS of motherboards. Since the release of Raven Ridge, motherboard manufacturers are again actively updating firmware, and new BIOS versions do bring additional performance improvements to the Raven Ridge memory controller.

Thus, in total, the changes in the Raven Ridge memory subsystem are diverse, and the reduced L3 cache is unlikely to be a serious drawback of these processors. But he was not the only one who underwent resection in the Raven Ridge. One more block was also seriously cut - the PCI Express graphics bus controller built into the processor. To connect an external graphics card in Raven Ridge processors, a full PCI Express 3.0 x16 interface is not supported: instead, it is proposed to use a truncated PCI Express 3.0 x8 bus. However, in the case of non-top-tier graphics cards, this limitation is unlikely to have any effect on performance, and the only thing worth keeping in mind is the lack of compatibility of Raven Ridge with multi-GPU configurations.

Raven Ridge does not work with Dual Graphics technology, which was supported in previous generations of AMD APUs. It is impossible to "pair" the built-in Vega graphics core with an external video card with the same architecture into a single multi-GPU array directly using the graphics driver. However, the joint operation of the integrated graphics and an external video card is still possible through the mGPU technology, which is part of DirectX 12. In other words, the built-in Vega can still "help" an external accelerator, and it does not matter which discrete video card is used, but such the bundle will be exclusively in DirectX 12.

Ryzen 2000G Family: Ryzen 5 2400G and Ryzen 3 2200G

AMD has released two desktop variants of the Raver Ridge. Both are based on the same design and are manufactured at GlobalFoundries using a 14nm (14LPP) process that is also used in the case of our familiar Ryzen processors without integrated graphics. This means that, although the hybrid novelties received model numbers from the two thousandth series, the more advanced 12-nm process technology for their release is not used and they have nothing to do with the promising Zen + generation processors, which are scheduled for release in April.

The senior desktop Raven Ridge is a $ 169 Ryzen 5 2400G quad-core processor with SMT support and integrated Vega 11 graphics. Its younger sibling, Ryzen 3 2200G, is also a quad-core processor, but without SMT support and with a weaker Vega 8 graphics core. the characteristics of the new processors can be found in the table, where we have placed them next to the "classic" quad-core Ryzen 5 and Ryzen 3.

	Ryzen 5 2400G	Ryzen 5 1500X	Ryzen 5 1400	Ryzen 3 2200G	Ryzen 3 1300X	Ryzen 3 1200
Codename	Raven Ridge	Summit ridge	Summit ridge	Raven Ridge	Summit ridge	Summit ridge
Production technology, nm	14	14	14	14	14	14
Kernels / threads	4/8	4/8	4/8	4/4	4/4	4/4
Base frequency, GHz	3,6	3,5	3,2	3,5	3,5	3,1
Turbo frequency, GHz	3,9	3,7	3,4	3,7	3,7	3,4
XFR frequency, GHz	-	3,9	3,45	-	3,9	3,45
Overclocking	There is	There is	There is	There is	There is	There is
L3 cache, MB	4	2 × 8	2 × 4	4	2 × 4	2 × 4
Memory support	DDR4-2933	DDR4-2666	DDR4-2666	DDR4-2933	DDR4-2666	DDR4-2666
Integrated graphics	Vega 11	Not	Not	Vega 8	Not	Not
Stream Processors	704	-	-	512	-	-
Graphics core frequency, GHz	1,25	-	-	1,1	-	-
PCI Express Lines	8	16	16	8	16	16
TDP, W	65	65	65	65	65	65
Socket	Socket AM4	Socket AM4	Socket AM4	Socket AM4	Socket AM4	Socket AM4
Official price	$169	$174	$169	$99	$129	$109

If you remember that Raven Ridge is based on a semiconductor crystal with one CCX-module, then it is quite clear that more powerful APU models from AMD are not expected in the foreseeable future. No Ryzen 7 with integrated graphics is possible. Ryzen 5 2400G fully reveals the possibilities that are inherent in the developed design. This processor utilizes all four processor cores and SMT multithreading technology, as well as the full set of 11 Compute Units (CUs) found in the embedded Vega accelerator. It is worth noting that as a result, the Ryzen 5 2400G turned out to be even more powerful than the mobile Ryzen 7 2700U, in which the graphics core uses only 10 out of 11 computing units.

The Ryzen 5 2400G's 11 CUs translate to 704 stream processors, 38 percent more than the arsenal of the Kaveri, Carrizo and Bristol Ridge generations. Combined with this comes a roughly 13 percent increase in graphics frequency, an increased number of texture units (from 32 to 44) and rasterization (from 8 to 16), as well as a new generation of architecture. Vega belongs to the most recent, fifth generation GCN, while the previously embedded video cores had a third generation architecture. All this together should provide a significant superiority of the older novelty over its predecessors in terms of performance.

However, here it will be appropriate to recall the existence of Kaby Lake-G with Radeon RX Vega M graphics again. Obviously, Raven Ridge will not be able to compete with them in any of its manifestations. Due to the fact that in Intel's version of processors with Vega graphics, the video core is located on a separate semiconductor crystal, it is much more powerful - it houses 24 computing units and 1536 stream processors. In addition, do not forget about the separate 4 GB HBM2 memory, which Intel also managed to fit into the processor package. Therefore, the scope of application for Ryzen and Kaby Lake-G with Vega graphics will be different. The Intel variant is a premium and expensive product for laptops and ultra-compact NUC desktops, while AMD is aiming for the mainstream segment.

That is why it is noteworthy that the Ryzen 5 2400G received a recommended price of $ 169: this allows this processor to be a direct and improved alternative to the Ryzen 5 1400. Obviously, the old version without graphics will now gradually go off the shelves, because the Ryzen 5 2400G surpasses the Ryzen 5 1400 in many basic parameters. In addition to having an integrated GPU, it has a higher clock speed (3.6 GHz versus 3.2 GHz - base and 3.9 GHz versus 3.4 GHz - turbo), there is support for faster DDR4-2933 memory and things are much better with inter-core interaction. In fact, the Ryzen 5 1400 can be more interesting only due to the more capacious L3 cache, but it is worth recalling that in this model it is also cut from 16 to 8 MB. Thus, in the vast majority of scenarios, the Ryzen 5 2400G will be faster when operated with an external graphics card.

Ryzen 3 2200G looks no worse than the $ 169 Ryzen 5 2400G in its niche. In terms of baseline performance, this processor is a typical Ryzen 3, with four non-SMT cores and a nominal 3.5 GHz clock rate with auto-overclocking capability up to 3.7 GHz. But to all this is added the comparatively powerful Vega 8 graphics core, and the price is set at $ 99, which makes this offer not only an attractive hybrid APU, but also the cheapest Ryzen in general. That is, even if you forget about the presence of good graphics in the Ryzen 3 2200G, it is unique in that it offers four productive x86 cores at a price below $ 100. There are no other offers of similar generosity at the moment.

As for the Vega 8 accelerator built into the Ryzen 3 2200G, this GPU option offers 512 stream processors, that is, it is at least as good as the graphics from previous generations of APUs, which AMD implemented under the names A10 and A12 at a price significantly exceeding 100- dollar level.

Despite the fact that Ryzen processors with Vega graphics got quite high clock speeds, AMD managed to keep their heat dissipation within reasonable limits. The Ryzen 5 2400G and Ryzen 3 2200G have a typical heat dissipation of 65W - a great achievement when the company's fastest desktop APUs previously could have a design heat dissipation of 95W. And even more, in Raven Ridge, with the simultaneous load on the computing and graphics parts of the processor, the frequency of cores of both types does not drop below the nominal values, as was the case with APUs of previous generations. Even the older Ryzen 5 2400G can remain within the declared thermal package without any tweaks.

Separately, it should be mentioned that the updated Precision Boost 2 technology deals with clock frequency control in Raven Ridge. It implements an improved and more aggressive algorithm, thanks to which the turbo mode in new processors with an integrated graphics core is turned on more often than before. In addition, with an incomplete load on some of the cores, intermediate frequencies between the base and maximum values ​​are more actively involved. In other words, tuning for a specific load in Ryzen 5 2400G and Ryzen 3 2200G is more sensitive than it was before.

However, the XFR technology, which made it possible to additionally increase the frequency when the processor was operated in a favorable temperature mode, is absent in Raven Ridge.

You can install new processors of the Raven Ridge family in the same Socket AM4 motherboards that run other Ryzen. The only limitation is that compatible boards must use an updated BIOS: Raven Ridge requires versions built with AGESA Libraries 1.0.7.1 or later. In other words, the new CPUs with integrated graphics do not require any additional costs. They come to an existing and widespread platform.

Talking about how attractive the combination of price and performance was received by the new desktop Raven Ridge, one cannot ignore the fact that the boxed versions of Ryzen 5 2400G and Ryzen 3 2200G come with a complete Wraith Stealth cooler, the cost of which is also included in the announced $ 169 and $ 99. ...

Of course, such a cooler has nothing to do with high-efficiency cooling solutions, but it will definitely cope with heat removal from 65-watt processors and will allow you to save an additional couple of tens of dollars when building a system on Raven Ridge. Moreover, the capabilities of this cooler will probably suffice for moderate overclocking.