Why you shouldn't buy Intel's eighth-generation Coffee Lake processors just yet. Intel has released the eighth generation of Core CPU 8th series coffee lake processors

As a rule, processors are tested in tandem with top-end video cards of the 1080 Ti or Titan X level. They show the capabilities of the “stones” well, but do not answer the question of what to take for more simple systems. We ordered at "Citylink" three “stones” based on Coffee Lake and prepared a computer for the 1070 Ti Strix.

Test stand

Let's start with the computer. It is based on ASUS TUF Z370-Pro, a board from the mid-segment, but with the right power system, good set ports and flexible BIOS. Why TUF and not Strix? We wanted to take a break from the backlight and get a decent set of technologies, high-quality sound chip hardware, DTS support and fan control.

Specifications ASUS TUF Z370-PRO GAMING
Chipset:	Intel Z370
Socket:	Socket 1151
Form factor:	ATX (305 x 244) cm
RAM:	4x DIMM, DDR4-4000, up to 64 GB
PCIE slots:	3x PCIEx16, 3x PCIEx1
Disk subsystem:	2x M.2, 6x SATA III 6Gb/s
Sound subsystem:	7.1 HD (Realtek ALC887)
Net:	1 Gbit Ethernet (Intel I219V)
Panelinput/output:	PS/2, DVI-D, HDMI, RJ45, 2x USB 3.1 Type-A, 4x USB 3.0, 2x USB 2.0, Optical S/PDIF, 5x 3.5 mm audio
Price for February 2018:	11,500 rubles ($205)

A DeepCool MAELSTROM 120K air cooler was installed to cool the “stones”. It is suitable for both top-end i5 and i7, as well as i3. Intel turned it out hot and reaches 71°C under load.

The case is spacious, with a pair of turntables, and is designed for dual liquid cooling radiators. Note that the standard fans are installed on the front panel and that for assembly without a cooling fan you will have to either rearrange one of the fans or buy an additional one.

1070 Ti was taken by ASUS Strix. This series has been talked about more than once, so let’s just note important points. The card is cooled by an aluminum radiator with three turntables, the main elements are glued with thermal pads, and the processor takes 1962 MHz versus 1683 from the reference and stays within 53°C.

And finally, Seasonic was sent to provide power at 650 W - cold and with enormous efficiency. Anticipating comments in the spirit of “why such an expensive power supply?”, let’s say right away. The computer would run on FSP for 2500 rubles, but we rely on reliability and stability. If you don't like this option, we don't insist.

CPU

And now about the tests. We ended up with a pre-top system with a budget of approximately 100 thousand rubles. “Approximately” because the price for the video card is recommended, and if you don’t focus on quality, flexibility and maximum frequencies, you can save on the chipset, memory and power supply. But that's not the point. Let's see which processor is suitable for such a computer.

So, there are three “stones” on hand - i3-8350K, i5-8600K and i7-8700K. All of them were tested in stock and in total passed seven gaming and thirteen processor tests, including both synthetic and real applications. The result is interesting.

CPU	Core i7-8700K	Core i5-8600K	Core i3-8350K
Microarchitecture	Coffee Lake	Coffee Lake	Coffee Lake
Technical process	14 nm	14 nm	14 nm
Socket	LGA1151	LGA1151	LGA1151
Cores/threads	6/12	6/6	4/4
L3 cache	12 MB	9 MB	8 MB
Frequency	3.7-4.7 GHz	3.6—4.3 GHz	4 GHz
Memory channels	2	2	2
Memory type	DDR4-2666	DDR4-2666	DDR4-2666
PCI Express lines	16	16	16
Thermal package (TDP)	95 W	95 W	91 W
Price for February 2018	28,000 rubles ($500)	19,390 rubles ($345)	11,210 rubles ($200)

There's not much difference in gaming with the 1070 Ti. This means that for the first time in a long time, i3 can be purchased for purely gaming systems, even with powerful video cards.

The conclusion from this is simple. For gaming computer Core i3 is enough for up to 80-100 thousand rubles. Older processors are worth buying if you are interested in work tasks. Which model to take - decide for yourself, we have given the processor tests and breakdown.

Let us repeat once again that the choice in favor of i3 applies only to systems with 1080-level video cards. With Ti or Titan X, older Core i5 with i7 will go ahead. However, this can be compensated for by overclocking. All processors are overclocked, and from the same i3 we squeezed 4.4 GHz, and from the i7 - 4.7 GHz.

CPU tests
3ds Max 2017
Scene rendering (V-Ray), s, (less is better)
Core i7-8700K	Core i5-8600K	Core i3-8350K
180	239	387
Photoshop CS6
Filter overlay, s, (less is better)
135	164	216
Media Coder .264
Video encoding MPEG2 ->MPEG4 (H.264), (less is better)
113	163	183
Cinebench R15
1543	1059	678
7zip
Rate, MIPS
43138	29197	18764
WinRar 5.10
Archiving speed, KB/s
19533	10318	6903
Corona 1.3
129	212	343
V-Ray Benchmark
Rendering time, s, (less is better)
82	114	182
Zbrush 4R7 P3
Rendering time (Best, 4x SS), s, (less is better)
94	132	200
x265 Benchmark
Encoding time, s (less is better)
39	45	71

CPU tests
SPECwpc 2.1
Performance index
	Core i7-8700K	Core i5-8600K	Core i3-8350K
Media and Entertainment	3,45	2,84	2,65
Product Development	2,31	1,81	1,67
SVPmark 3.0.3
Performance index
Decode Video	36	27	18
Vector Search	3,34	2,53	1,6
Frame Composition	6,27	5,88	4,42
GeekBench 4.2.0
Performance index
Multi-core CPU	26940	22573	15785
AES (multi-core)	15421	16771	16743

Game tests
Battlefield 1
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
High	102	102	102
Ultra	91	92	91
1920x1080
High	141	139	137
Ultra	126	124	125
Total War: WARHAMMER II
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
High	72	72	72
Ultra	55	55	56
1920x1080
High	113	113	113
Ultra	81	80	82
For Honor
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
High	105	105	105
Very High	81	81	81
1920x1080
High	167	166	167
Very High	129	129	129
Tom Clancy's Ghost Recon: Wildlands
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
Very High	67	66	67
Ultra	44	45	45
1920x1080
Very High	89	89	90
Ultra	57	58	58
DiRT 4
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
High	163	136	134
Ultra	111	97	96
1920x1080
High	204	170	170
Ultra	147	135	133
PLAYERUNKNOWN'S BATTLEGROUNDS
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
High	104	106	98
Ultra	71	71	71
1920x1080
High	141	142	143
Ultra	113	104	109
Mass Effect: Andromeda
	Core i7-8700K	Core i5-8600K	Core i3-8350K
2560x1440
High	94	98	96
Ultra	65	64	64
1920x1080
High	100	102	100
Ultra	96	95	96

Hi all! Not so long ago Intel company presented to users its new brainchild - processors of the Coffee Lake line. And at the start of sales in Russia, they, like many other innovations, will be a frenzied excitement. Today I will not make a comparison, make detailed review, to identify the best model in the line, but I’ll just explain to you why buying new products in the first couple of months is not profitable. And it’s not all about the coffee, it’s all about e What is written below applies to absolutely any innovation. I take the new processors from Intel as an example, only because this topic is now relevant and the brightest in the field of computer technology.

So, the first reason to refuse to purchase in the near future is the price. In most cases, a new product will cost you more. The amount of overpayment depends on a huge number of factors. For example, depending on the number of models in the first batch prepared for sale, the fewer processors that are released to the market at first, the more people there will be who want to be among the first to purchase a stone. This means that dealers and distributors can adjust prices as they see fit. The recommended price for the i5 8400 is $182, which at the time of writing this is approximately 10,500 rubles. Not only is the price abroad already high, but it’s no secret that in Russia it will be even higher. Not in any store this moment there are no stones, but you can already purchase new processors in the foreign ComputerUniverse. The i5 8400 costs about 12,000 rubles, which is 1,500 rubles more expensive than indicated in the recommendations. And let me remind you that prices there, in comparison with DNS or Citylink, may differ by 10-20% in favor of the German site.

Moreover, it is important to understand that new stones are aimed at all three main market segments - budget, medium and premium. Stones in the budget and mid-range segments are in much greater demand than stones in the premium segment. This means that the number of budget models on the market is significantly greater than models from the premium segment. It follows that for the top models in the line, the price will be even more inflated. For example, the best i7-8700K in the line should cost $359, which equals 20,500 rubles. But even abroad it costs about 26,000-27,000 rubles.

That is, for the average i5 8400 the overpayment is currently about 1,500 rubles, and for the top-end i7 8700k the overpayment is already about 5,000 rubles. In our stores the price will be even higher.

• However, exceptions to the rules still happen. Just remember the recently released , which was approximately equal to the recommended price. How did this happen? It's anyone's guess, but I don't think the same thing will happen with coffee.

The next reason is the dampness of the product. And although the new line of processors has very tasty options, it is important to understand that even a successful new product requires some time to break in. Just remember how it is with the Rizens. At the start of sales, standard BIOSes did not reveal the full potential of processors, and only with new versions came optimization and correct operation. Multithreading was not stable in some applications, and only after the appearance of patches did everything return to normal. And the point here is not in the processor itself, but in how other components interact with it, both at the hardware and software levels. Just look at the situation with boxed coolers, when they didn’t stand up to motherboards due to the fact that the fastening did not fit. And this problem was not on the part of AMD, but on the part of motherboard manufacturers, but for us users it doesn’t matter who is to blame, the main thing for us is that everything works correctly and reliably. Of course, it’s not a fact that the same thing will happen to Intel, but anything can happen. Even before Ryazan, the most striking example is Windows 10, which for a very long time was in the so-called “beta testing” state, when there were a lot of errors and bugs and they were corrected over time with each new patch until the operating system became stable Overall, all I'm saying is that any new product tends to run into some unexpected problems at first, so you should wait until those problems are resolved.

The third reason is marketing. The era of marketing, what can I say. Marketing decisions are present in any area of ​​production and computer technology is no exception. The new socket 1151 v.2, which will support Coffee Lake, currently has only one chipset on the market - the z370, which is premium, very expensive and supports overclocking.

What is this if not marketing? Those who want to buy simple i3 8100 and i5 8400 stones will have to buy the motherboard for the first two months on this particular chipset. But why, if these stones cannot be overclocked? Obviously, this is a premeditated move that will force those who want to be among the first to buy more expensive motherboards with a top-end chipset. The simplest H370 and H310 chipsets will appear only in the new year. Returning to the question of price, we can include motherboards here. Due to the shortage on the market, at first they will cost significantly more.

And the last reason is competition. There is actually a duopoly currently reigning in the processor production market. Accordingly, the more successful the new product is for some, the more radical measures others need to take in order to retain their audience or attract new customers. That's what happened with Vega. Its release encouraged the green ones to develop it, because Nvidia saw a strong competitor in the Vega 56. This was the case with Ryzen. After the release of Ryazhenka, prices for blue processors of the Kaby Lake series dropped sharply due to the fact that the new Coffee Lake line was still in development, and buyers needed to be encouraged to buy their product. There are many examples in history. The most important thing is that, ultimately, we, the end users, benefit from all these manipulations in any case. Perhaps the release of Coffee Lake will force the Reds to tighten up and update the Ryzen line in the near future. This may not happen, but it’s worth waiting a couple of months in any case, there is more than one reason for this.

Intel today introduced its eighth generation Core processors. Only this announcement did not turn out at all what we expected. Firstly, they presented only four CPUs of the Core i5 and Core i7 families. Secondly, they are not called Coffee Lake at all, but Kaby Lake Refresh.

So, first, about the processors themselves.

Model	Number of cores/threads	Frequency, GHz	L3 cache size, MB	GPU	GPU frequency, MHz	TDP, W	Price, dollars
Core i5-8250U	4/8	1,6-3,4	6	UHD Graphics 620	300/1100	15	297
Core i5-8350U	4/8	1,7-3,6	6	UHD Graphics 620	300/1100	15	297
Core i7-8550U	4/8	1,8-4,0	8	UHD Graphics 620	300/1150	15	409
Core i7-8650U	4/8	1,9-4,2	8	UHD Graphics 620	300/1150	15	409

So, as we see, mobile CPUs of the U family have now become quad-core, which is one of the most impressive changes in Intel processors in recent years. In addition, this was achieved while maintaining the TDP at 15 W. However, of course, this did not come in vain. As you can see, the frequencies are significantly lower than those of its predecessors. Moreover, all new products received a junior GPU UHD Graphics 620, while some Kaby Lake CPUs use the Iris Plus Graphics 640 core. That is, in some tasks the new processors may even be inferior to the old ones, but in general there should be a very significant advantage, especially in resource-intensive ones applications. Also, the actual energy consumption of new products will most likely still be higher.

Now let's move on to an equally interesting part of Intel's presentation. Recently, we have repeatedly asked questions regarding the logic of releasing new generations of the company’s CPUs. We finally have answers. The thing is that from now on one numbered generation of Intel processors can include several generations of CPUs that are different from an architectural point of view. More precisely, the eighth generation Core will ultimately consist not only of Kaby Lake Refresh models, but also Coffee Lake and even Cannonlake processors.

Probably, Intel decided to do this in order to at least somewhat streamline the too large number of new solutions that will be released in a short period of time. Intel promises eighth-generation desktop models in the fall, without specifying a time frame. Apparently, these processors will be called Coffee Lake-S, although they could also be called Kaby Lake Refresh. Further, within the framework of the eighth generation, there will even be a change in the technical process, since Cannonlake solutions will be 10-nanometer. In the end, everything comes together, since the ninth generation, as we already know, will be called Ice Lake. True, this probably means that with the transition to these processors, Intel will again return to the principle of one architectural generation per number.

All news for today

• 00:05 5 A gallium nitride charger was released with the Xiaomi Mi 10 Pro. It is half the size of the original adapter
• 22:04 7 Nvidia introduced the "GeForce RTX 2077". Only 200 of these video cards will be produced.. In honor of the game Cyberpunk 2077
• 21:43 7 Inexpensive “professional” AirPods will be delayed. Apparently due to coronavirus
• 20:42 6 A new image of the Fujifilm X-T4 camera has appeared. The entire camera is shown from the front and back
• 20:23 2 Sales of the Vazen 28mm T2.2 Micro Four Thirds anamorphic lens have begun. Vazen 28mm T2.2 lens costs $3,250

At the beginning of April 2018, Intel finally filled the gaps in its line of processors based on the Coffee Lake architecture. Now we have the opportunity to purchase budget Pentium and Celeron. Several intermediate Core i3 and Core i5 models also appeared. In addition, the long-awaited motherboards based on the H370, B360 and H310 chipsets have gone on sale.

Before we delve into the intricacies of choosing a processor, a little about motherboards based on 300 series chipsets.

Boards based on H310 are the best in terms of price-features ratio, because all 8th processors will work perfectly on them Intel generation. Unless there may not be enough power for the i7-8700, and, of course, there is no talk of any overclocking. Only processors with the “K” index are overclocked and only on motherboards with the Z370 chipset.

Boards built on the B360 and H370 chipsets fill the gap between the most budget H310-based products and the top-end Z370-based products. However, one thing is worth noting interesting fact, that in April-May 2018 such boards may cost more than the cheapest Z370 models. At the same time, they have less functionality and can only offer some purely “marketing features” (lighting, painting, decorative radiators and other useless elements). The pricing logic is still unclear. Perhaps in the future they will become cheaper and then it will make sense to buy them.

When choosing a processor, we will, first of all, be guided by the “price-performance” principle, because this approach is optimal when building a budget PC and saves you money in any case. It is also worth noting that all desktop Intel processors have built-in graphics, and in any case you will be able to use office applications, surf the Internet, watch videos high resolution and play simple 2D games. Regarding the Box and Tray (OEM) versions of the processor configuration, things are as follows: if in a particular store the price difference between the version with a standard cooler (Box) and the version without a cooler (Tray) is significant, and with this difference you can buy a more efficient cooling system , then take the Tray version and a separate cooler. The benefits from such a purchase will be greater. However, do not let your guard down: some stores give a 12-month warranty instead of 36 for the Tray version.

Now let's start looking at processors, starting with the weakest.

Celeron G4900– the cheapest 8th generation processor. It has 2 cores / 2 threads with a frequency of 3.1 GHz and a modest TDP of 54 W. The third level cache is only 2 MB. Supports dual-channel DDR4-2400 memory with a maximum capacity of up to 64 GB. Integrated graphics – Intel UHD Graphics 610.

It’s worth buying either when there is no money at all, or if the processor is taken as a “plug” for an expensive Z370 motherboard, on which the entire budget was spent, but not enough for a stone. Because in 2018, two cores are extremely few.

We will not consider the G4900T and G4920 models as options. Because the G4900T is the same G4900, only with a frequency of 2.9 GHz and a TDP of 35 W for the same money. And the G4920 has a frequency of only 100 MHz higher than the G4900, which has almost no effect on performance, but it is more expensive.

Pentium Gold G5400– the next contender for a budget build. It has 2 cores / 4 threads (which is important for games) with a frequency of 3.7 GHz and a TDP of 54 W. The third level cache is already 4 MB. There is integrated Intel UHD Graphics 610 on board, the same as in the Celeron G4900.

With this processor you can already play everything modern games, if you pair it with a good video card. Medium and high settings in Full HD resolution are provided to you.

We will not consider the G5500 and G5600 models either. Availability of more powerful Intel The UHD Graphics 630 in these processors does not make a difference given such a difference in price.

As with the Celeron, boosting the frequency by 100 MHz and 200 MHz respectively is not worth the money.

Core i3-8100-golden mean. Four full-fledged physical cores with a frequency of 3.6 GHz and a third level cache of 6 MB. The heat generation did not increase much - 65W. A boxed cooler can easily cope with such a heat package. Until recently, it was almost the best “people's” 8th generation Intel processor. But with the release of Pentiums with hypertrading, I lost my position a little. And AMD Ryzen at a similar price also looks good. Although 4 physical cores still give an advantage, at least over Pentiums and Celerons.

One thing cannot be taken away from the i3-8100 - it almost “destroyed” all previous quad-core Core i5s, making their purchase pointless, since it offers similar performance for a lower price.

You can skip the Core i3-8300 processor, because it’s not worth overpaying for 100 MHz frequencies and an additional 2 MB of cache. It is unremarkable, which cannot be said about the next processor.

Core i3-8350K– yes, it’s a Core i3, and, yes, it can be overclocked! The second Core i3 model in Intel's history with the "K" index. The first was the Intel Core i3-7350K based on the Kaby Lake architecture, but it only had 2 cores and 4 threads. Now you have at your disposal 4 physical cores running at 4 GHz in stock. With good cooling, it accelerates to 5 GHz without any problems and maintains this frequency stably. TDP is already 91 W and it will increase with overclocking.

Please note that Intel processors with an unlocked multiplier, despite the “Box” version, do not have a standard cooler included, as if hinting that good cooling is needed. You can have good air or dropsy - it’s your choice. Of course, for overclocking you need a board with the Z370 chipset.

And here a dilemma appears: buy an i3-8350K, a Z370 motherboard and overclock it all, or take the cheapest one with the H310 chipset, and transfer the saved money to the processor budget and reach for the Core i5.

Core i5-8400– 6 cores / 6 threads, 9 MB of third-level cache, frequency 2.8 GHz (boost 4.0 GHz). Supports DDR4-2666 up to 64 GB and all this at a TDP of 65 W. The characteristics do not need explanation, a truly “people's processor”. A stock cooler and the cheapest motherboard with the H310 chipset will be enough for him. There's no point in overpaying. You can also take a couple of DDR4-2666 sticks with a total capacity of 8 or 16 GB and you will get an excellent gaming build for a very reasonable price.

Next come the not particularly interesting i5-8500 and i5-8600 processors. The first has a stock frequency of 3 GHz (200 MHz more) and a boost frequency of 4.1 GHz (100 MHz more). And the second is 3.6 GHz (already 800 MHz more!) in the drain and 4.3 GHz (300 MHz more) in the boost with a TDP of 65 W. A very good processor for the money, if there weren’t a Core i5-8600K on the market.

Core i5-8600K– in stock it is like a regular 8600, but it can be overclocked. As in the case of the i3-8350K, you will need good cooling (after all, the stated 95 watt TDP is not the limit) and a motherboard with the Z370 chipset. In return, you get excellent performance. Paired with a GTX 1080 Ti-level video card, this processor will handle any games at maximum settings.

By buying and overclocking this stone, you provide yourself with five years in advance and have the opportunity to skip a couple of generations of new processors. You won't have to worry about upgrading anytime soon.

Core i7-8700 and Core i7-8700K are the current flagships of the Coffee Lake architecture. The Core i7-8700 has frequencies of 3.2 GHz in stock and 4.6 GHz in boost, and the Core i7-8700K has frequencies of 3.7 GHz and 4.7 GHz, respectively. In all other respects, the processors are identical: 6 cores / 12 threads, 12 MB of third-level cache. There is also a difference in TDP: the i7-8700 has 65 W (which is hard to believe) and 95 W for the i7-8700K.

The i7-8700 comes with a stock cooler, but when buying such an expensive processor, it wouldn’t hurt to fork out more for cooling. The Core i7-8700K, of course, does not have complete cooling.

By purchasing such a processor, you get all the best that is available at the moment. However, you must clearly know and understand why you need such power. Or just overpay for unnecessary features that you will never take full advantage of.

conclusions

When choosing a processor, allocate your budget wisely. If the computer is for office use (for study, multimedia), then you should not buy an expensive i3, i5 or i7. Pentium and Celeron can cope with the task quite well. It is better to invest the saved money in an SSD, HDD or monitor.

If the computer is intended to be a gaming computer, then keep in mind that a good video card is about 1/3 of the cost system unit. And the motherboard must match the capabilities of the processor. In other words, it’s stupid to buy a Core i7-8700, put it in a board with the H310 chipset and complete it with a GT 1030 video card. Such a combination, of course, will work, but powerful processor will stand idle uselessly due to a weak video card. There will be much more benefit, for example, from assembling a Core i3-8100 + a cheap H310 motherboard + a GTX 1050 Ti-level video card.

Almost always, under any publication that in one way or another touches on the performance of modern Intel processors, sooner or later several angry reader comments appear that progress in the development of Intel chips has long stalled and there is no point in switching from the “good old Core i7-2600K "to something new. In such remarks, most likely, there will be irritated mention of productivity gains at an intangible level of “no more than five percent per year”; about the low-quality internal thermal interface, which irreparably damaged modern Intel processors; or about what to buy in modern conditions processors with the same number of computing cores as several years ago are generally the lot of short-sighted amateurs, since they do not have the necessary reserves for the future.

There is no doubt that all such remarks are not without reason. However, it seems very likely that they are greatly exaggerating the existing problems. The 3DNews laboratory has been testing Intel processors in detail since 2000, and we cannot agree with the thesis that any kind of their development has come to an end, and what has been happening with the microprocessor giant in recent years can no longer be called anything other than stagnation. Yes, any drastic changes with Intel processors rarely occur, but nevertheless they continue to be systematically improved. Therefore, those Core i7 series chips that you can buy today are obviously better models, proposed several years ago.

Generation Core	Codename	Technical process	Development stage	Release time
2	Sandy Bridge	32 nm	So (Architecture)	I quarter 2011
3	IvyBridge	22 nm	Tick ​​(Process)	II quarter 2012
4	Haswell	22 nm	So (Architecture)	II quarter 2013
5	Broadwell	14 nm	Tick ​​(Process)	II quarter 2015
6	Skylake	14 nm	So (Architecture)	III quarter 2015
7	KabyLake	14+ nm	Optimization	I quarter 2017
8	CoffeeLake	14++ nm	Optimization	IV quarter 2017

Actually, this material is precisely a counterargument to arguments about the worthlessness of Intel’s chosen strategy for the gradual development of consumer CPUs. We decided to collect in one test the older Intel processors for mass platforms over the past seven years and see in practice how much the representatives of the Kaby Lake and Coffee Lake series have advanced relative to the “reference” Sandy Bridge, which over the years of hypothetical comparisons and mental contrasts have become in the minds of ordinary people a true icon of processor engineering.

⇡ What has changed in Intel processors from 2011 to the present

Starting point in modern history development of Intel processors is considered to be microarchitecture SandyBridge. And this is not without reason. Despite the fact that the first generation of processors under the Core brand was released in 2008 based on the Nehalem microarchitecture, almost all the main features that are inherent in modern mass CPUs of the microprocessor giant came into use not then, but a couple of years later, when the next generation became widespread processor design, Sandy Bridge.

Now Intel has accustomed us to frankly leisurely progress in the development of microarchitecture, when innovations have become very few and they almost do not lead to an increase in the specific performance of processor cores. But just seven years ago the situation was radically different. In particular, the transition from Nehalem to Sandy Bridge was marked by a 15-20 percent increase in IPC (the number of instructions executed per clock), which was caused by a deep reworking of the logical design of the cores with an eye to increasing their efficiency.

Sandy Bridge laid down many principles that have not changed since then and have become standard for most processors today. For example, it was there that a separate zero-level cache appeared for decoded micro-operations, and a physical register file began to be used, which reduces energy costs when operating out-of-order instruction execution algorithms.

But perhaps the most important innovation was that Sandy Bridge was designed as a unified system-on-a-chip, designed simultaneously for all classes of applications: server, desktop and mobile. Most likely, public opinion placed him as the great-grandfather of modern Coffee Lake, and not some Nehalem and certainly not Penryn, precisely because of this feature. However, the total amount of all the alterations in the depths of the Sandy Bridge microarchitecture also turned out to be very significant. Ultimately, this design lost all the old kinship with the P6 (Pentium Pro) that had appeared here and there in all previous Intel processors.

Speaking about the general structure, one cannot help but recall that a full-fledged graphics core was built into the Sandy Bridge processor chip for the first time in the history of Intel CPUs. This block went inside the processor after the DDR3 memory controller, shared by the L3 cache and the PCI Express bus controller. To connect the computing cores and all other “extra-core” parts, Intel engineers introduced into Sandy Bridge a new scalable ring bus at that time, which is used to organize interaction between structural units in subsequent mass-produced CPUs to this day.

If we go down to the level of the Sandy Bridge microarchitecture, then one of its key features is support for the family of SIMD instructions, AVX, designed to work with 256-bit vectors. By now, such instructions have become firmly established and do not seem unusual, but their implementation in Sandy Bridge required the expansion of some computing actuators. Intel engineers strived to make working with 256-bit data as fast as working with vectors of smaller capacity. Therefore, along with the implementation of full-fledged 256-bit execution devices, it was also necessary to increase the speed of the processor and memory. Logical execution units designed for loading and storing data in Sandy Bridge received double the performance, in addition, the throughput of the first level cache when reading was symmetrically increased.

It is impossible not to mention the fundamental changes made in Sandy Bridge in the operation of the branch prediction block. Thanks to optimizations in the applied algorithms and increased buffer sizes, the Sandy Bridge architecture made it possible to reduce the percentage of incorrect branch predictions by almost half, which not only had a noticeable impact on performance, but also made it possible to further reduce the power consumption of this design.

Ultimately, from today’s perspective, Sandy Bridge processors could be called an exemplary embodiment of the “tock” phase in Intel’s “tick-tock” principle. Like their predecessors, these processors continued to be based on a 32-nm process technology, but the performance increase they offered was more than convincing. And it was fueled not only by the updated microarchitecture, but also by clock frequencies increased by 10-15 percent, as well as the introduction of a more aggressive version of Turbo Boost 2.0 technology. Taking all this into account, it is clear why many enthusiasts still remember Sandy Bridge with the warmest words.

The senior offering in the Core i7 family at the time of the release of the Sandy Bridge microarchitecture was the Core i7-2600K. This processor received a clock frequency of 3.3 GHz with the ability to auto-overclock at part load to 3.8 GHz. However, the 32-nm representatives of Sandy Bridge were distinguished not only by relatively high clock frequencies for that time, but also by good overclocking potential. Among the Core i7-2600K it was often possible to find specimens capable of operating at frequencies of 4.8-5.0 GHz, which was largely due to the use of a high-quality internal thermal interface - flux-free solder.

Nine months after the release of the Core i7-2600K, in October 2011, Intel updated its older offering in model range and offered a slightly accelerated Core i7-2700K model, the nominal frequency of which was increased to 3.5 GHz, and the maximum frequency in turbo mode to 3.9 GHz.

However, the life cycle of the Core i7-2700K turned out to be short - already in April 2012, Sandy Bridge was replaced by an updated design IvyBridge. Nothing special: Ivy Bridge belonged to the “tick” phase, that is, it represented a transfer of the old microarchitecture to new semiconductor rails. And in this regard, the progress was indeed serious - Ivy Bridge crystals were produced using a 22-nm process technology based on three-dimensional FinFET transistors, which were just coming into use at that time.

At the same time, the old Sandy Bridge microarchitecture at a low level remained practically untouched. Only a few cosmetic tweaks were made to speed up Ivy Bridge's division operations and slightly improve the efficiency of Hyper-Threading technology. True, along the way, the “non-nuclear” components were somewhat improved. The PCI Express controller gained compatibility with the third version of the protocol, and the memory controller increased its capabilities and began to support high-speed overclocking DDR3 memory. But in the end, the increase in specific productivity during the transition from Sandy Bridge to Ivy Bridge was no more than 3-5 percent.

The new technological process did not provide serious reasons for joy either. Unfortunately, the introduction of 22 nm standards did not allow for any fundamental increase in Ivy Bridge clock frequencies. The older version of the Core i7-3770K received a nominal frequency of 3.5 GHz with the ability to overclock in turbo mode to 3.9 GHz, that is, from the point of view of the frequency formula, it turned out to be no faster than the Core i7-2700K. Only energy efficiency has improved, but users desktop computers This aspect is traditionally of little concern.

All this, of course, can be attributed to the fact that no breakthroughs should occur at the “tick” stage, but in some ways Ivy Bridge turned out to be even worse than its predecessors. We're talking about acceleration. When introducing carriers of this design to the market, Intel decided to abandon the use of flux-free gallium soldering of the heat distribution cover to the semiconductor chip during the final assembly of processors. Starting with Ivy Bridge, banal thermal paste began to be used to organize the internal thermal interface, and this immediately hit the maximum achievable frequencies. Ivy Bridge has definitely become worse in terms of overclocking potential, and as a result, the transition from Sandy Bridge to Ivy Bridge has become one of the most controversial moments in the recent history of Intel consumer processors.

Therefore, for the next stage of evolution, Haswell, special hopes were placed. In this generation, belonging to the “so” phase, serious micro-architectural improvements were expected to appear, from which it was expected to be able to at least push forward stalled progress. And to some extent this happened. The fourth generation Core processors, which appeared in the summer of 2013, did acquire noticeable improvements in the internal structure.

The main thing: the theoretical power of Haswell actuators, expressed in the number of micro-operations executed per clock cycle, has increased by a third compared to previous CPUs. In the new microarchitecture, not only was the existing actuators rebalanced, but two additional execution ports appeared for integer operations, branch servicing and address generation. In addition, the microarchitecture gained compatibility with an expanded set of vector 256-bit instructions AVX2, which, thanks to three-operand FMA instructions, doubled the peak throughput of the architecture.

In addition to this, Intel engineers reviewed the capacity of internal buffers and, where necessary, increased them. The planner window has grown in size. In addition, the integer and real physical register files were enlarged, which improved the processor's ability to reorder the execution order of instructions. In addition to all this, the cache subsystem has also changed significantly. L1 and L2 caches in Haswell received a twice wider bus.

It would seem that the listed improvements should be enough to significantly increase the specific performance of the new microarchitecture. But no matter how it is. The problem with Haswell's design was that it left the front end of the execution pipeline unchanged and the x86 instruction decoder retained the same performance as before. That is, the maximum rate of decoding x86 code in microinstructions remained at the level of 4-5 commands per clock cycle. And as a result, when comparing Haswell and Ivy Bridge at the same frequency and with a load that does not use the new AVX2 instructions, the performance gain was only 5-10 percent.

The image of the Haswell microarchitecture was also spoiled by the first wave of processors released on its basis. Based on the same 22nm process technology as Ivy Bridge, the new products were unable to offer high frequencies. For example, the older Core i7-4770K again received a base frequency of 3.5 GHz and a maximum frequency in turbo mode of 3.9 GHz, that is, there has been no progress compared to previous generations of Core.

At the same time, with the introduction of the following technological process With 14-nm standards, Intel began to encounter all sorts of difficulties, so a year later, in the summer of 2014, it was not the next generation of Core processors that was launched on the market, but the second phase of Haswell, which received the code names Haswell Refresh, or, if we talk about flagship modifications , then Devil's Canyon. As part of this Intel updates was able to significantly increase the clock speeds of the 22nm CPU, which really breathed new life into them. As an example, we can cite the new senior Core i7-4790K processor, which at its nominal frequency reached 4.0 GHz and received a maximum frequency taking into account turbo mode at 4.4 GHz. It is surprising that such a half-GHz acceleration was achieved without any process reforms, but only through simple cosmetic changes in the processor power supply and by improving the thermal conductivity properties of the thermal paste used under the CPU cover.

However, even representatives of the Devil’s Canyon family could not become especially complained about proposals among enthusiasts. Compared to the results of Sandy Bridge, their overclocking could not be called outstanding; moreover, achieving high frequencies required complex “scalping” - removing the processor cover and then replacing the standard thermal interface with some material with better thermal conductivity.

Due to the difficulties that plagued Intel when transferring mass production to 14 nm standards, the performance of the next, fifth generation of Core processors Broadwell, it turned out very crumpled. The company could not decide for a long time whether it was worth releasing desktop processors with this design onto the market, since when attempting to manufacture large semiconductor crystals, the defect rate exceeded acceptable values. Ultimately, Broadwell quad-core processors intended for desktop computers did appear, but, firstly, this happened only in the summer of 2015 - with a nine-month delay relative to the originally planned date, and secondly, just two months after their announcement, Intel presented the design next generation, Skylake.

Nevertheless, from the point of view of microarchitecture development, Broadwell can hardly be called a secondary development. And even more than that, desktop processors of this generation used solutions that Intel had never resorted to before or since. The uniqueness of desktop Broadwells was determined by the fact that they were equipped with a powerful integrated graphics core Iris Pro at the GT3e level. And this means not only that the processors of this family had the most powerful integrated video core at that time, but also that they were equipped with an additional 22-nm Crystall Well crystal, which is a fourth-level cache memory based on eDRAM.

The point of adding a separate fast integrated memory chip to the processor is quite obvious and is determined by the needs of a high-performance integrated graphics core in a frame buffer with low latency and high bandwidth. However, the eDRAM memory installed in Broadwell was architecturally designed specifically as a victim cache, and it could also be used by the CPU cores. As a result, Broadwell desktops have become the only mass-produced processors of their kind with 128 MB of L4 cache. True, the volume of the L3 cache located in the processor chip, which was reduced from 8 to 6 MB, suffered somewhat.

Some improvements have also been incorporated into the basic microarchitecture. Even though Broadwell was in the tick phase, the rework affected the front end of the execution pipeline. The window of the out-of-order command execution scheduler was enlarged, the volume of the second-level associative address translation table increased by one and a half times, and, in addition, the entire translation scheme acquired a second miss handler, which made it possible to process two address translation operations in parallel. In total, all the innovations have increased the efficiency of out-of-order execution of commands and prediction of complex code branches. Along the way, the mechanisms for performing multiplication operations were improved, which in Broadwell began to be processed at a significantly faster pace. As a result of all this, Intel was even able to claim that microarchitecture improvements increased the specific performance of Broadwell compared to Haswell by about five percent.

But despite all this, it was impossible to talk about any significant advantage of the first desktop 14-nm processors. Both the fourth level cache and microarchitectural changes only tried to compensate for Broadwell's main flaw - low clock speeds. Due to problems with the technological process, the base frequency of the senior representative of the family, Core i7-5775C, was set at only 3.3 GHz, and the frequency in turbo mode did not exceed 3.7 GHz, which turned out to be worse than the characteristics of Devil’s Canyon by as much as 700 MHz.

A similar story happened with overclocking. The maximum frequencies to which it was possible to heat up Broadwell desktops without using advanced cooling methods were in the region of 4.1-4.2 GHz. Therefore, it is not surprising that consumers were skeptical about the Broadwell release, and processors of this family remained a strange niche solution for those who were interested in a powerful integrated graphics core. The first full-fledged 14-nm chip for desktop computers, which was able to attract the attention of wide layers of users, was only the next project of the microprocessor giant - Skylake.

Skylake, like the previous generation processors, was produced using a 14 nm process technology. However, here Intel has already been able to achieve normal clock speeds and overclocking: the older desktop version of Skylake, Core i7-6700K, received a nominal frequency of 4.0 GHz and auto-overclocking in turbo mode to 4.2 GHz. These are slightly lower values ​​when compared to Devil's Canyon, but the newer processors were definitely faster than their predecessors. The fact is that Skylake is “so” in Intel nomenclature, which means significant changes in the microarchitecture.

And they really are. At first glance, not many improvements were made in the Skylake design, but all of them were targeted and made it possible to eliminate existing weak points in the microarchitecture. In short, Skylake received larger internal buffers for deeper out-of-order execution of instructions and higher cache memory bandwidth. Improvements affected the branch prediction unit and the input part of the execution pipeline. The execution rate of division instructions was also increased, and the execution mechanisms for addition, multiplication and FMA instructions were rebalanced. To top it off, the developers have worked to improve the efficiency of Hyper-Threading technology. In total, this allowed us to achieve approximately a 10% improvement in performance per clock compared to previous generations of processors.

In general, Skylake can be characterized as a fairly deep optimization of the original Core architecture, in such a way that there are no leftovers in the processor design bottlenecks. On the one hand, by increasing the decoder power (from 4 to 5 microoperations per clock) and the speed of the microoperations cache (from 4 to 6 microoperations per clock), the rate of instruction decoding has significantly increased. On the other hand, the efficiency of processing the resulting micro-operations has increased, which was facilitated by the deepening of out-of-order execution algorithms and the redistribution of the capabilities of execution ports, along with a serious revision of the execution rate of a number of regular, SSE and AVX commands.

For example, Haswell and Broadwell each had two ports for performing multiplications and FMA operations on real numbers, but only one port for additions, which did not correspond well to real program code. In Skylake, this imbalance was eliminated and additions began to be performed on two ports. In addition, the number of ports capable of working with integer vector instructions has increased from two to three. Ultimately, all this led to the fact that for almost any type of operation in Skylake there are always several alternative ports. This means that in the microarchitecture almost all possible reasons conveyor downtime.

Noticeable changes also affected the caching subsystem: the bandwidth of the second and third level cache memory was increased. In addition, the associativity of the second level cache was reduced, which ultimately made it possible to improve its efficiency and reduce the penalty when processing misses.

Significant changes have also occurred at a higher level. Thus, in Skylake, the throughput of the ring bus, which connects all processor units, has doubled. In addition, the CPU of this generation has a new memory controller, which is compatible with DDR4 SDRAM. And in addition to this, to connect the processor to the chipset, it began to use new tire DMI 3.0 with doubled bandwidth, which made it possible to implement high-speed PCI Express 3.0 lines, including through the chipset.

However, like all previous versions of the Core architecture, Skylake was another variation on the original design. This means that in the sixth generation of the Core microarchitecture, Intel developers continued to adhere to the tactics of gradually introducing improvements at each development cycle. Overall this is not a very impressive approach and does not allow you to see any significant changes in performance immediately - when comparing CPUs from neighboring generations. But when upgrading old systems, it’s not difficult to notice a noticeable increase in productivity. For example, Intel itself willingly compared Skylake with Ivy Bridge, demonstrating that processor performance has increased by more than 30 percent in three years.

And in fact, this was quite serious progress, because then everything became much worse. After Skylake, any improvement in the specific performance of processor cores stopped completely. Those processors that are currently on the market still continue to use the Skylake microarchitectural design, despite the fact that almost three years have passed since its introduction in desktop processors. The unexpected downtime occurred because Intel was unable to cope with the implementation of the next version of the semiconductor process with 10nm standards. As a result, the whole “tick-tock” principle fell apart, forcing the microprocessor giant to somehow get out and engage in repeated re-release of old products under new names.

Processors generation KabyLake, which appeared on the market at the very beginning of 2017, became the first and very striking example of Intel’s attempts to sell the same Skylake to customers for the second time. The close family ties between the two generations of processors were not particularly hidden. Intel honestly said that Kaby Lake is no longer a “tick” or “so”, but a simple optimization of the previous design. At the same time, the word “optimization” meant certain improvements in the structure of 14-nm transistors, which opened up the possibility of increasing clock frequencies without changing the thermal envelope. A special term “14+ nm” was even coined for the modified technical process. Thanks to this production technology, the senior mainstream desktop processor Kaby Lake, called Core i7-7700K, was able to offer users a nominal frequency of 4.2 GHz and a turbo frequency of 4.5 GHz.

Thus, the increase in Kaby Lake frequencies compared to the original Skylake was approximately 5 percent, and that was all, which, frankly, cast doubt on the legitimacy of classifying Kaby Lake as the next generation Core. Until this point, each subsequent generation of processors, no matter whether it belonged to the “tick” or “tock” phase, provided at least some increase in the IPC indicator. Meanwhile, in Kaby Lake there were no microarchitectural improvements at all, so it would be more logical to consider these processors simply as the second Skylake stepping.

However a new version The 14-nm process technology was still able to show itself in some positive ways: the overclocking potential of Kaby Lake compared to Skylake increased by about 200-300 MHz, thanks to which the processors of this series were quite warmly received by enthusiasts. True, Intel continued to use thermal paste under the processor cover instead of solder, so scalping was necessary to fully overclock Kaby Lake.

Intel also failed to cope with the commissioning of 10-nm technology by the beginning of this year. Therefore, at the end of last year, another type of processors built on the same Skylake microarchitecture was introduced to the market - CoffeeLake. But talking about Coffee Lake as the third guise of Skylake is not entirely correct. Last year was a period of radical paradigm shift in the processor market. AMD returned to the “big game”, which was able to break established traditions and create demand for mass processors with more than four cores. Suddenly, Intel found itself playing catch-up, and the release of Coffee Lake was not so much an attempt to fill the pause until the long-awaited appearance of 10nm Core processors, but rather a reaction to the release of six- and eight-core AMD processors Ryzen.

As a result, Coffee Lake processors received an important structural difference from their predecessors: the number of cores in them was increased to six, which Intel platform happened for the first time. However, no changes were reintroduced at the microarchitecture level: Coffee Lake is essentially a six-core Skylake, assembled on the basis of exactly the same internal design of computing cores, which are equipped with an L3 cache increased to 12 MB (according to the standard principle of 2 MB per core ) and are united by the usual ring bus.

However, despite the fact that we so easily allow ourselves to say “nothing new” about Coffee Lake, it is not entirely fair to say about the complete absence of any changes. Although nothing has changed in the microarchitecture, Intel specialists had to spend a lot of effort to ensure that six-core processors could fit into a standard desktop platform. And the result was quite convincing: the six-core processors remained true to the usual thermal package and, moreover, did not slow down at all in terms of clock frequencies.

In particular, the senior representative of the Coffee Lake generation, Core i7-8700K, received a base frequency of 3.7 GHz, and in turbo mode it can accelerate to 4.7 GHz. At the same time, the overclocking potential of Coffee Lake, despite its more massive semiconductor crystal, turned out to be even better than that of all its predecessors. Core i7-8700K are often taken by their ordinary owners to reach the five-gigahertz mark, and such overclocking can be real even without scalping and replacing the internal thermal interface. And this means that Coffee Lake, although extensive, is a significant step forward.

All this became possible solely thanks to another improvement in the 14nm process technology. In the fourth year of using it for mass production of desktop chips, Intel was able to achieve truly impressive results. The introduced third version of the 14-nm standard (“14++ nm” in the manufacturer’s designations) and the re-arrangement of the semiconductor crystal made it possible to significantly improve performance per watt spent and increase the total computing power. With the introduction of six-cores, Intel was perhaps able to take an even more significant step forward than any of the previous microarchitecture improvements. And today Coffee Lake looks like a very tempting option for upgrading older systems based on previous Core microarchitecture media.

Codename	Technical process	Number of cores	GPU	L3 cache, MB	Number of transistors, billion	Crystal area, mm 2
Sandy Bridge	32 nm	4	GT2	8	1,16	216
Ivy Bridge	22 nm	4	GT2	8	1,2	160
Haswell	22 nm	4	GT2	8	1,4	177
Broadwell	14 nm	4	GT3e	6	N/A	~145 + 77 (eDRAM)
Skylake	14 nm	4	GT2	8	N/A	122
Kaby Lake	14+ nm	4	GT2	8	N/A	126
Coffee Lake	14++ nm	6	GT2	12	N/A	150

⇡ Processors and platforms: specifications

To compare the seven latest generations of Core i7, we took the older representatives in the respective series - one from each design. The main characteristics of these processors are shown in the following table.

	Core i7-2700K	Core i7-3770K	Core i7-4790K	Core i7-5775C	Core i7-6700K	Core i7-7700K	Core i7-8700K
Codename	Sandy Bridge	Ivy Bridge	Haswell (Devil's Canyon)	Broadwell	Skylake	Kaby Lake	Coffee Lake
Production technology, nm	32	22	22	14	14	14+	14++
release date	23.10.2011	29.04.2012	2.06.2014	2.06.2015	5.08.2015	3.01.2017	5.10.2017
Cores/threads	4/8	4/8	4/8	4/8	4/8	4/8	6/12
Base frequency, GHz	3,5	3,5	4,0	3,3	4,0	4,2	3,7
Turbo Boost frequency, GHz	3,9	3,9	4,4	3,7	4,2	4,5	4,7
L3 cache, MB	8	8	8	6 (+128 MB eDRAM)	8	8	12
Memory support	DDR3-1333	DDR3-1600	DDR3-1600	DDR3L-1600	DDR4-2133	DDR4-2400	DDR4-2666
Instruction Set Extensions	AVX	AVX	AVX2	AVX2	AVX2	AVX2	AVX2
Integrated Graphics	HD 3000 (12 EU)	HD 4000 (16 EU)	HD 4600 (20 EU)	Iris Pro 6200 (48 EU)	HD 530 (24 EU)	HD 630 (24 EU)	UHD 630 (24 EU)
Max. graphics core frequency, GHz	1,35	1,15	1,25	1,15	1,15	1,15	1,2
PCI Express version	2.0	3.0	3.0	3.0	3.0	3.0	3.0
PCI Express lanes	16	16	16	16	16	16	16
TDP, W	95	77	88	65	91	91	95
Socket	LGA1155	LGA1155	LGA1150	LGA1150	LGA1151	LGA1151	LGA1151v2
Official price	$332	$332	$339	$366	$339	$339	$359

It is curious that in the seven years since the release of Sandy Bridge, Intel has not been able to significantly increase clock speeds. Despite the fact that the technological manufacturing process and the microarchitecture was seriously optimized twice, today's Core i7 has made almost no progress in its operating frequency. The latest Core i7-8700K has a nominal frequency of 3.7 GHz, which is only 6 percent higher than the frequency released in 2011 Year Core i7-2700K.

However, such a comparison is not entirely correct, because Coffee Lake has one and a half times more computing cores. If we focus on the quad-core Core i7-7700K, then the increase in frequency still looks more convincing: this processor has accelerated relative to the 32-nm Core i7-2700K by a fairly significant 20 percent in megahertz terms. Although this can still hardly be called an impressive increase: in absolute terms, this is converted into an increase of 100 MHz per year.

There are no breakthroughs in other formal characteristics. Intel continues to provide all its processors with an individual L2 cache of 256 KB per core, as well as a common L3 cache for all cores, the size of which is determined at the rate of 2 MB per core. In other words, the main factor in which the greatest progress has occurred is the number of computing cores. The development of Core began with four-core CPUs and came to six-core ones. Moreover, it is obvious that this is not the end and in the near future we will see eight-core variants of Coffee Lake (or Whiskey Lake).

However, as is easy to see, for seven years Intel has hardly changed and price policy. Even the six-core Coffee Lake has risen in price by only six percent compared to previous quad-core flagships. However, other older processors of the Core i7 class for the mass platform have always cost consumers about $330-340.

It is curious that the biggest changes have occurred not even with the processors themselves, but with their support random access memory. Bandwidth Dual-channel SDRAM has doubled since the release of Sandy Bridge until today: from 21.3 to 41.6 GB/s. And this is another important circumstance that determines the advantage of modern systems compatible with high-speed DDR4 memory.

And in general, all these years, along with the processors, the rest of the platform has evolved. If we talk about the main milestones in the development of the platform, then, in addition to the increase in the speed of compatible memory, I would also like to note the appearance of support GUI PCI Express 3.0. It seems that speed memory and a fast graphics bus, along with progress in processor frequencies and architectures, are significant reasons why modern systems became better and faster than the previous ones. Support for DDR4 SDRAM appeared in Skylake, and the transfer of the PCI Express processor bus to the third version of the protocol occurred in Ivy Bridge.

In addition, the system logic sets accompanying processors have received noticeable development. Indeed, today's Intel chipsets of the three hundredth series can offer much more interesting capabilities in comparison with the Intel Z68 and Z77, which were used in LGA1155 motherboards for Sandy Bridge generation processors. This is easy to see from the following table, in which we have summarized the characteristics of Intel's flagship chipsets for the mass platform.

	P67/Z68	Z77	Z87	Z97	Z170	Z270	Z370
CPU compatibility	Sandy Bridge Ivy Bridge		Haswell	Haswell Broadwell	Skylake Kaby Lake		Coffee Lake
Interface	DMI 2.0 (2 GB/s)				DMI 3.0 (3.93 GB/s)
PCI Express standard	2.0				3.0
PCI Express lanes	8				20	24
PCIe M.2 support	No			Eat	Yes, up to 3 devices
PCI support	Eat	No
SATA 6 Gb/s	2		6
SATA 3 Gb/s	4		0
USB 3.1 Gen2	0
USB 3.0	0	4	6		10
USB 2.0	14	10	8		4

Modern logic sets have significantly improved the ability to connect high-speed storage media. The most important thing: thanks to the transition of chipsets to PCI bus Express 3.0 today in high-performance builds you can use high-speed NVMe drives, which, even compared to SATA SSDs, can offer noticeably better responsiveness and higher read and write speeds. And this alone can become a compelling argument in favor of modernization.

In addition, modern system logic sets provide much richer possibilities for connecting additional devices. And we’re not just talking about a significant increase in the number of PCI Express lanes, which ensures the presence of several additional PCIe slots on boards, replacing conventional PCI. Along the way, today's chipsets also have innate support for USB 3.0 ports, and many modern motherboards are equipped with USB ports 3.1 Gen2.