AMD or Intel. Which processor is better? Reducing the area occupied by the transistor
Read also
Introduction
If you don't have the time to run your own benchmarks, or if you don't feel confident enough that you can choose the right processor for your next gaming machine, don't hesitate. We'll make it easy for you by providing a simple list of the best gaming CPUs on the market.
January updates
During the last month of 2011, there were no revolutionary breakthroughs in the field of CPU, although AMD updated the Llano-based APU family with two new models with unlocked multipliers (including the graphics part). The A8-3870K and A6-3670K are also interesting in that they use the Intel K-series suffix rather than the familiar Black Edition label. E. Trust us, these APUs don't even come close in performance to the $600 Corei7-3930K.
Despite the shameless imitation of the name, these APUs may be of interest to buyers with a small budget and not interested in discrete graphics cards. The A8-3870K is a quad-core model with a TDP of 100W and 400 ALUs, the frequency of the main cores is 4 GHz, and the graphics 600 MHz. The A6-3670K has 320 shaders running at 444 MHz, complemented by a 2.7 GHz processor. We spotted the APUA8-3870K for sale on Newegg for $145, but the A6-3670K has yet to show up. The company says that the recommended retail price of the junior model will be $115. None of these APUs can be recommended as a serious gaming processor, as there are stronger competitors in this area. As a result, they are not included in this month's list.
We don't have anything particularly new from Intel either. Although the company recently announced a new generation of Atom processors called CedarTrail with 32nm process technology, which should start in the first half of 2012. The press release noted two models: the N2600 will be released with a core frequency of 1.6 to 1.86 GHz and a TDP below 3.5 W, and the N2800 is expected with a frequency of 1.86 to 2.13 GHz and a TDP of less than 6.5 W. The N2650 at 1.7 GHz and N2850 at 2.0 GHz were not mentioned, although they are already included in the company's data sheet. In any case, gamers in general don't pay attention to the Atom brand.
The retail price of the Core i3-2120 3.3 GHz has dropped to $120, making it a couple of dollars cheaper than the Core i3-2100 3.1 GHz, earning it a place on the recommended buy list. This change came as a surprise to us, as the Core i3-2100, which beat the Phenom II X4 955, was our favorite for this spot at $125. The processor from AMD remains viable, especially when you consider the unlocked multiplier. However, the speed of the Core i3 demonstrates how serious Intel is in the budget arena.
In addition to these changes, the more notable news was not presentations, but exits. The Phenom II X4 840 recently disappeared from the market, leaving the Athlon II X4 640 (which is 200 MHz slower) to represent AMD in the $100 price segment. therefore, it is removed from the list of recommendations for upgrading an LGA 1156 based processor.
A few notes on our recommendations
This list is for players who want the best value for their money. If you don't play games, then the CPUs on this list may not be suitable for your needs.
The criteria by which the list was compiled are as follows: price / performance. We recognize that there are other factors that affect a CPU, such as platform price or CPU overclocking potential, but we're not going to complicate things by adding motherboard costs to the list. For now, our recommendations are based on base clock speeds, performance, and pricing.
The cost changes daily. In this article, we can't offer you the most up-to-date and accurate pricing information, but we can list a few good chips that you might not regret spending your money on.
The list is based on the most best prices in online stores. Prices in other countries or retail stores are likely to vary. Of course, we presented you retail prices to new CPUs. Used CPUs or OEM products (Vendor/Original Equipment Manufacturer, OEM) available at retail were not included in the table.
The best gaming CPUs under $100
Best gaming CPUs under $80: Athlon II X3 455
| Specifications Athlon II X3 455 | |
| code name | Rana |
| Process technology | 45 nm |
| Number of CPU cores | 3 |
| Clock frequency | 3.3 GHz |
| socket | AM2+/AM3 |
| L1 cache | 3 x 128 kb |
| L2 cache | 3 x 512 KB |
| HyperTransport | 4000 MT/s |
| Thermal package, W | 95 |
The Athlon II X3 455 is the second fastest processor in the Athlon II X3 series and boasts a well-balanced combination of three execution cores, high clock speeds, low cost and plenty of overclocking potential. While a value for money purchase, this processor suffers from some performance issues in games, which contributed to placing this model at the beginning of our recommender ladder.
AMD's quad-core Athlon II 640 or Phenom II X4 925 outperform the X3 latest products better optimized for multi-threading, but the Athlon II X3 455, with its 300 MHz clock advantage, can somewhat balance this disadvantage. At a price point $20 cheaper, the Athlon II X3 455 CPU remains an excellent low-budget option.
Best gaming CPUs under $100: 1st option - Athlon II X4 640
| Specifications Athlon II X4 640 | |
| code name | Propus |
| Process technology | 45 nm |
| Number of CPU cores | 4 |
| Clock frequency | 3.0 GHz |
| socket | AM3 |
| L1 cache | 4 x 128 kb |
| L2 cache | 4 x 512 KB |
| HyperTransport | 4000 MT/s |
| Thermal package, W | 95 |
Since the Phenom II X4 840 3.2 GHz is no longer being produced, AMD Athlon II X4 640 3.0 GHz takes its place as the best $100 option. Although its frequency is 200 MHz lower than its predecessor, this model is the best quad-core solution in this price range.
Best gaming CPUs under $100: 2nd option - Pentium G860
| Specifications Pentium G860 | |
| code name | Sandy Bridge |
| Process technology | 32 nm |
| Number of CPU cores | 2 |
| Clock frequency | 3.0 GHz |
| socket | LGA 1155 |
| L2 cache | 2 x 256 kb |
| L3 cache | 3 MB |
| thermal package | 65 W |
Pentium G860 on new Intel architecture It is in no way inferior to the quad-core Phenom II X4 840, although it has only two cores and does not even support Hyper-Threading. All these "shortcomings" are compensated by a more modern architecture and high energy efficiency (Pentium consumes only 65 W, while its competitor Phenom II X4 consumes 95 W).
Since these two processors, which have a similar cost, are so different from each other in terms of architecture, it is rather difficult to compare them. When it comes to production applications, the leader in this pair depends on whether the specific application for multithreaded calculations or not. On average, both CPUs provide close performance in games.
Best gaming CPUs priced: $100-$200
Best gaming CPUs under $120: Core i3-2120
| Specifications Core i3-2120 | |
| code name | Sandy Bridge |
| Process technology | 32 nm |
| Number of CPU cores/threads | 2/4 |
| Clock frequency | 3.3 GHz |
| socket | LGA 1155 |
| L2 cache | 2 x 256 kb |
| L3 cache | 3 MB |
| thermal package | 65 W |
The budget Core i3-2100 CPU is a surprisingly powerful device in the gaming arena, capable of beating the powerful quad-core CPUs that have traditionally dominated this price segment. With that in mind, the newer and faster $120 Core i3-2120 is a great starting point for those who want decent gaming performance now, with the option to upgrade to Ivy Bridge-based models in 2012.
Yes, you will essentially have to forget about overclocking potential, given the (in our opinion) unfavorable for enthusiasts locked multiplier and BCLK (base clock) with very little potential for overclocking above 100 MHz. But the underlying performance is impressive, so this CPU still deserves a recommendation.
More information about the architecture can be found in the overview "SandyBridge: Second Generation IntelCore" .
Honorable Mention: Phenom II X4 955 Black Edition
| Specifications Phenom II X4 955 Black Edition | |
| code name | Deneb |
| Process technology | 45 nm |
| Number of CPU cores | 4 |
| Clock frequency | 3.2 GHz |
| socket | AM3 |
| L1 cache | 4 x 128 KB |
| L2 cache | 4 x 512 KB |
| L3 cache | 6 MB |
| Hyper Transport | 4000MT/s |
| thermal package | 125 W |
The former flagship product of the AMD Phenom II X4 family, the Phenom II X4 955 offers the best value in AMD's high performance CPU lineup. This is four nuclear processor with large 6MB L3 cache and unlocked multiplier. In our experience, most Phenom II X4 955 processors can run as fast as Phenom II X4 975 by simply changing the BIOS clock multiplier from 16x to 18x. For gaming, it's an easy way to put this $120 CPU on par with the Core i5-760 model, which sells for around $210.
The real challenge for the Phenom II X4 955 BE CPU is the Intel Core i3-2100 based on the Sandy Bridge architecture. Intel's new low-end processor can easily outperform the Phenom II X4. But AMD's CPU deserves an honorable mention as a good option, entertainment oriented, more suitable for multitasking thanks to its quad-core architecture.
Best gaming CPUs under $190: Core i5-2400
| Specifications Core i5-2400 | |
| code name | Sandy Bridge |
| Process technology | 32 nm |
| Number of CPU cores | 4 |
| Clock frequency | 3.1 GHz (3.4) GHz |
| socket | LGA 1155 |
| L2 cache | 2 x 256 KB |
| L3 cache | 6 MB |
| thermal package | 95 W |
Intel's Sandy Bridge microarchitecture is, without a doubt, very productive. Benchmark data suggests that the new Core i5-2400 can compare with the Core i7-900 series processors in terms of gaming performance. We don't mean entry-level models. This affordable processor can easily compete with thousand-dollar Intel Extreme Edition chips when it comes to the number of frames per second in games.
As cool as the Core i5-700 series chips, the new Core i5-2xxx processors keep pace with their brethren in terms of performance. In addition, the LGA 1156 interface, one might say, has outlived its usefulness, and therefore it seems foolish to spend money on it, taking into account all of the above.
.
The best gaming CPUs for $200 and up
Best gaming CPUs under $220: Core i5-2500K
| Specifications Core i5-2500K | |
| code name | Sandy Bridge |
| Process technology | 32 nm |
| Number of CPU cores | 4 |
| Clock frequency | 3.3 GHz (3.7) GHz |
| socket | LGA 1155 |
| L2 cache | 4 x 256 KB |
| L3 cache | 6 MB |
| thermal package | 95 W |
In terms of pure performance, the Core i5-2500K offers very little beyond what the cheaper Core i5-2400 has in its arsenal. However, this CPU has three differences: it overclocks a few hundred MHz higher, comes with Intel HD 3000 graphics, and has an unlocked CPU multiplier.
The 200 MHz advantage (300 MHz with Turbo Boost) becomes almost irrelevant when compared to the Core i5-2400 model, and fans of games who have a discrete graphics card do not worry much about the integrated graphics core. But for overclockers using a Sandy Bridge-based CPU, an unlocked CPU multiplier is a must. CPU Core i5-2500K – obvious choice for gamers looking for the best combination of overclocking potential and gaming performance.
Our review of the new Sandy Bridge based CPUs can be found in the article "Sandy Bridge: Intel Core 2nd Generation" .
Reasonable level passed
Beyond the $220 threshold, prices will skyrocket, but the performance gains in games will be less and less. Therefore, we are unlikely to recommend a processor more expensive than the i5-2500K. Especially since the i5-2500K can be overclocked if higher performance is required, while still easily reaching (and surpassing) the stock clock speeds of the $1,000 i7-990X Extreme Edition.
But now, with the advent of the LGA 2011 interface, there are also several arguments to make it an unrivaled gaming platform. LGA 2011-based processors have more available cache and two more cores than leading LGA 1155 socket models. Plus, the quad-channel controller provides more memory bandwidth. With 40 Gen 3 PCIe lanes available on Sandy Bridge-E processors, the platform natively supports two x16 slots and one x8 slot, or one x16 slot and three x8 slots, removing potential bottlenecks in CrossFire or SLI configurations for three and four video cards.
While all of the above sounds impressive, it doesn't necessarily translate into significant performance gains in today's games. Our benchmarks show very little difference between the $225 LGA 1155 Core i5-2500K and the $1000 LGA 2011 Core i7-3960X, even when three graphics cards are installed in SLI. It turns out that memory bandwidth and PCIe do not greatly affect performance. current systems on the Sandy Bridge architecture.
The real potential of the Sandy Bridge-E comes to the fore in CPU-heavy games like World of Warcraft or multiplayer in Battlefield 3. If you're using three or four graphics cards, it's possible that you already have enough performance. An overclocked Core i7-3960X or 3930K can help the rest of the platform catch up with an extremely powerful video system.
In general, while we do not recommend buying a processor over $220 in terms of price/performance, there are always users who do not mind spending extra money and who want to get the highest possible performance. If you're willing to spend a few hundred dollars on graphics cards and are concerned about a potential platform performance bottleneck, then we recommend looking at the following CPUs.
Best gaming CPU starting at $600: Core i7-3930K
| Specifications Core i7-3930K | |
| code name | Sandy Bridge-E |
| Process technology | 32 nm |
| Number of CPU cores | 6/12 |
| Clock frequency | 3.2 GHz (3.8) GHz |
| socket | LGA 2011 |
| L2 cache | 6 x 256 KB |
| L3 cache | 12 MB |
| thermal package | 130 W |
Take the $1,000 Core i7-3960X, strip away 3MB of shared L3 cache, and drop the base clock by 100MHz, and you've got an Intel Core i7-3930K that costs $400 less.
The 100 MHz base frequency difference is not significant, since both processors use unlocked multipliers for more comfortable overclocking. What's more, it's hard to find a situation where additional cache alone helps to increase performance. The money saved on the second-fastest Core i7 processor can be spent on a high-performance motherboard and cooler, despite the fact that the four-channel memory controller is not going anywhere, like 40 PCI Express 3.0 lanes.
Detailed information about the new Sandy Bridge-E architecture can be found in the article "Intel Core i7-3960X: Sandy Bridge-E and X79" .
Comparison table of gaming CPUs
What about other processors that are not on our list of recommendations? Are they worth buying or not?
Questions like these are expected as stock frequency levels and prices change daily. How to find out if the processor you have your eye on will be best buy in this price range?
We decided to help you in this difficult task by presenting a CPU hierarchy table, where processors of the same gaming performance level are on the same line. The top lines show the most productive gaming CPUs, and as you move down the lines, performance decreases.
We would like to warn you right away: the hierarchy is based on the average performance that each CPU demonstrates in four games, namely: Crysis, Unreal Tournament 3, World in Conflict and Supreme Commander. This sample is acceptable for typical game scenarios, but we should not forget that each game behaves differently. Some games, for example, are severely limited by the graphics subsystem, others respond positively to more CPU cores, more cache, or even a specific architecture. We cannot test every processor on the market, so we calculated the performance of some CPUs based on the performance of models with a similar architecture. In any case, this hierarchy should only be considered as a generalized assessment; we do not claim to be an absolutely accurate comparison list of CPU performance.
You can use the table to compare the prices of the two processors to see which one is the best value for your money, as well as to gauge the value of an upgrade. We do not recommend upgrading if new processor costs less than three or four lines from the current one. Otherwise, you may not notice a performance boost in games.
| Table of comparative CPU performance in games | |
| Intel | AMD |
| Core i7-2600, -2600K, -2700K, -3820, -3930K, -3960X Core i7-965, -975 Extreme, -980X Extreme, -990X Extreme Core i7-980, -970, -960 Core i5-2500, -2500K, -2310, -2300 |
|
| Core i7-860, -870, -875K, -920, -930, -940, -950 Core i5-750, -760, -2405S, -2400S Core 2 Extreme QX9775, QX9770, QX9650 Core 2 Quad Q9650 Core i3-2100, -2105, -2120, -2125, -2130 |
FX-8150 Phenom II X4 Black Edition 980, 975 |
| Core 2 Extreme QX6850, QX6800 Core 2 Quad Q9550, Q9450, Q9400 Core i5-650, -655K, -660, -661, -670, -680 Core i3-2100T, -2120T |
Phenom II X6 1100T BE, 1090T BE, 1075T Phenom II X4 Black Edition 970, 965, 955 |
| Core 2 Extreme QX6700 Core 2 Quad Q6700, Q9300, Q8400, Q6600, Q8300 Core 2 Duo E8600, E8500, E8400, E7600 Core i3 -530, -540, -550 Pentium G860, G850, G840, G630 |
Phenom II X6 1055T Phenom II X4 945, 940, 920, 910, 910e, 810 Phenom II X3 Black Edition 720, 740 A8-3850 A6-3650 Athlon II X4 645, 640, 635, 630 Athlon II X3 460, 455, 450, 445, 440, 435 |
| Core 2 Extreme X6800 Core 2 Quad Q8200 Core 2 Duo E8300, E8200, E8190, E7500, E7400, E6850, E6750 Pentium G620 Celeron G540, G530 |
Phenom II X4 905e, 805 Phenom II X3 710, 705e Phenom II X2 565BE, 560BE, 555BE, 550BE, 545 Phenom X4 9950 Athlon II X4 620, 631 Athlon II X3 425 |
| Core 2 Duo E7200, E6550, E7300, E6540, E6700 Pentium Dual-Core E5700, E5800, E6300, E6500, E6600, E6700 Pentium G9650 |
Phenom X4 9850, 9750, 9650, 9600 Phenom X3 8850, 8750 Athlon II X2 265, 260, 255 Athlon 64 X2 6400+ |
| Core 2 Duo E4700, E4600, E6600, E4500, E6420 Pentium Dual-Core E5400, E5300, E5200, G620T |
Phenom X4 9500, 9550, 9450e, 9350e Phenom X3 8650, 8600, 8550, 8450e, 8450, 8400, 8250e A4-3400 Athlon II X2 240, 245, 250 Athlon X2 7850, 7750 Athlon 64 X2 6000+, 5600+ |
| Core 2 Duo E4400, E4300, E6400, E6320 Celeron E3300 |
Phenom X4 9150e, 9100e Athlon X2 7550, 7450, 5050e, 4850e/b Athlon 64 X2 5400+, 5200+, 5000+, 4800+ |
| Core 2 Duo E5500, E6300 Pentium Dual Core E2220, E2200, E2210 Celeron E3200 |
Athlon X2 6550, 6500, 4450e/b, Athlon X2 4600+, 4400+, 4200+, BE-2400 |
| Pentium Dual Core E2180 Celeron E1600, G440 |
Athlon 64 X2 4000+, 3800+ Athlon X2 4050e, BE-2300 |
| Pentium Dual Core E2160, E2140 Celeron E1500, E1400, E1200 |
|
Conclusion
Remember that the situation in stores is constantly changing. Therefore, focus on current prices and change your strategy accordingly. In any case, good luck!
2012 for desktop processors, unlike the market tablet computers And mobile phones, was quite ordinary. There were no major changes, if you do not take the integration of the graphics core. The number of cores is in no hurry to grow, however, as well as the clock frequency of the processor. In past years, the pace of CPU development has been more noticeable. There is an opinion that all sorts of tablets, laptops and other gadgets will replace the inpatient, but, to be honest, I hardly believe it. At desktop computers computing power is much higher, and they can easily work 24/7. And game consoles cannot compare with the quality of PC games, and it is likely that desktop computers will supplant them. Yes, over the past year, desktop sales have fallen by about 10%, a rather big figure. But is it not because sales have fallen that it does not observe rapid evolution?
Partly, such a slow development of processors is connected, no, not with the fact that the 35-year-old x86 architecture is already outdated, it's just that both companies have put a lot of effort into other tasks.
As for AMD, they are primarily concerned with survival. The company has lost a lot of valuable personnel and now cannot compete with the main enemy - Intel Corporation - in the field of high-performance computing. AMD is forced to significantly reduce prices in order to somehow increase the level of sales. But in this way it is very difficult to cope with problems, so they decided to take those market niches where Intel does not dominate.
As for Intel, the situation is different. Its main competitor is significantly behind it, so they are in no hurry to strive to release new processors. But Intel may lose the title of microprocessor giant in other markets dominated by arm-architecture.
The main events in 2012 from the companies were Intel Ivy Bridge and AMD Piledriver.
Intel: Excursion of events of 2012
The production of conventional desktop processors is no longer a top priority. As evidence, we can cite the postponement of the official announcement of Ivy Bridge until a later time, and then problems with the supply. The new architecture was expected at the beginning of the year, and it came out in April, and normal sales began only by mid-summer. Intel had no problems, they were just in no hurry, and Sandy Bridge stocks could be sold at the same time. The new microarchitecture turned out to be just a meager update to Sandy Bridge: 22-nm process technology, hence reduced heat dissipation, new 3D transistors (Tri-Gate), insignificant increase in performance and clock speed.
Overclockers were also disappointed in this pebble, its overclocking potential was in no way superior to the previous generation of processors. How do you think the owners of Sandy Bridge reacted to the novelty? That's right - no way! And there is nothing to be surprised. But this does not automatically make this UG processor. It's just that it is more focused on laptops, ultrabooks and low-power computers. The integrated video core is powerful enough not to buy a discrete video adapter. It is powerful and Full HD to watch calmly and play new toys, however, not at high settings and without FSAA.
But the recently released Y-series mobile processors have a maximum TDP of 13W! And the average power consumption is only 7W. And this despite the fact that they have Hyper-Threading support, a powerful Intel HD Graphics core, a frequency of 2Ghz. The company hopes to smooth out problems with the new Atom (Clover Trail) with this series. Recently, Intel Atom is somehow losing ground, a kind of crisis. Also, Intel's Medfield platform for smartphones and server-side Atom (Centerton) didn't bring much success either, although it's in a better situation. Microservers and compacted servers find their salvation in this processor.
Well, it turns out that we have to discuss not cool productive processors, but novelties in the field of economical SoCs. There was nothing fresh in the field of powerful productive processors on the LGA2011 socket - all the same improved analogs of last year. Nothing remarkable has happened in the field of server computing, all announced processors are based on Sandy Bridge-EP. Last year, another new Intel Itanium was also announced, which is based on the IA-64 architecture. The new processor has more than doubled the performance, but the engineering team is slowly shrinking, so progress will be slower. Yes, and Intel itself is losing love for this architecture.
Advanced Micro Devices (AMD): Actions in 2012
If everything was more or less serene for Intel, then AMD entered this year far from calm. She needs to get out of the hole she's in. AMD processors were in demand mainly in the budget segment. Only Brazos platform processors were in demand. But from cheap processors and the profit is small.
AMD's most popular desktop processor is the flagship Bulldozer architecture processor. But neither 8 cores, nor a high clock speed, nor a Windows patch helped him. Almost everyone was disappointed with his performance. Hybrid processors of the Llano family have brightened up the gray days of the company a little, but their outdated K10 architecture does not allow them to compete with their counterparts from Intel.
AMD was suffering losses, something urgently needed to be done. The company restructured, there was a wave of layoffs, priorities changed, contracts with semiconductor manufacturers were revised. Thus, the company has identified for itself 3 main areas where it can expect success: server platforms, energy-efficient processors with low consumption, and embedded solutions.
But, perhaps, the most significant event of the last year was the announcement of second-generation hybrid processors - Trinity. They included up to 4 cores of the Piledriver architecture and GPU of the Radeon HD 7000 family. Compared to Llano, Trinity managed to raise the computing bar by 25%, and graphics performance increased by as much as 50%. As a result, 4-core APUs with thermal packages of 35, 25, 17 and 15 W appeared in the assortment of the company, which had pretty good specifications to change something in this market segment.
So, Trinity processors have become very successful for the mobile market. This APU is significantly superior to Intel HD Graphics, but the CPU performance, alas, is noticeably inferior to processors from Intel. But in the desktop market, APU data could only occupy a budget niche. And even then, many will prefer Intel, if the issue is not limited to saving money.
Desktop processors of the Vishera family (updated Piledriver) of the FX series include up to 8 cores, but this update was not the most successful. The performance of the FX has risen by literally 10-15 percent, and even then because of the clock speed alone. Flagship processor FX can only compete with the Core i5, and even then with a stretch, and its power consumption will be much higher.
And in the server market, the situation is favorable, due to the use of the Piledriver architecture, among the Opterons for the G34 platform with the design of Abu Dhabi, the number of x86 cores has increased to 16! And this is a unique offer for the server market. Soon AMD plans to integrate x64 into the Opteron - ARM cores.
It is noteworthy that 75% of the products sold by the company are energy-efficient low-cost hybrid solutions.
Well, the year turned out to be poor for high-performance solutions, there is a massive boom in the tablet market. The efforts of microprocessor giants are not aimed at desktop platforms, more precisely, they are directed, but no one seeks to quickly create something revolutionary in this area, preferring to slowly update and improve their products. We hope that 2013 will bring more good news, especially in the field of high-performance systems.
Back in 2002, I wrote about the expected problems of processor manufacturers when switching to thinner ones. processes. Some of them were solved completely unnoticed by the general computer community, some (for example, problems with gate leakage current) were widely covered in the press.
Movement to thin tech. processes is not only a way to search for new technical ideas, but also a way of financial costs and technological compromises, which in turn limit the success of processor manufacturers
History of processor development
This is a constant desire to improve its performance, and to do this, make the main cell (key) - a complementary pair of transistors as fast as possible or as smaller sizes. This was achieved by the use of increasingly fine technological processes.
Moreover, the performance of the cell is the higher the thinner those. process.
The development of processors can be divided into two stages.
The first one is around 2005.
At the first stage, the main goal of the designers was to make the size of the CMOS key as small as possible in order to obtain ever higher clock frequencies of the processor and, accordingly, increase its performance. And only then, due to the small size, increase the number of keys in order to obtain a more complex structure, the optimization of which also gives some performance gain.
And only then there was a decrease in the power consumed by the key and, accordingly, by the processor, and other advantages of thin technologies.
Moreover, the main increase in processor performance was provided precisely by the increase in clock frequencies.
The second one began in 2005, from the moment the processor clock speed stopped growing.
At the second stage, the race to reduce the size of the CMOS key continues. Its goal was to place as much as possible large quantity keys on a chip, in order to be able to complicate the structure of the processor (including an increase in the number of cores and the size of the cache "she"), which allows to increase performance. The second reason for the movement is a decrease in the power consumed by the key and, accordingly, the processor. The growth of clock frequencies has stopped.
It was in this way that the performance of server processors was increased earlier, when even thinner tech. the process did not provide an opportunity to increase productivity.
From that moment on, manufacturers switched to the so-called rating - the equivalent performance of the processor.
On the way to fine technological processes, many problems arose and were solved. Some of them were solved completely unnoticed by the general computer community, some (for example, problems with gate leakage current) were widely covered in the press. This path is not only the path of searching for new technical ideas, but also financial costs and, most importantly, the path of compromises that impose certain restrictions on the development of technology.
At the beginning of May there was information
about the Intel solution, literally - “launch a program to phase out their processors Core i7 940”, both retail models and OEM products.
The Intel-style formula, "run-on-withdraw" is a nasty action, looks pretty positive! Not at all like "out of production".
Note that since the release of the first chips of the Core family i7 has already passed almost half a year, and this is a rather short period for the processor industry ... and here is the solution!
The Core i7 940 was followed by the Core i7 965!
What does this mean?
Some people think that against the backdrop of the crisis, the principle of Intel's work does not work - "everyone will take what we offer, with an appropriate advertising company."
There is an opinion that this is an attempt to sell stocks of 4-series system logic sets, the demand for which has fallen due to the global economic crisis. But "realize by giving up" is a no-win formula. All the same, losses here or there.
Another opinion is that the cost of manufacturing Intel Core i7 940 turned out to be high and it does not have the demand that allows it to have cost-effective production.
Another opinion, against the background of the crisis at Intel exacerbated internal problems.
So far, one can only guess why the life of the Core i7 940 and Core The i7 965 turned out to be so short, but usually the reasons for the cessation of production should be quite weighty, because the money was spent, and the crisis is in the yard. Moreover, new Core i7 975 and 950 models are planned for release - not very different in performance.
But most likely this is the whole set of the above, which was superimposed on the problems of mastering more subtle technological processes.
Processor trends
Each step in the development of fine technological processes means a decrease in the linear dimensions of the transistor by about 1.4 times and its area by about 2 times.
Therefore, there are trends and facts:
|
The last two points significantly affect the economic feasibility of releasing new models for sale, and their price.
The most characteristic points in the history of the development of new technological processes are shown in Table 1.
| YEAR* | 1995 | 1997 | 1999 | 2001 | 2003 | 2005 | 2007 | 2009 | 2011 | 2012** | 2013** |
| micron technology | 0,35 | 0,25 | 0,18 | 0,13 | 0,09 | 0,065 | 0,045 | 0,045 | 0,032 | 0,022/0,024 | 0,01 |
| Channel length nm | - | 120 | 90 | 70 | 45 | 38 | 35 | 35 | 20 | 15 | 7-8 |
| Max. processor clock speed MHz /Model |
450/ Pentium Pro | 1000/ Pentium III | 2000/ Pentium 4 - 2.0 | 3400/ Pentium 4 - 3.4 | 3800/ Pentium 4-571 | 3800/Pentiu m 4-673 | 3160*
/ Penryn Quad-Core Xeon DP X5460 |
2660 (plan up to 3300) Nehalem |
<
2500 Forecast |
<
2200 Forecast |
<
2000 Forecast |
| Switching time τ (psec) |
5.5 ns | 250 | 125 | 65 | 23 | 14 | 10 | 10 | 5-7 | 3-5 | 1-3 |
| Max. frequency generated interference
f max GHz |
0, 2 | 4 | 8 | 15 | 43 | 83 | >9 0 | >90 | >130 | >200 | >500 |
| Number of contacts | 387 | 370 | 423 | 478 | 775 | 775 | 771, 940 AMD |
1 366 | 1366/ 1156 | >1400 | >1400 |
Table 1.
*Intel considers the year of development of those. process, the year of presentation to consumers of a chip sample made according to this tech. process. Previously, it took several weeks from the introduction of a processor chip to its release for sale. Starting from 45 nm tech. The process, after the presentation of the memory chip (the technology is now being developed on them), takes up to six months before the presentation of the first processor, and the deployment of mass production (many models) takes up to six months. Therefore, here is the date of serial production of the first model of processors for this tech. process. Therefore, this line may have values different from those accepted by Intel.
** in Intel plans for 2009.
According to Intel Corporation officials, in 2012, microchip manufacturers will switch to a 10-nm process technology. Vice President of Intel Digital Enterprise Group (Intel division responsible for the design and manufacture of discrete chips) Pat Gelsinger believes Intel factories will be able to make transistors as small as 10 nanometers or less.
Such a statement devoid of logic can only be considered as another publicity stunt, since such a range of technology changes previously required from 4 to 7 years. Since each step is associated with the introduction of new technologies, equipment and their debugging.
But in the history of not only Intel, but in general, there were no such abrupt transitions to new tech. processes. Therefore, realistically, in my opinion, we can expect the step taken by Intel. processes, which will give a series of 32, 22, 16, 11 nm.
Not even considering the unknown that awaits the developer.
See Table 1.
| YEAR* | 2009 | 2011 | > 2012 | >2014 | >2017 | |
| Constructive | ||||||
| Standard | Another | |||||
| Technology nm | 45 | 32 | 22 | 16 | 11 | 11 |
| Channel length nm | 35 | 24 | 17 | 12 | 8-9 | 8-9 |
| Switching time τ (psec) |
10 | 6-7 | 5-6 | 3-5 | 2-3 | 2-3 |
| Number of contacts | 1366 | 1500 | 2000 | 3000 | 4000 | - |
| Number of transistors up to a million | 731 | 1100 | 1600 | 2400 | 3600 | Up to 8000 |
| Max. interference frequency, f max GHz |
>90 | >130 | >150 | >200 | >250 | >250 |
Table 2.
1. With the transition to more subtle technologies,
the length of the channel of transistors that make up the discrete structures of the processor is shortened, and this, in turn, causes an increase in their speed.
Those skilled in the art are aware of dependencies that relate the length of a MOS transistor channel (process size) and its speed. Look at the graph describing this dependence in Fig.3.
Picture 1.
The concept of speed, up to 90 nm tech. process, was uniquely related to the clock frequency of the processor. The speed of the transistor grows - the clock frequency of the processor core also grows.
Now, the speed does not mean - the clock frequency of the core.
Restrictions.
In existing technologies for manufacturing system (motherboard) boards, switching times equal to the switching times of core transistors cannot be used for external buses.
Because, with the growth of performance, the requirements for the accuracy of the time of arrival (synchronism) of signals on parallel buses for information transmission and synchronization increase.
This is not a critical limitation, it can be bypassed by applying the transfer of information over serial channels.
2. The areas occupied by the transistor in the chip are reduced,
approximately two times for each step of reducing technological standards, as a result, its internal capacities should decrease .
But the use of a high-k dielectric for gate insulation of transistors made at 45 nm tech. process, reduces the gate capacitance slightly. This reduces the specific (by 1 key) power consumption less than before when switching from one tech. process to another.
Not taking this factor into account (or maybe just to test the technology on users - a structure designed for 22 nm process at 32 nm technical process), Intel released Intel Core i7 940 chips for sale with TDP equal to 130 W. And so, at the beginning of May, there was information about their removal from production (although their appearance on the 32 nm technical process is possible).
In fact, heat dissipation powers of more than 100 W require a special approach to the problem of cooling the processor and system block. The slightest inaccuracy in this matter leads to the appearance of temperature gradients on the chip, which does not contribute to its durability.
According to my data, the use of a high-k dielectric as an insulator led to the preservation of capacitance (100-70%) of the transistor when going from 65 to 45 nm. those. process.
As a result of an increase in the number of transistors, the power consumed by the processor and a slight decrease in the gate capacitance of the transistor increases. An example of this is the Intel Core i7 940.
3. Despite the increase in performance
the clock frequencies of the processor core stopped growing before reaching 4 GHz.
 Rice. 1 (my data). |
 Rice. 2 (data http://ru.wikibooks.org/wiki/ search word Processor) |
| On fig. 1 and 2 are graphs of the processor clock frequency. They are not synchronized along the horizontal axis, since Fig. 2 used from another source. And fig. 1 shows only the characteristic region. But its task is to show the change in the clock frequency over time or with a decrease in those standards. processes they perform quite clearly. |
|
I'm not talking here about:
- ability to overclock the processor, since the overclocked mode is your experiment - your risk, in which stable operation of the processor is not guaranteed.
- equivalent processor performance, which is determined not only by the core clock speed, but by a complex of processor characteristics.
Here in question only about the clock frequency of the core determined by the manufacturer.
Of course, one can dispute the drop in the core clock frequency by 45 nm tech. process, but already, no one disputes the lack of its growth. And a comparison of the increase in clock frequency during the transition from 250 nm to 180 nm tech. process, clearly not in favor of similar situations after 90 nm.
And the statements of some "craftsmen" about a high clock frequency are highly controversial. Since overclocking mine sample (as I said, not everyonesampleCPU can be overclocked Intel processor up to just over 4 GHz, they have not been able to translate their "know-how" into the category of a standard solution for a wide range of at least "craftsmen", and, as far as I understand, they themselves do not use record modes constantly.
Otherwise, by analogy with the headings "Processor XXXXXXX - exceeded 4.2 GHz!" the headlines "Processor XXXXXXX - 3 years at 4.2 GHz!"
It is believed that there is another reason for the limitation of the processor clock frequency - this is the limitation of the bus bandwidth for communication between PC devices.
4. Reducing the area occupied by the transistor
allows a larger number of transistors to be placed on a substrate of the same size, complicating the structure of the processor. This to some extent has a positive effect on the overall speed of calculations.
This is what processor developers use. The number of transistors on a chip is constantly growing.
Figure 2.
The increase in the number of transistors is due to the complexity of the processor structure and the placement on the processor chip of a larger number of cores, larger caches (which, by the way, tend to increase), memory controllers, .....
It should be noted that the heaviest for the chip, in terms of heat dissipation, are the cores that operate at high clock frequencies.
In order not to heat the chip, there is an idea, in multi-core processors, to use additional cores sharpened to perform some kind of narrow (specialized) tasks. This will allow you to turn them off when there are no tasks and thereby reduce the power consumed by the processor and heat dissipation.
On the other side - Increasing the total number of transistors in a chip - as an aspiration Intel fit into the Procrustean bed of Moore's Law.
This requires an increase in the number of nodes on a chip and, as a result, an increase in the number of transistors. But not doubling every year or two.
If the main thing is not optimal performance processor, and Moore with his law, there is an easy way to comply with this law, just increase the cache. After all, it is known that each bit of the cache requires 6 transistors to store a bit of information, and together with controllers - interfaces, strapping (practice shows) there are already more than 50 transistors per 1 bit of a level 3 cache. This is a significant contribution to the triumph of Moore's Law.
Although there is a refutation of Moore's Law, this is a processor:
Intel Atom Z515 - 1.20 GHz (512 KB L2, 400 MHz FSB, 1.4 W TDP) - introduced April 8, 2009, Silverthorne- 45 nm process technology and having a crystal of 47 mil. transistors. He positioned as a microprocessor for ultra-mobile systems / Netbook and Nettop class systems.
There is a drop in the number of transistors!
Another significant contribution to the increase in the number of transistors is the use of architectures with multiple cores.
But the number of nodes - cores and the size of the cache cannot be infinite, starting from a certain level, managing them will take so many resources that the increase in processor performance will stop.
Therefore, talk about the use of 100 and 1000 core processors in a PC is still premature.
The result of this is an increase in the number of external connections (lines) of the processor and an increase in the number of contacts of its connector - Socket "a.
5. The number of processor cores is growing
the number of which in forecasts is approaching a hundred. The increase in their number is caused by the desire to increase system performance.
It is clear that such an increase cannot continue indefinitely. After all, synchronization and control of parallel computing also requires computing resources. An end to multiplying the number of cores where their further increase does not give a performance increase.
But, we must not forget that an increase in the number of cores, as well as the size of caches, also requires resources.
Information flashed that Intel plans to sharpen individual cores of a multi-core processor for separate specialized tasks, which will increase their performance and turn them off if there are no tasks for them. The latter will reduce power consumption. For example, one of the cores can be sharpened to perform graphics operations.
But it seems that the extreme situation of such development is the chip where all the main processor nodes are located, leaving outside it only those nodes that do not have a significant impact on the speed of the PC.
It is clear that the development, improvement of processors is aimed at increasing the speed of its work and the speed of the system. To do this, its architecture is optimized, including the number of cores, the size of caches of all levels, memory controllers are transferred to the processor.
This requires an increase in the number of nodes on a chip and, as a result, an increase in the number of transistors.
6. Approximation of TDP to the limit value,
which in modern processor designs in conditions of optimized cases has a value of the order of 130 - 150 watts.
This limitation is imposed not by the presence of efficient coolers, but design features the processor itself, the size of the crystal, the inhomogeneity of heat release on its surface.
You probably noticed that lately processors with a TDP of about 130 W have sometimes appeared. Most often, these are processors designed for release on a thinner tech. process. For example processor Intel Corei7 940 architecture Nehalem made on 45 nm tech. process has a TDP of about 130 W, being made at 32 nm. TP it will have a TDP of 65 to 95 watts, depending on the clock speed.
Usually TDP does not exceed 100W.
130 W is the maximum power that can be drawn from semiconductor device with such dimensions of heat-conducting surfaces and a similar design.
But it imposes high requirements on the level of semiconductor device cooling technology.
These are connections of a crystal with a heat distribution plate on a processor with a thermal resistance of about 0.01 ° C / W, effective heat-conducting materials (pastes), coolers with a thermal resistance of less than 0.1 ° C / W, and cases with effective ventilation.
When TDP approaches 150 W, it threatens with local overheating on the chip, reducing its noise immunity, sensitivity to external cooling devices and, accordingly, overall reliability.
Restrictions imposed -
TDP limits the number of transistors on a chip and the processor clock speed.
7. Increase in the number of processor socket pins
(connector) - Socket" A.
3 factors influencing the increase in the number of contacts:
- The complexity of the processor structure,
- The increase in current consumption,
- Increasing the interference frequency.
1. The complication of the processor structure and the increase in its external connections creates a need to increase the number of contacts on the Socket "e of the processor. But the increase is not only in the number of external connections. The transmission goes through pairs of conductors, so the number of contacts increases by twice the number of external connections of the processor.
This is logical and understandable.
Figure 4
2. As we know, the number of contacts on the Socket "e, to supply power to the processor, exceeds 150 pairs. This requires large currents supplied to power the processor. Moreover, a decrease in the supply voltage requires an increase in the current supplied to the processor. This occurs even while maintaining the consumed power processor, because the value of the supply voltage is reduced (so far, up to 1 V).
And with a current limit of 0.5 A (0.5 A - limit) for one pair of contacts, you can estimate how many contacts are required for this. (The current safety factor requires approximately 0.3A per pin) But the number of contacts insocket" e allocated for these purposes is always more. The increase in the number of contacts determined by the maximum current, especially with a decrease in the supply voltage, is not a trend, but a technical necessity. (With a supply voltage of 1.1 V and a power consumption of 130 W, more than 230 pins are required for this.)
3. Parallel connection of power lines requires not only power supply, but also the removal of broadband interference generated by the processor during operation outside the chip and the Socket. This requires a low inductance of the power distribution lines, which is achieved in the applied Socket design parallel connection many contacts.
This is especially important at 0.45 nm or less TC, because the upper frequency limit of interference exceeds 50 GHz.
But with the transition to thinner tech. processes, the RF boundary of the generated interference increases and a decrease in the inductance of the power supply lines to the processor is required and, as a result, an increase in the number of Socket contacts.
Therefore - at the complexity of the processor structure, the increase in current consumption, and the need to remove the noise generated by it from the processor - all this requires an increase in the number of contacts by socket"e.
Increasing the number of contacts increases the size socket" and, accordingly, the inductance of the connections on it. At a certain size socket"
But this process is not unlimited.
Increasing the number of contacts increases the size socket" and, accordingly, the inductance of the connections on it. At a certain size socket" and an increase in the number of contacts does not give the necessary reduction in their inductance.
8. New solutions
Appear periodically in print. They mainly refer to new, faster transistors.
For example:
- The so-called vertical structure transistors,
- Double gate transistors.
- New semiconductor materials, ...... The list is constantly updated.
Of course, transistors of new structures with operating frequencies (cutoff frequency) of 20.50 GHz are an interesting thing, and not only from the point of view of application in digital (discrete) technology.
But don't forget:
The nature of the operation of transistors in the switching mode is the same, and all structures with high switching speeds always have concomitant negative phenomena that limit their capabilities.
Yes, and CMOS structures made at 45 nm. - have a switching time of the order of 10 ps and an operating frequency (cutoff frequency of the slope - characterizing its amplifying properties in the linear mode) of about 16 GHz. This means that the transistors modern processors made at 45 nm. those. process is theoretically capable of running at a processor speed of 16 GHz. But, those very negative phenomena do not allow this.
After some refinement of the design and structure of the processor, the operation of MOS structures is possible at frequencies approaching the cutoff frequency of the slope. So the processor is made at 45 nm. those. The process is capable of running at core clock speeds of 7-10 GHz.
The increase in the number of processor cores continues 2, 4, 8 and in the future 60, 80, 100. Although the latter is doubtful for widespread use.
I would like to say a few words about new semiconductor materials that have a significant impact on performance and operating temperature processor.
Now appeared new semiconductor materials, transistors made on which work for more high frequency, at higher temperatures.
| Material | Band gap, eV | Electron mobility, cm 2 / V * s | Breakdown field strength, MV/cm | Electron velocity, 10 7 cm/s | Thermal conductivity, W/cm*K | Working temperature, º С, max |
|---|---|---|---|---|---|---|
| Si | 1,1 | 1350 | 0,3 | 1 | 1,5 | 200 |
| GaAs | 1,4 | 8500 | 0,4 | 2 | 0,5 | 300 |
| GaN | 3,4 | 900 | 3,3 | 2,7 | 1,3 | 500 |
| AlN | 6,2 | 300 | 11,7 | 2,0 | 2,5 | 500 |
Table 3
According to [L.1]
FETs based GaN already on sale.
Intel conducts research on the possibility of using semiconductors III groups (which includes GaN).
There are several design options for high-performance processors.
Now there are new technologies on the horizon
What will they be?
It is difficult to guess, but obviously not purely optical, which is still at an early stage.
But optical technologies are already being explored by Intel and others.
So far, not optical processors, but only high-speed optical I/O interfaces for chip-to-chip interconnects.
According to Intel -
“Currently used 15-20 Gb/s copper-based interconnect technologies are marginal due to the inevitable signal degradation, power dissipation, and increased negative impact of electromagnetic interference at ultra-high clock frequencies.”
Figure 5
Intel is already working on optical data transmission systems [L.4].
And not only creates technologies that allow embedding optical data transmission systems into processor chips, but also already has prototypes of such transceivers.
Such transceivers ( electronic devices interfacing, used, in particular, to connect computers to a network) on CMOS transistors will be able to operate at clock frequencies of the order of 14 GHz, which is quite enough to provide a data transfer rate of 20 Gbit / s. [L.2]
And the latest models are capable of communicating at a speed of 40 Gb / s, and in the near future an 8-channel transceiver with throughput up to 1 Gbps.
And computer models with similar transceivers (optical communication channels) used instead of external processor buses are already being tested in Intel laboratories.
“The Moscow inventor, Alexander Verbovetsky, was able to change the microcircuit of this board in such a way that it was possible to increase performance, noise immunity, reliability and survivability personal computers using optoelectronic motherboards.
This result was achieved through the use of optical input / output and signaling methods, which can dramatically increase the data transfer rate, as well as through the use of a group bus architecture.
Additional processors, processor interface blocks, optical communication nodes of each block of the circuit with each other (processor with system bus, cache memory with system bus, system control unit with system bus, etc.) control unit.
Such a combination of blocks and connections between them made it possible to obtain a device with more than 100 times greater performance, noise immunity and reliability than conventional modern motherboards for personal computers." (end quote)
These two solutions are practical creation a single high-speed optical bus on which all its nodes can be planted providing internal and external Relations PC.
There are solutions
Which allow you to increase the clock frequency without increasing TDP, other solutions allow you to increase the TDP of the processor at least twice, which allows you to increase the processor clock frequency at least 2 times without changing anything in modern design approaches. By changing the organization of the internal structure of the processors and applying some design solutions 2 more times.
In total, this makes it possible to have a processor clock frequency of more than 10 GHz. This is where synchronization issues come into play.
Conclusion
Of course, these are not all trends and problems in the development of processors.
There is no end to the depth of the issue, dozens of deeply scientific works can be written on it, but time will still pass and new problems will arise that need to be addressed.
I wanted to tell here that the history of the development of processors is a constant compromise, the result of which is often not at all what the leaders of the industry are planning. And the number of compromises and, accordingly, the restrictions becomes greater when approaching the physical limits of the main element of the CMOS transistor processor. And then it remains only to fulfill Moore's "Law" at the expense of huge caches.
An example of such a compromise is limiting the clock frequency of the processor.
The accumulation of these compromises eventually becomes insurmountable, and this is the dead end of this technology.
According to information Fujitsu , made on 45 microns of those. process, eight-core SPARC64 VIIIfx processor ( Venus ) has a computation speed of 128 GFLOPs, - 2.5 times faster than the best Intel, dual-core Itanium 2, however, even with built into Venus memory manager consumes only 33% of Itanium 2 , therefore about 35W.
One of the "specialists" calculated the clock speed of this processor as 16 GHz.
This is not true already because, with a similar structure of transistors, modern tech. processes and a TDP of 35 W, its clock frequency cannot exceed 4 GHz.
But soon there will be processors new generation, where instead of buses for communication with external devices, the built-in processor will be used optical systems data transmission. These are buses for information exchange with memory, external devices (PCI-E, ...), and even communication buses with HDD, SSD, ....
And the processor, like the computer, will appear in a new form and possibly quality.
P.S.
The article was written in 2009, and now it’s mid-2013 (a year from the forecast), and now, after some silence, reports from observers like “10 nm process technology is a reality of 2015” appeared, and practitioners attribute the development of the processor to 2018. In the meantime, since the beginning of 2012, only processors based on the 22 nm process technology have been mass-produced.
With a further decrease in technological standards (already from 45 nm process technology), the technological difficulties of their development progressively increase.
An example of this is the 22 nm process technology, which was demonstrated in 2008, and mastered in the production of processors only 4 years later (2012).
Therefore, even if (not at all a 10 nm process technology) a 14 -18 nm process is demonstrated in 2015-2018, it can be mastered no earlier than 2020-2025.
I'll be happy to be wrong.
August 2013
Literature.
1. “The GaN transistor is the toughest nut yet” V. Danilin, T. Zhukova, Yu. 4/3
2. Intel Introduces Prototype High-Speed Optical I/O Interface for Chip-to-Chip Interconnects by Ian Young, http://www.intel.com/corporate/europe/emea/rus/country/update/ contents/it04041.htm
3. A Russian specialist has developed an optoelectronic motherboard new generation, surpassing even the modern counterparts of IBM. http://www.sciteclibrary.ru/rus/catalog/pages/5833.html
4. Optical future news from [email protected] Daw, Chip, September 2009
A.Sorokin
The best CPU for your money
Do you want to buy the best CPU for your money? With the best performance/price ratio? With high speed? Then we recommend that you read our article. In it, we will indicate the processors that provide the best performance for their price.
We understand that not everyone has time to read. detailed reviews processors, as well as digging into complex CPU specifications. That is why experts release a summary every few months, allowing you to choose the best processor in your price range.
Before you begin to get acquainted with our recommendations, we will make a few reservations. The prices in this article are at the time of publication. Therefore, we recommend that you familiarize yourself with the prices relevant to this moment, on resources such as market.yandex.ru and price.ru. We took into account the prices of new processors only. Do not forget that various promotions and discounts can be obtained in stores, which can tip the scales in favor of one or another CPU. In any case, you will certainly not regret buying any of the processors recommended in the article.
Before buying, we recommend that you familiarize yourself with the comparative performance index of selected models. This can be done, for example, in the Anandtech online database.
Latest news from AMD
In October 2011, AMD introduced the new AMD FX processor line, also known as the Bulldozer. Unfortunately, performance was pretty poor, and even the fastest processor, the 8-core 3.6GHz FX-8150, couldn't compete with the Intel Core i5-2500 in most cases, let alone new processors.
Or you can refer to the following diagrams.
AMD released in retail sale the Phenom II X6 1045T processor, which was previously only available to OEMs. Six cores operate at a frequency of 2.7 GHz, and at a price of 4,200 rubles. we get a really interesting novelty for "budget" workstations, where applications will be able to load all six cores. But modern games do not know how to use more than four (or even three) cores, so this processor is not so interesting to us.
at a price of 4,500 rubles.
for 4,000 rubles.
few tests available so far
The six-core FX-6200 was also released for 5,600 rubles. ,
for 300 rubles. expensive . But if you run applications capable of using six cores, then the new FX-6200 will be quite interesting.
Latest news from Intel
Of course everyone is looking forward to Intel processors Ivy Bridge, which should appear at the end of April. They are manufactured on a 22nm process, which allows us to hope for better power efficiency. It is hardly worth expecting a special increase in performance, but the prices of other models should be shaken.
9 900 rubles.
18 300 rub.
If you buy four cores, then the Core i7-2600K processor with an unlocked multiplier for LGA1155 seems to be a more interesting alternative for the same 9,900 rubles. However, many enthusiasts will disagree with us, as they prefer a powerful platform with support for configurations on multiple video cards and four memory channels. Either way, it's up to you, which is why we've added a quad-core Core i7-3820 to the alternatives.
Intel also decided to introduce the Core i5-2550K processor to the market at a price of 7,300 rubles. It runs at a base clock speed of 3.4 GHz, with Turbo Boost up to 3.8 GHz, a 100 MHz increase over the recommended Core i5-2500K (3.3 - 3.7 GHz). Moreover, the Core i5-2500K costs a little cheaper - 6,700 rubles. To be honest, we don't think it's worth paying extra for a 100 MHz increase, since the Core i5-2500K multiplier is already unlocked, and you can do the same operation in the BIOS for free. Of course, if the Core i5-2550K had any overclocking advantage or better potential, then we would recommend it. But we did not find any evidence of this.
The Core i7-2700K processor fell in price to 10,600 rubles. - perhaps in order not to stand out indecently against the background of the Core i7-3820 for 9,900 rubles.
As a result, today the Core i7-2700K costs only 700 rubles more than the Core i7-2600K for 9,900 rubles. The difference isn't huge, but we still don't see the point in paying extra for 2700K since the 2600K has an unlocked multiplier and you can get the same boost for free.
Intel also busied itself with announcing some "stripped down" processors. The "twin" Intel Core i5-2400 without the HD Graphics 2000 graphics core, called the Core i5-2380P, entered the market. His price is the same - 5,800 rubles. ,
all specifications are identical to the Intel Core i5-2400. Another curious Intel Core i5-2450P model has also been released at a price of 6,400 rubles. You won’t get an integrated graphics core either, and the operating frequency of 3.2-3.5 GHz is between the Core i5-2400 (3.1-3.4 GHz) and Core i5-2500 (3.3-3.7 GHz) . Both the Core i5-2380P and Core i5-2450P processors are hardly recommended, as you get a CPU without a graphics core (and without the ability to accelerate video encoding on it), but without a price advantage.
price 9 500 rub. for 9 300 rubles,
In March 2012, Intel announced new Xeon E5 processors for servers and workstations, which Chekanova Lab already wrote about in a report from an Intel event in Moscow. workstation, the option is just great.
The best processor at a price of 1,400 rubles - Intel Celeron G530 (Sandy Bridge)
The Intel Celeron G530 processor, with its modern Sandy Bridge architecture, runs at 2.4 GHz, yet it easily outperforms the Athlon II X2 260 at 3.2 GHz in almost every application. So don't look at the low clock speed.
The best processor under the price of 2,000 rubles - Intel Pentium G630 (Sandy Bridge)
The Intel Pentium G630 processor replaced the previous G620 model due to the previous price level of 2,000 rubles, but the frequency increased by 100 MHz and amounted to 2.7 GHz. The processor is slightly more productive than the Intel Celeron G530 and has only one competitor in this price range: AMD Athlon II X2 260 (1,900 rubles on Yandex.Market). But the Pentium G620 easily outperforms the competitor Athlon II X2 260 in games and in most applications. Not to mention the G630, which is 100 MHz faster than the G620. Also, according to Anandtech's review, the Pentium G620 consumes 40W less under load than the Athlon II X2 260.
The best processor at a price of 2,600 rubles - Intel Pentium G850 (Sandy Bridge)
In this price range, the Intel Pentium G850 processor costs 2,600 rubles. there is only one competitor on Yandex.Market - Athlon II X3 455 at a price of 2,500 rubles. with three cores at 3.3 GHz, but no L3 cache. But we still chose the Pentium G850 because this processor outperforms the Athlon II X3 in games and many applications, and consumes 51.8 W less under full load.
Verdict: an excellent processor for "budget" assemblies, including gaming PCs. But if you can pay extra for the Core i3-2120, then it's better to choose the latter. See how the Core i3-2100 is faster than the Pentium G850. And the Core i3-2120 is another 200 MHz more productive.
Alternative 1. AMD Phenom II X2 555 Black Edition for 3,000 rubles.
The AMD Phenom II X2 555 processor runs at 3.2 GHz, has two cores and a full 6 MB L3 cache. The performance is close to the Phenom II X3 720, and the possibility of unlocking the cores also exists. Add to that an unlocked multiplier.
In general, we have an interesting alternative to the Intel Pentium G850 for fans of AMD products.
The best processor at a price of 3,900 rubles - Intel Core i3-2120 (Sandy Bridge)
Alternative 1. AMD Phenom II X4 955 Black Edition for 4,100 rubles.
The AMD Phenom II X4 955 Black Edition processor with four cores at 3.2 GHz at stock frequencies is slower than the Core i3-2120, but the advantage lies in overclocking the AMD CPU to 3.8-4.0 GHz without any problems. And then the Phenom II X4 955 Black Edition will provide performance at the level of the Core i3-2120 in games and will be significantly faster in multi-threaded applications (audio and video encoding) thanks to four physical cores. Don't forget to get a good cooler!
Alternative 2. AMD Phenom II X4 960T Black Edition for 4,100 rubles.
The AMD Phenom II X4 960T Black Edition processor is based on the Zosma core, a 4-core version of the 6-core Thuban design. The L3 cache is 6MB and the four cores run at 3.0GHz. Along with that, you get an unlocked multiplier as well as the ability to unlock all six cores.
After unlocking all six cores, gaming performance will still be inferior to the Core i3-2120, according to Anandtech benchmarks. But you'll get a noticeable boost over Intel in multi-threaded tests like video and audio encoding and photo editing. At the same time, overclocking the processor to 3.3 GHz already gives performance at the level of Core i3-2100, and no one bothers to overclock AMD Phenom II X4 960T Black Edition even more.
Alternative 3. AMD Phenom II X6 1045T for 4,200 rubles.
Six cores for 4,200 rubles - the offer is very profitable. Let the 1045T processor's multiplier be locked and the frequency is 2.7 GHz, but you can overclock this CPU on the bus. And for workstations, six cores do very well - if you have applications that can load them.
Alternative 4. AMD FX-4170 for 4,500 rubles.
In March 2012, a 4.2 GHz AMD FX-4170 processor with four 4.2 GHz cores (maximum Turbo Core frequency 4.3 GHz) entered the market at a price of 4,500 rubles.
At a price it is sold a little more expensive than the dual-core Core i3-2120 for 4,000 rubles.
Performance in practice appears to be close, although few benchmarks are currently available. Therefore, we recommend this processor as an alternative to the Core i3-2120.
The best processor at a price of 5,900 rubles - Intel Core i5-2400 (Sandy Bridge)
The Intel Core i5-2400 processor provides four computing cores with Sandy Bridge microarchitecture at a frequency of 3.1-3.4 GHz. And it is sold at a price of 5,900 rubles in Yandex.Market, that is, somewhat cheaper than the 3.3-GHz Core i5-2500.
You get great performance per core, but overclocking is unfortunately limited. Raising the base frequency of BCLK will not seriously work, and for overclocking we recommend versions of the "K" processors, the multiplier of which is unlocked. For example, Core i5-2500K.
In the case of the Intel Core i5-2400, only limited overclocking is possible, that is, the maximum frequency will be 3.8 GHz with one active core. In the case of four active cores, limited overclocking allows you to get 3.6 GHz instead of the default 3.2 GHz. Basically, not bad.
Intel Core i5-2500K processor at a price of 7,293 rubles. The overpayment is noticeable, but the multiplier for this processor is unlocked, so nothing will interfere with overclocking. Of course, except for the cooler and the motherboard.
Verdict: good processor for productive assemblies, including for gaming PCs.
If you are interested Intel performance Core i5-2400 compared to the more expensive Core i5-2500, we recommend referring to the following chart.
Note that for HTPC you can take a more economical Intel Core i5-2400S processor with a maximum heat dissipation of 65 W, which operates at a frequency of 2.5-3.3 GHz. It will cost 200 rubles more. You will get a comparable level of performance with less heat generation.
Alternative 1. AMD FX-6200 for 5,600 rubles.
Also in February / March 2012, the six-core FX-6200 was released for 5,600 rubles. ,
The processor runs at 3.8 GHz (4.1 GHz maximum Turbo Core frequency). The processor turned out to be much more interesting than the FX-6100 model, since we get faster six cores. On the other hand, this frequency is still not enough to effectively compete with Sandy Bridge cores, so we would prefer the Core i5-2400 for 300 rubles. expensive .
But if you run applications capable of using six cores, then the new FX-6200 will be quite interesting.
The best processor at a price of 6,500/6,900 rubles - Intel Core i5-2500 / K (Sandy Bridge)
The Intel Core i5-2500 processor provides four computing cores with Sandy Bridge microarchitecture at a frequency of 3.3-3.7 GHz. And it is sold at a price of 6,500 rubles. in Yandex.Market.
You get great performance per core, but overclocking is unfortunately limited. Raising the base frequency of BCLK will not seriously work, and for overclocking we recommend versions of the "K" processors, the multiplier of which is unlocked.
In the case of the Intel Core i5-2500, only limited overclocking is possible, that is, the maximum frequency will be 4.1 GHz with one active core. In the case of four active cores, limited overclocking allows you to get 3.8 GHz instead of the default 3.4 GHz. Basically, not bad.
But for serious overclocking, we recommend choosing an Intel Core i5-2500K processor at a price of 6,900 rubles.
Verdict: An excellent processor for high performance builds, including gaming PCs.
Does the Intel Core i5-2500 have competitors? AMD's fastest processor to date is the 8-core 3.6GHz FX-8150 at an average price of 8,100 rubles. on Yandex.Market. But the Core i5-2500 outperforms the FX-8150 in most tests, especially in gaming applications. In addition, the Core i5-2500 is cheaper, and consumes about 100 watts less under load, according to Anandtech.
If you are interested in the performance of the Intel Core i5-2500 compared to other processors, then we recommend that you refer to the following charts.
Note that for HTPC you can take a more economical Intel Core i5-2500S processor with a maximum heat dissipation of 65 W, which operates at a frequency of 2.7-3.7 GHz. It will cost the same amount. You'll get a comparable level of performance (with a base frequency of 2.7 GHz) with less heat.
Alternative 1. AMD FX-8150 for 8,100 rubles.
We decided to add the eight-core flagship AMD FX-8510 to our recommendations. The processor operates at a frequency of 3.6 GHz. The performance in games did not please, the FX-8150 processor hardly overtook the Phenom II processors previous generation(sometimes even lagged behind). The Intel Core i5 and i7 processors led noticeably in terms of gaming performance. In intense multi-threaded environments, the FX-8150 could compete with the Core i5-2500 or Core i7-2600 and even outperform the Core i7-2600 in some cases. However, the FX line shows itself extremely poorly in single-threaded performance, yielding even to Phenom II processors.
The best processor at a price of 9,200/9,900 rubles - Intel Core i7-2600/K (Sandy Bridge)
At first glance, the Intel Core i7-2600 processor seems only slightly faster. Intel version Core i5-2500 since the number of physical cores is the same. And there, and there are four of them. But do not forget that the Intel Core i7-2600 processor supports Hyper-Threading virtual multithreading technology, as a result of which you will get eight logical cores that will perform well in multi-threaded environments (video and audio encoding, photo editing).
As for games, it hardly makes sense to buy a processor faster than the Intel Core i5-2500 or Intel Core i5-2500K. And the money saved is better to put aside for a faster video card.
Verdict: A great processor for performance builds and environments that can load all eight logical cores.
Overclocking in the case of the Intel Core i7-2600 is only possible limited. Therefore, for serious overclocking, we recommend choosing an Intel Core i7-2600K processor at a price of 9,900 rubles. The overpayment is quite small, but the multiplier for this processor is unlocked, so nothing will interfere with overclocking. Of course, except for the cooler and the motherboard.
Intel recently announced the Core i7-2700K, priced at Rs. but we do not recommend taking it. You will just get a 100 MHz accelerated version of the CPU, which, given the unlocked multiplier for "K" processors, is not at all relevant. Moreover, the Core i7-2700K and Core i7-2600K processors have the same stepping.
Recently, Intel introduced the Core i7-2600S processor, which is priced at 9,500 rubles. It runs at a base frequency of 2.8 MHz, which is 600 MHz lower than the regular Core i7-2600 model for 9,200 rubles, although the Turbo Boost frequency of 3.8 GHz is the same here. But the thermal package was reduced to 65 watts instead of 95 watts. This processor will be an interesting alternative for economical, but productive computers.
Alternative 1. Intel Core i7-3820 for 9,900 rubles.
The main news of February-March can be called the appearance on sale of the Core i7-3820 processor, which can be found at a price of 9,900 rubles.
The processor is the least expensive product in the Intel family for Socket 2011, we just chose this particular CPU for . It is equipped with four channels of DDR3 memory and an integrated PCI Express 3.0 controller, but this hardly justifies its high price. Still, do not forget that the main attractive feature of Sandy Bridge-E is six processing cores, so we recommend taking at least the Core i7-3930K, even if it costs 18,200 rubles.
The best processor at a price of 18,200 rubles - Intel Core i7-3930K (Sandy Bridge-E)
Before us is the second-best processor on the market, which is sold for 14 thousand rubles cheaper than the leader Core i7-3960X, runs only 100 MHz slower and is equipped with only 3 MB of L3 cache less. Meet: Intel Core i7-3930K at a price of 18,200 rubles in Yandex.Market. The processor is worth buying if you want to purchase a Sandy Bridge-E microarchitecture model with six physical cores (twelve logical ones), a four-channel memory controller and an unlocked multiplier.
In general, we have an ideal processor for workstations. For regular assemblies and gaming PCs, it is redundant, it is better to take the Core i5-2500 or Core i5-2500K, and invest the money saved in the video card. On the other hand, if you're working in a multi-threaded environment, or have multiple high-end GPUs in your gaming PC, then the Intel Core i7-3930K can unleash its potential.
Verdict: A great processor for performance builds and environments that can load all twelve logical cores.
The best processor at a price of 31,700 rubles - Intel Core i7-3960X Extreme Edition (Sandy Bridge-E)
If you can afford to spend any amount on a processor, then we recommend taking the most productive CPU on the market - Intel Core i7-3960X Extreme Edition at a price of 31,700 rubles.
You'll get six cores, which turn into 12 logical cores thanks to Hyper-Threading support. Normally they operate at a frequency of 3.3 GHz, but acceleration up to 3.9 GHz is possible in the case of single-threaded applications. However, the unlocked multiplier allows you to overclock the processor to higher frequencies.
You can find more details about the performance of the top processor in our article.
Processor Performance Comparison Table
On the Tom's Hardware Guide website you can find a table of relative CPU performance. We recommend upgrading only if the new processor is three or four positions ahead of the old one. Otherwise, the update is unlikely to affect performance.
New laptops based on the Intel Ivy Bridge platform have already appeared on sale, and many are wondering what this mobile platform. By the way, it is available in the version for mobile computers, and for ordinary, desktop. Traditionally, it is believed that the desktop version is more productive, but now Intel promises us that mobile processors will be very powerful.
In this article we will talk about the new processors from Intel in 2012, but in the next one we will touch on the integrated graphics of the Intel HD 4000. We will deliberately not go into technical details. Still, our site is more aimed not at professionals, but at those who simply want to better understand the design of laptops. Well, if this is not enough for you, there are a lot on the network. detailed reviews Intel Ivy Bridge.
So, Intel Ivy Bridge is a logical continuation of another popular one that made a lot of noise at one time. Only if the latter was made according to the 32nm process technology, then Ivy Bridge is a step forward, because these processors are made according to the 22nm process technology. This made it possible to reduce their size, while increasing performance and reducing power consumption.
Recall that Intel releases its processors using its own tick-tock strategy. “Tick” is the miniaturization of the process technology (for example, from 32 to 22 nm), “so” is already a completely new architecture. Thus, Sandy Bridge processors are "so", and the new Ivy Bridges are "tic". In 2012, a new “so” is expected - Haswell processors.
Ivy Bridge processors belong to the Intel Core family already known to us, this is their third generation. The manufacturer promises us higher performance and improved support compared to older versions. wireless networks. Well, plus the built-in USB 3.0, which will make it possible to exchange data with external devices much faster. Reduced power consumption was added to the increased performance - from 17 to 55 watts, depending on the processor.
Processors in the new line - both quad-core and dual-core. The most productive of them is the 3920XM, which runs at a stock clock speed of 2.9 GHz, but at the same time can be overclocked using Turbo Boost technology up to 3.8 GHz. New processors will transcode video much faster - almost four times faster. In addition, they heat up less.
The processor also has a built-in random number generator plus protection operating system from hacker attacks aimed at "elevation of privileges". The memory controller has also been improved - it now supports faster and less power-intensive RAM DDR3.
Built-in and support for the Thunderbolt interface, which now uses Apple company on their laptops. It provides very fast data transfer from external devices. Well, in general, up to three displays can be connected to a laptop on this platform at once, and if you want to play games in this way or simply expand your desktop, you are welcome.
Here is a list of all 2012-2013 Intel Ivy Bridge mobile processors:(as of 05/06/2013)
Meaning of indexes:
M- Mobile processors
XM- extreme 4-core processors with unlocked multiplier
QM- 4-core processors
U- processors with reduced TDP (power consumption)
Y- ultra-low TDP processors
And there are more, most of which are designed for installation in ultrabooks and tablets:
(image enlarges by clicking)
Meaning of indexes:
E- embedded processors
QE- 4-core embedded processors
ME- embedded mobile
LE- performance optimized
UE- energy optimized