Intel is a success story. Company "Intel" entering the market

Send your good work in the knowledge base is simple. Use the form below

Students, graduate students, young scientists who use the knowledge base in their studies and work will be very grateful to you.

Similar documents

Intel History, RAM output for computer. The main features of building a brand company. Processor models manufactured by Intel. Types of substrates used in the production of microcircuits. Brief history of Pentium processors.

abstract, added 02/13/2013


Intel processor development strategy. The structural organization of modern universal microprocessors. Features of the multi-core processor microarchitecture Intel Core, Intel Nehalem, Intel Westmere. Intel server platforms using Xeon.

abstract, added 07.01.2015


The history of the development of Intel. Development and release of Intel processors. ATOM technology review. Overview of processors. Gigabyte GC230D motherboard. Laptops based on Intel Atom processors. MSI Wind U100-024RU, ASUS EEE 1000H, Acer One Aoa 150-BB.

coursework, added 24.11.2008


Nest or slit connector of the central processor to facilitate its installation. Standard Socket type slot. The history of the change and characteristics of all sockets used to install Intel processors. Development of new Intel interfaces.

abstract, added 01.10.2009


Development of software that effectively using computational resources due to the simultaneous execution of the code on several computing nodes. Intel Review to use tools and parallel programming languages.

abstract, added on 12/25/2011


The architecture of system boards based on Intel 6 Series and Intel P67 Express chipsets. Technologies used in Intel 6 Series: Smart Response, Intel Quick Sync Video, Hyper-Threading Technology, Intel VPRO technology. Error in the Intel 6th series chipsets.

abstract, added 11.12.2012


The history of the development of Intel Corporation, its financial indicators and plans for the future. Basic software products: C ++ Compiler for Linux and For Windows, Visual Fortran Compiler for Windows, Vtune Performance Analyzer. Intel Anti-Theft Information Protection.

abstract, added 04/02/2010


Characteristics of microprocessors Intel and AMD. Development and comparison of microprocessor performance. AMD headquarters, its production facilities. Description of the free Linux operating system and its capabilities. Methods for entering information.

examination, added 19.02.2009

Understand the company Intel And three of its founders can only be when you understand the silicon valley and its origins. And in order to do this, you need to penetrate the company's story. Shokley Transistor., Treacherous eight and Fairchild Semiconductor. Without their understanding, Intel will remain for you the same as for most people - a secret.

The invention of computers did not mean that the revolution began immediately. The first computers based on large, non-shrouded, quickly breaking electronic lamps were expensive mounds, which could only contain corporations, universities where scientific research was conducted, and the military. The appearance of transistors, and then new technologies that allow millions of transistors on a tiny microchip, meant that the computational power of many thousands of Eniac devices can be focused on the head part of the rocket, in a computer that can be kented and in portable devices.

In 1947, Bell Laboratory engineers John Bardin and Walter Brattein invented the transistor, which was represented by the general public in 1948. A few months later, William Shockley, one of the employees of Bell, developed a model of a bipolar transistor. The transistor, which, in fact, is a solid-state electronic switch, replaced the bulky vacuum lamp. The transition from vacuum lamps to transistors laid the beginning of a tendency to miniaturization, which continues today. The transistor has become one of the most important discoveries of the XX century.

In 1956, the Nobel laureate in Physics William Shockley created the company SHOCKLEY SEMICONDUCTOR LABORATORY to work on four-layer diodes. Shocley failed to attract their former employees from Bell Labs; Instead, he hired a group, in his opinion, the best young electronics specialists who have recently graduated from American universities. In September 1957, due to the conflict with Shockley, who decided to stop the study of silicon semiconductors, eight key employees of Shokley Transistor decided to leave their jobs and start doing their own business. Eight people are now forever known as a treacherous eight. This epithet gave them shocks when they left work. The eight includes Robert Neuss, Gordon Moore, Jay Lasta, Gina Guiurni, Viktor Grhenich, Yujina Kleiner, Sheldon Roberts and Julius Blanca.

After care, they decided to create their own company, but the investment to take it was nowhere. As a result of a call, 30 firms they stumbled upon Fairchild - the owner of Fairchild Camera and Instrument. He happily invested one and a half million dollars to a new company, which was almost twice as much as it was originally considered the eight of its founders. The so-called transaction with the award was concluded: if the company is successful, he will be able to redeem it completely over three million. Fairchild Camera and Instrument took advantage of this right in 1958. Came a subsidiary of Fairchild Semiconductor.

In January 1959, one of the eight founders of Fairchild, Robert Neuss invented a silicon integral scheme. At the same time, Jack Kilby in Texas Instruments invented Germany integrated circuit for six months before - in the summer of 1958, however, the Neuss model turned out to be more suitable for mass production, and it is it used in modern chips. In 1959, Kilbi and Neuss independently submitted applications for patents on the integrated circuit, and both successfully received them, and Neuss received his patent first.

In the 1960s, Fairchild became one of the leading manufacturers of operating amplifiers and other analog integrated circuits. However, at the same time, the new management of Fairchild Camera and Instrument began to limit Fairchild Semiconductor's freedom, which led to conflicts. Members of the G8 and other experienced employees one after another began to dismiss and base their own companies in the Silician Valley.

The first name selected by Necess and Murom was NM Electronics, N and M - the first letters of their surnames. But it was not too impressive. After a large number of not very successful offers, such as the Electronic Solid State Computer Technology Corporation, came to the final decision: the company will be called Integrated Electronics Corporation. In itself, it was also not too impressive, but there was one dignity. Abbreviated company could be called Intel. It sounded well. The name was energetic and eloquent.

Scientists set themselves a completely definite goal: create a practical and affordable semiconductor memory. Nothing similarly was previously created, given the fact that the storage device on silicon chips was worth at least a hundred times more expensive for the time of memory on magnetic cores. The cost of semiconductor memory reached one dollar per bit, while the storage device on magnetic cores was worth only about the cent of the bits. Robert Neuss said: "We needed to make only one thing - to reduce the cost a hundred times and thereby conquer the market. This is exactly what we basically and engaged. "

In 1970, Intel has released a memory chip in 1 kbps, far exceeding the capacity of the current microcircuits (1 kbps is 1024 bits, one byte consists of 8 bits, that is, the microcircuit could store only 128 bytes of information, which is negligible for modern standards. ) The created chip, known as the dynamic operational storage device (DRAM) 1103, was by the end of next year the most sold semiconductor device in the world. By this time, Intel rose from a handful of enthusiasts to the company, numbering more than a hundred employees.

At this time, the Japanese company Busicom turned to Intel with a request to develop a set of microcircuits for a family of highly efficient programmable calculators. The initial design of the calculator was provided for at least 12 microcircuits of various types. Intel Ted Hoff Engineer rejected this concept and instead developed a single-chip logical device that receives the application commands from semiconductor memory. This central processor has been working running a program that allows you to adapt the microcircuit functions to perform incoming tasks. The microcircuit was universal in nature, that is, its use was not limited to a calculator. The logical modules had only one destination and a strictly defined set of commands that were used to control its functions.

One problem was connected with this microcham: all rights to it belonged exclusively Busicom. Ted Hoff and other developers understood that this design has almost unlimited use. They insisted that Intel bought the rights to the created chip. Intel suggested a busicom to return 60 thousand dollars paid by it for a license in exchange for the right to dispose of the developed microcircuit. As a result, Busicom, being in a difficult financial situation, agreed.

On November 15, 1971, the first 4-bit microcomputer kit 4004 appeared (the term microprocessor appeared significantly later). The microcircuit contained 2300 transistors, cost 200 dollars and in its parameters was comparable to the first EUM ENIA created in 1946, which used 18 thousand vacuum electronic lamps and occupied 85 cubic meters.

The microprocessor performed 60 thousand operations per second, worked at a frequency of 108 kHz and was produced using a 10 micron technology (10,000 nanometers). The data was transmitted by 4 bits for tact with blocks, and the maximum addressable memory volume was 640 bytes. The 4004th was used to control traffic lights, when analyzing blood and even in the Pioneer 10 Research Rocket, launched by NASA.

In April 1972, Intel released the 8008 processor, which worked at a frequency of 200 kHz.

The following processor model, 8080, was announced in April 1974.

This processor has already contained 6000 transistors and could be addressed to 64 KB of memory. On it was the first personal computer (not PC) Altair 8800. The CP / M operating system was used in this computer, and Microsoft has developed a Basic programming language interpreter. It was the first mass model of the computer for which thousands of programs were written.

Over time, 8080 has become so famous that he began to copy it.

At the end of 1975, several former Intel engineers involved in the development of the 8080 processor were created by Zilog. In July 1976, this company released the Z-80 processor, which was a significantly improved version of 8080.

This processor was incompatible from 8080 by contact conclusions, but combined many different functions, such as memory interface and RAM update scheme, which made it possible to develop cheaper and simple computers. The Z-80 also includes an extended set of 8080 processor commands, which allows using its software. This processor includes new teams and internal registers, therefore software developed for Z-80 could be used almost with all versions of 8080.

Initially, the Z-80 processor worked at a frequency of 2.5 MHz (later versions already worked at a frequency of 10 MHz), contained 8500 transistors and could address 64 KB of memory.

Radio SHEC has chosen the Z-80 processor for its personal computer TRS-80 Model 1. Soon the Z-80 has become a standard processor for systems operating with the CP / M operating system and the most common at that time.

Intel did not stop at the achieved, and in March 1976 released the 8085 processor, which contained 6500 transistors, worked at 5 MHz and was produced in 3 micron technology (3000 nanometers).

Despite the fact that it was released a few months earlier than the Z-80, he never managed to achieve the popularity of the latter. It was used mainly as a control chip of various computerized devices.

In the same year, Mos Technologies released a 6502 processor, which was absolutely not similar to Intel processors.

It was developed by a group of engineers of Motorola. The same group worked on the creation of a 6800 processor, which in the future was transformed into the family of processors 68000. The price of the first version of the 8080 processor reached the three hundred dollars, while the 8-bit 6502 cost only about twenty-five dollars. Such a price was quite acceptable for Steve Woznia, and he embedded the processor 6502 to the new models of Apple I and Apple II. The 6502 processor was also used in the systems created by Commodore and other manufacturers.

This processor and its successors were successfully worked in game computer systems, which included Nintendo Entertainment System. Motorola continued to work on creating a 68000 processor series, which were subsequently used in Apple Macintosh computers. The second generation of MAC computers used the PowerPC processor, which is a successor of 68000. Today, Mac computers switched to the PC architecture and use some processors, system logic chips and other components with them.

In June 1978, Intel introduced the 8086 processor, which contained a set of commands under the codenamed x86.

The same set of commands is still supported in all modern microprocessors: AMD Ryzen Threadripper 1950x and Intel Core i9-7920X. The 8086 processor was completely 16-bit - internal registers and data bus. It contained 29,000 transistors and worked at 5 MHz. Thanks to the 20-bit address bus, it could address 1 MB of memory. When creating the 8086th, backward compatibility with the 8080s was not provided. But at the same time, the significant similarities of their commands and the language allowed to use earlier software versions. This property subsequently played an important role to quickly transfer CP / M system (8080) on PC rails.

Despite the high efficiency of the 8086 processor, its price was still too high by the standards of the time and, which is much more important, for its work, an expensive microcircuit of supporting a 16-bit data bus was required. To reduce the cost of the processor, in 1979 Intel released the 8088 processor - a simplified version of 8086.

The 8088th used the same inner kernels and 16-bit registers as 8086, could address 1 MB of memory, but unlike the previous version used an external 8-bit data bus. This allowed backward compatibility with a previously developed 8085-developed 8085 processor and thereby significantly reduce the cost of the systemics and computers created. That is why IBM chose the 8088 processor for its first PC, and not 8086. This decision had far-reaching consequences for the entire computer industry.

The 8088 processor was completely software-compatible with 8086, which made it possible to use 16-bit software. In the processors 8085 and 8080, a very similar set of commands was used, so programs written for processors of previous versions could be easily converted for processor 8088. This, in turn, made it possible to develop a variety of programs for IBM PC, which was the key to his future success. Not wanting to stop halfway, Intel was forced to provide 8086/8088 backward compatibility support with most processors released at that time.

Intel immediately began to develop a new microprocessor after exit 8086/8088. Processors 8086 and 8088 demanded a large number of support chips, and the company decides to develop a microprocessor that already contains all the necessary modules on the crystal. The new processor included a plurality of components previously produced in the form of individual chips, this would allow dramatically to reduce the number of microcircuits in the computer, and, therefore, and reduce its value. In addition, the internal command system was expanded.

In the second half of 1982, Intel releases an embedded processor 80186, which, in addition to the improved 8086 kernel, also contained additional modules that replace some support chip.

Also in 1982, 80188 was released, which is an option of microprocessor 80186 with an 8-bit external data bus.

A 16-bit X86-compatible microprocessor 80286 was released on February 1, 1982 was an advanced version of the 8086 processor and possessed 3-6 times greater performance.

This qualitatively new microprocessor was then used in an IBM PC-AT epochal computer.

The 286th was developed in parallel with the processors 80186/80188, but it did not have some modules in the Intel 80186 processor. The Intel 80286 processor was produced in exactly the same case as Intel 80186 - LCC, as well as in PGA enclosures with sixty eight with conclusions.

In those years, the backward compatibility of processors was still maintained, which no longer prevented introducing various innovations and additional possibilities. One of the main changes was the transition from the 16-bit internal architecture of the processor 286 and earlier versions to 32-bit internal architecture of the 386th and subsequent processors belonging to the category IA-32. This architecture was presented in 1985, but it took another 10 years so that such operating systems appear on the market as Windows 95 (partially 32-bit) and Windows NT (requiring the use of exceptionally 32-bit drivers). And after another 10 years later, Windows XP operating system appeared, which was 32-bit both at the driver level and at the level of all components. So, the adaptation of 32-bit calculations was required for 16 years. For the computer industry, this is quite a long time.

80386th appeared in 1985. It contained 275 thousand transistors and performed more than 5 million operations per second.

Compaq's DeskPro 386 computer was the first PC created on the basis of a new microprocessor.

The following from the family of processors X86 was the 486th, which appeared in 1989.

Meanwhile, the US Department of Defense did not please the prospect of staying with a single supplier of chips. As the latter became less and less (remember, what kind of zoo was observed at the beginning of the nineties), the importance of AMD, as an alternative manufacturer, grew. By agreement of 1982, AMD had all licenses for the production of processors 8086, 80186 and 80286, however, the freshly developed 80386 Intel processor to transmit AMD refused to be categorically. And the agreement broke. Further followed by a long and loud trial - the first in the history of companies. He ended only in 1991 by Victory AMD. For its position Intel paid the plaintiff a billion dollars.

But nevertheless, the relationship was poured, and there was not a relationship about the former confidence. Moreover, the AMD went along the way Reverse Engineering. The company continued to produce different hardware, but completely coinciding the Microc of the AM386 processors, and then AM486. Intel went to court here. The process was dragged for a long time, and the success turned out to be on one, then on the other side. But on December 30, 1994, a court decision was made, according to which the Intel microcode is still the property of Intel, and somehow it is not good to use other companies if the owner does not like it. Therefore, since 1995, everything has changed seriously. In Intel Pentium and AMD K5 processors, any applications for the X86 platform were launched, but from the point of view of architecture they were fundamentally different. And it turns out that at all the real competition Intel and AMD began only after a quarter of a century after the creation of companies.

However, to ensure compatibility, cross-pollination technologies have not gone anywhere. In modern Intel processors, a lot of patented AMD, and, on the contrary, AMD gently adds instruction sets developed by Intel.

In 1993, Intel introduced the first Pentium processor, the performance of which increased fivefold compared with the productivity of the 486 family. This processor contained 3.1 million transistors and performed up to 90 million operations per second, which is about one and a half thousand times higher than the speed of 4004.

When the next generation of processors appeared, those who hoped the name Sexium were disappointed.

The P6 family processor, called Pentium Pro, was born in 1995.

Revising the architecture P6, Intel in May 1997 introduced the Pentium II processor.

It contained 7.5 million transistors, packed, in contrast to the traditional processor, in the cartridge, which made it possible to place the L2 cache directly in the processor module. It helped to significantly increase its speed. In April 1998, the Pentium II family was replenished with a cheap Celeron processor used in the home PC, and the Pentium II Xeon professional processor, intended for servers and workstations. Also in 1998, Intel first integrated the second-level cache memory (which worked at the full frequency of the core of the processor) directly into the crystal, which made it possible to significantly increase its speed.

While the Pentium processor rapidly conquered the dominant position in the market, AMD acquired Nexgen, who was working on the NX686 processor. As a result of the merger of companies, AMD K6 processor appeared.

This processor, both in hardware and software, was compatible with the Pentium processor, that is, installed in the socket Socket 7 and performed the same programs. AMD continued the development of faster versions of the K6 processor and won a significant part of the middle class PC market.

The first processor for desktop computing machines of the older model containing the built-in second-level cache and operating with the full core frequency was the Pentium III processor, created on the basis of the Coppermine kernel, presented at the end of 1999, which was, in essence, Pentium II, Containing SSE instructions.

In 1998, AMD introduced the Athlon processor, which allowed her to compete with Intel on the high-speed desktop market practically on equal.


This processor was very successful, and Intel got him represented by a decent opponent in the field of high-performance systems. Today, the success of the Athlon processor does not cause doubt, but during his release to the market for this account there were concerns. The fact is that, in contrast to its predecessor, the K6, which was compatible both on the software and the hardware level with the Intel processor, Athlon was compatible only at the software level - it required a specific set of microcircuits of system logic and a special socket.

New AMD processors were produced in 250-nm technology with 22 million transistors. They have a new unit of integer calculations (ALU). The EV6 system bus provided data transmission on both fronts of the clock signal, which made it possible at a physical frequency of 100 megahertz to obtain an effective frequency of 200 megaggers. The amount of the first level cache was 128 KB (64 Kb of instructions and 64 kb of data). The second level cache reached 512 KB.

The year 2000 was marked by the emergence of new developments of both companies in the market. On March 6, 2000, AMD released the world's first processor with a clock frequency of 1 GHz. It was a representative of the popularity of the Athlon family at the Orion Core. Also, AMD first introduced the Athlon Thunderbird and Duron processors. The DURON processor, essentially, was identical to the Athlon processor and differ from it only the smaller volume of the second level cache. Thunderbird, in turn, used integrated cache, which made it possible to increase its speed. Duron was a cheaper version of the Athlon processor, which was designed primarily in order to make a worthy competition in low-cost Celeron processors. And Intel at the end of the year introduced a new Pentium 4 processor.

In 2001, Intel has released a new version of the Pentium 4 processor with a working frequency of 2 GHz, which became the first processor reached such frequency. In addition, AMD introduced the Athlon XP processor created on the basis of the Palomino kernel, as well as the Athlon MP, designed specifically for multiprocessor server systems. During 2001, AMD and Intel continued to work on improving the performance of the microcircuits being developed and improving the parameters of existing processors.

In 2002, Intel introduced the Pentium 4 processor, which first reached the operating frequency of 3.06 GHz. Following processors for it will also support Hyper-Threading technology. The simultaneous execution of two streams is given for processors with Hyper-Threading technology. Performance growth in 25-40% compared to conventional Pentium 4. This inspired programmers to develop multi-threaded programs, and prepared soil for the emergence of multi-core processors.

In 2003, AMD released the first 64-bit ATHLON 64 processor (Clawhammer code name, or K8).

Unlike server 64-bit ITANIUM and Itanium 2 processors optimized for the new 64-bit architecture of software systems and quite slowly working with traditional 32-bit programs, Athlon 64 embodies the 64-bit expansion of the X86 family. After some time, Intel presented its own set of 64-bit extensions, which called EM64T or IA-32E. Intel extensions were almost identical to AMD extensions, which meant their compatibility at the program level. Until now, some operating systems call them AMD64, although in marketing documents, competitors prefer their own brands.

In the same year, Intel produces the first processor in which the third-level cache - Pentium 4 Extreme Edition was implemented. It was built in 2 MB of cache, the number of transistors was significantly increased and as a result - performance. The Pentium M microcircuit also appeared for laptop computers. She thought as an integral part of the new Centrino architecture, which was supposed to reduce power consumption, thereby increasing the battery resource, secondly, to ensure the possibility of producing more compact and lung buildings.

In order for the 64-bit calculations to become a reality, 64-bit operating systems and drivers are required. In April 2005, Microsoft began to distribute the trial version of Windows XP Professional X64 Edition supporting additional AMD64 and EM64T instructions.

Not driving turnover, AMD in 2004 produces the world's first dual-core X86-core Athlon 64 x2.

At that time, very few applications could use two cores simultaneously, but in a specialized productivity gains was very impressive.

In November 2004, Intel was forced to cancel the release of the Pentium 4 model with a clock frequency of 4 GHz due to heat sink problems.

On May 25, 2005, Intel Pentium D processors were first demonstrated. There is nothing to say about them, except that only about heat dissipation in 130 W.

In 2006, AMD represents the world's first 4-nuclear server processor, where all 4 cores are grown on one crystal, and not "glued" from two, like a business colleague. Solved the most complex engineering tasks - and at the stage of development, and in production.

In the same year, Intel changed the name of the Pentium brand on Core and released the Core 2 Duo dual-core chip.

Unlike the NetBurst architecture processors (Pentium 4 and Pentium D), in the Core 2 architecture, the rate was not made to increase the clock frequency, but to improve other processor parameters, such as cache, efficiency and number of cores. The dispersion capacity of these processors was significantly lower than that of the desktop Pentium. With the TDP parameter, equal to 65 W, the Core 2 processor had the smallest dispel power from all available then on the sale of desktop microprocessors, including on the PRESCOTT kernels (Intel) with TDP equal to 130 W, and on SAN DIEGO (AMD) cores with TDP equal 89 W.

The first desktop quad-core processor was the Intel Core 2 Extreme QX6700 with a clock frequency of 2.67 GHz and 8 MB of second-level cache.

In 2007, the 45-nanometer microarchitecture of Penryn was published using HI-K metal shutters without lead. The technology was used in the Intel Core 2 DUO processor family. Support for SSE4 instructions was added to the architecture, and the maximum amount of 2-level cache in dual-core processors increased from 4 MB to 6 MB.

In 2008, the next generation architecture was published - Nehalem. Processors acquired a built-in memory controller supporting 2 or 3 channels DDR3 SDRAM or 4 FB-DIMM channel. A new QPI bus arrived at the FSB bus. The volume of the 2nd level cache reduced to 256 KB per each kernel.

Soon Intel translated Nehalem architecture to the new 32-nm technical process. This line of processors was named Westmere.

The first model of the new microarchitecture was Clarkdale, which possesses two nuclei and an integrated graphics core produced in 45-nm technical process.

AMD tried to keep up with Intel. In 2007, she released a new generation of microprocessor architecture X86 - Phenom (K10).

Four cores of the processor were combined on one crystal. In addition to the Cache of the 1st and 2nd levels of the model, the K10 finally received L3 of 2 MB. The amount of data cache and level of level 1 was 64 KB each, and the 2nd level cache - 512 KB. Also appeared promising support for the DDR3 memory controller. In K10, two 64-bit controllers were used. Each processor kernel had a 128-bit floating point calculation module. In addition to all, new processors have worked through the Hypertransport 3.0 interface.

In 2009, many years of conflict was completed between Intel and AMD corporations related to patent law and antimonopoly legislation. So, for almost ten years, Intel used a number of dishonest decisions and receptions that prevented the fair development of competition in the semiconductor market. Intel put pressure on his partners, forcing them to abandon the acquisition of AMD processors. Customer bribing was used, providing large discounts and conclusion of agreements. As a result, Intel paid AMD 1.25 billion dollars and pledged to follow a certain set of business activities of the following 5 years.

By 2011, the Athlon Epoch and the competitive struggle in the processor market has already moved into some calm, but it lasted at all long ago - in January, Intel presented her new Sandy Bridge architecture, which became the ideological development of the first generation Core - the whole milestone that allowed Xeno Giant take leadership in the market. AMD fans waited for red answers for quite a long time - only in October the long-awaited Bulldozer appeared on the market - return to the AMD FX brand market associated with the proceedings for the company's early century processors.


The new AMD architecture has taken on a lot - confrontation with the best solutions of Intel (later legendary) expensive was expected to have a chipmeiker from Sannywil. Already traditional for red bloated marketing, associated with loud statements and incredible promises, moved all the boundaries - "Bulldozer" was called the real revolution, and predicted the architecture a worthless battle against new products from a competitor. What did FX prepare for victory in the market?

A bet on multithreading and uncompromising multi-core - in 2011, AMD FX was proudly called the "most multi-cuisine desktop processor in the market", and this was not an exaggeration - the architecture was based on as much as eight nuclei (albeit or logical), each of which had one stream. At the time of the announcement of the architecture, the new FX against the background of the four competitor centers was an innovative and bold decision, looking far ahead. But alas, AMD always made a bet only on one direction, and in the case of Bulldozer it was not the sphere that was calculated by the mass consumer.

The productivity of new AMD chips was very high, and in the synthetics FX easily showed impressive results - unfortunately it was impossible to say the same game loads: Fashion for 1-2 kernels and the lack of support for normal parallelization of the nuclei led to the fact that the "bulldozer" With a big creak coped with the loads where Sandy Bridge did not even feel difficulties. To add two achilles stages of the series to this whole - dependence on fast memory and rudimentary northern bridge, as well as the presence of only one FPU block for every two cores - and the result comes out very deplorable. AMD FX was called hot and a harsh alternative to fast and powerful blue processors, which took only relative cheap and compatibility with old motherboards. At first glance, it was a complete failure, however AMD never squeaked to work on errors - and it was the work that Vishera became a kind of reboot of the Bulldozer architecture, which came to the market at the end of 2012.

The updated Bulldozer was called Piledriver, and the architecture itself added in the instructions, increased muscles in single-flow loads, and optimized the work of a large number of nuclei, which increased and multi-threaded performance. However, in those days, the competitor for the updated and extended series of reds was the most dismantling Ivy Bridge, only the incredant number of Intel adolers. The AMD decided to act on the already running strategy to attract budgetary users, total savings on components and opportunities to get more for less money (without encroaching on the segment above).

But the most funny in the history of the appearance of the most unsuccessful (according to the majority) architecture in Arsenal AMD is that AMD FX sales are difficult to call not that failed, but even mediocre - so, according to the Newegg store for 2016, AMD FX became the second in popularity of the processor -6300 (giving way only i7 6700K), and the notorious leader of the budget red segment FX-8350 entered the top five best-selling processors, a little rested from i7 4790K. At the same time, even relatively cheap I5, which was given as an example of marketing success and the "folk" status, were significantly lagging behind the tested oldriver older times.

Finally, it is worth noting a rather funny fact that a few years ago was considered an exclusion of AMD fans - we are talking about the confrontation of the FX-8350 and I5 2500K, which originated during the Bulldozer output. For a long time it was believed that the red processor is significantly lagging behind the 2500K challenged with many enthusiasts, but in the latest 2017 tests in a pair with the most powerful GPU FX-8350, it turns out faster in almost all game tests. It will be appropriate to say "Hurray, waited!".

And inten, meanwhile, continues to win the market.

In 2011, the party of new processors on the architecture of Sandy Bridge is announced, and then a few later, for the new year of LGA 1155 socket. This is the second generation of Intel modern processors, the full update of the ruler, which paved the road commercial success for the company, because There were no analogues for the core and acceleration. Perhaps you remember the i5 2500K - the legendary processor, it accelerated to the frequency of almost 5 GHz, with appropriate tower cooling, and is capable of even today, in 2017, to ensure acceptable performance in the system with one, and possibly two video cards in modern games. At the HWBOT.ORG resource, the processor overcame the frequency of 6014.1 megahertz from the Russian Overclocker SAV. It was 4 nuclear processor with a level of level 3 in 6 MB, the base frequency was only 3.3 GHz, nothing special, but at the expense of solder, the processors of this generation accelerated very much and did not have overheating. It is also absolutely successful in this generation were i7 2600K and 2700K - 4 nuclear processors with hyperterentine, which gave them as many as 8 streams. They accelerated, however, they are a little weaker, but had a higher productivity, and accordingly the heat dissipation. They were taken under systems for quick and efficient video editing, as well as for broadcasts on the Internet. What is interesting, 2600K like I5 2500K also use not only gamers today, but also streamers. It can be said that this generation has become a popular treasure, since everyone wanted exactly the processors from Intel, which affected their price, not to the best for the consumer.

In the 2012 Intel launches 3 generation of processors, called Ivy Bridge, which looks strange, because only a year passed, did they be able to invent something fundamentally new, which would give a tangible performance increase? As if, a new generation of processors, everything is based on the same socket - LGA 1155, and the processors of this generation are not strongly ahead of the previous ones, this is due, of course, with the fact that there were no competition in the top segment. All the same AMD, not to say that it would be tightly breathing in the back of the first, because Intel could afford to produce processors a little more powerful than their own, because in fact became monopolists in the market. But here it crept on another trick, now in the form of a thermal interface under the lid, Intel was not solder, but some kind of their own, as nicknamed - a chewing, made it was for saving, which brought even more income. This topic simply blew up the network, it was no longer possible to accelerate the processors under the string, because they received an average temperature of 10 degrees more than previous ones, because the frequencies came closer to the border of 4-4.2 GHz. Special extremals even opened the processor cover, in order to replace the thermal paste to more efficiently, do it without a crystal crystal or damage to the processor contacts were not possible, but the method turned out to be effective. Nevertheless, I can identify some processors that enjoyed success.

Perhaps you noticed that I did not mention I3, when a story about the second generation, this is due to the fact that processors of such power were not particularly popular. Everyone always wanted i5, who had money taken of course I7.

In the 3rd generation, about which we will talk now, the situation has not changed dramatically.
Successful among this generation, you can select i5 3340 and i5 3570k, they did not differ in performance, everything was resting in the frequency, the cache was all the same - 6 MB, 3340 did not have the possibility of overclocking, because 3570k was desirable, but that one thing is that The second - provided good performance in games. From i7 to 1155, it was the only 3770 with an index to with an 8 MB cache and a frequency of 3.5-3.9 GHz. In the boosy, it was usually accelerated to 4.2 - 4.5 GHz. Interestingly, in the same 2011, the new LGA 2011 socket was released, for which two super-processors I7 4820K (4 kernels, 8 threads, with L3 cache - 10 MB) and I7 4930K (6 cores, 12 streams, L3 cache was released. It is equal to 12 MB) that it was for Monsters - to say difficult, such a percentage cost 1000 bucks and was the dream of many schoolchildren at the time, although for games, of course, he was too powerful, more consistent under professional tasks.

In 2013, Haswell comes out, yes, yes, another year, another generation, according to tradition, a little more powerful than the previous one, because AMD could not again. It is known as the hottest generation. However, the i5 of this generation was pretty successful. It is connected with that, in my opinion, that the guys with "Sendika" were running to change their own, as they thought, outdated processes to the new "revolution" from Intel, where all the "Internet" were burning. Processors have accelerated even worse than the previous generation, which is why many still dislike this generation. The productivity of this generation was slightly higher than the previous one (percent on 15, which is not much, but the monopoly does its job), and the disagreement restriction is a good option for Intel to give less "free" performance to the user.

All I5 th traditions were without hypertension. We worked at a frequency of 3 to 3.9 GHz in the booster, you could take anyone with the index "K", as it guaranteed good performance, even with not very high acceleration. I7 here was at first only one, it is 4770k - 4 cores 8 flows, 3.5 - 3.9 GHz, a workhorse, but heats up without good cooling very much, I will not say that it was popular with scalpers, but people who scalped the lid, It is said that the result is much better, on the water takes about 5 gigahertz, if lucky. It concerned any processor since the Sendika. However, this is not an end, in this generation there was such a Xeon E3-1231v3, which, in fact, was the same I7 4770, only without integrated graphics and acceleration. Interesting what was inserted into an ordinary mother with a socket 1150 and cost much cheaper Ay seventh. A little later, I7 4790K comes out and it has an already improved thermal interface, but it is still not that solder that was before. However, the processor accelerates more than 4770. Even the cases of overclocking of 4.7 GHz in the air, of course on good cooling.

Also there are "Monsters" of this generation (Haswell-E): I7-5960x Extreme Edition, I7-5930K and 5820K, adapted under the desktop market, server solutions. These were the most stuffing on the most bad processors at that time. They are based on the new 2011 V3 socket and stand a bunch of money, but also the performance of them is exceptional, which is not wise, because the senior processor is in the range of as 16 streams and 20 MB cache. Pick the jaw and go on.

In 2015, Skylake comes out, on a socket 1151 and everything would have nothing like almost the same performance, but this generation differs from all the previous ones: first, the reduced dimensions of the heat dissipation cover, for improved heat exchange with the cooling system on the processor, secondly, DDR4 memory support and DirectX 12, Open GL 4.4 software support, OPEN Cl 2.0, which indicates better performance in modern games that will be used by these APUs. It also turned out that even processors without an index k can be accessed, it was done using the memory bus, but this case was quickly covered. Whether this method works through crutches - we are not known.

Processors here were a bit, Intel again improved the business model, why produce 6 processors, if 3-4 are popular from the entire line? So we will produce 4 medium-sized processors and 2 expensive segments. Personally, according to my observations, most often take i5 6500 or 6600K, all the same 4 kernels with 6 MB cache and turbo bush.

In 2016, Intel introduced the fifth generation of processors - Broadwell-E. Core i7-6950x was the first desktop ten-fold processor in the world. The price of such a processor at the time of the start of sales was 1723 dollars. Many seemed very strange such a move from Intel.

On March 2, 2017, new processors of the older line of AMD Ryzen 7 were on sale, which included 3 models: 1800x, 1700x and 1700. As you already know, on February 22 this year, the official presentation of Ryzen was held, on which Liza Su stated that Engineers exceeded the outlook 40%. In fact, Ryzen is 52% ahead of Excavator, and taking into account the fact that over six months has passed since the start of sales of Ryzen, the release of new BIOS updates that increase productivity and fisze small bugs in the Zen architecture can be said that this figure has grown to 60% . Today, the eldest Ryzen is the fastest eight-core processor in the world. And here it was confirmed another assumption. What about the ten-fold Intel. In fact, it was the real and only answer Ryzen. Intel stole a victory in advance from AMD, said that you would not have released there, the fastest processor will remain with us in any case. And then at the presentation of Lisa Su, I could not name Ryzen with an absolute champion, and just the best of eight-core. Such a thin trolling from Intel.

Now AMD and Intel are new flagship processors. AMD is Ryzen Threadripper, Intel - Core i9. The price of eighteen nuclear thirty-six-sixth flagship Intel Core i9-7980xe is about two thousand dollars. The price of sixteen nuclear thirty-two-fold Intel Core i9-7960X is $ 1,700, while at a similar sixteen nuclear thirty-two-flow AMD Ryzen ThreadRipper 1950x price is about a thousand dollars. Do reasonable conclusions yourself, gentlemen.

Video on this material.

Today we will talk about the history of one company, without which most computers in the world just did not work. We will discuss, naturally, about the company Intel.

Intel was born in the heads of Robert Neuss and Gordon Moore, when they also worked in Fairchild Semiconductor in the 60s. The company in those years was a leading manufacturer of analog integrated circuits, but not everything went smoothly: new leadership came and began to limit the freedom of scientists and employees of the company. Therefore, in 1968, Neuss and Moore left Fairchild Semiconductor and subsequently founded their company, which influenced the whole world.

Robert Neus (left) and Gordon Moore

Along with Fairchild Semiconductor, Moore and Neuss began working on a future business plan. The company was named Neuss and Moore Electronics, abbreviated by NM Electronics. Moore was not fully confident in the title, and at the next version of Integrated Electronics, proposed by Murom, Neus saw the abbreviated name Int.egrated El.ectronics (Intel), and it is with the same name on July 16, 1968, Robert Neus and Gordon Moore registered the company. After registering Intel, it turned out that there is a company with a similar name Intelco, and Intel had to pay $ 15,000 to freely use their name. Having received a loan of $ 2.5 million from financiers, Intel hired his first employee Andrew Growv and began his way into the world of electronics.

The company immediately chose, as history shows, the correct production vector - electronic memory schemes. It was at the production of RAM Intel earned the first solid money. Having a good capital, the company began to experiment with new products, and all this resulted in the fact that in 1971 the company produces its first commercial microprocessor Intel 4004. "A New Era of Integrated Electronics" - said intel to the whole world. It was a full-fledged 4-bit microprocessor, which contains everything you need to work. It was designed by order of one Japanese company specifically for its calculators. According to the contract, the rights to the production of the processor were to move Japanese. It was at this time that Intel began to understand which prospects in the future will open before the microprocessor. Fortunately, Gordon Mouur and Robert Neusu is just lucky. The Japanese company experienced serious financial problems and therefore decided to go to the new contract with Intel. Under the terms of this agreement, the American company pledged to supply his microprocessors to Japan at a price of two times less than the declared initially. But all rights to develop remained for Intel.

Gradually, microprocessors of the company began to appear not only in traffic lights and calculators, but also in the first personal computers. All this led to the fact that the 8080 processor has appeared on the light, which has become the standard of the industry at that time. It was installed even in such a popular computer at that time as Altair 8800, and after only three years, the company will present the first 16-bit 8086 processor.

Intel grew very quickly. In 1968, the company had only 12 employees, and by 1980 they had a total of 15 thousand! Naturally, such an increase demanded enough careful management. And Neuss with Murom understood it perfectly well. They were just the people who could not endure bureaucracy. They were enough for them in Fairchild Semiconductor. At first, the founders arranged weekly lunches with employees, then with the growth of the company, Intel always remained open to his employees. Each employee to some extent made decisions on this or that matter. And the right approach to the management of the company and the vector of its products led to the fact that in 1983 Intel's income was a whole $ 1 billion.

Since the 80s, Intel takes himself in hand and closes all different minor development to fully focus on the production of microprocessors. Next will come golden times 286s, then 386 and, in the end, 486-computers equipped with Intel processors. But even after all these successes, Intel will continue to remain a company that is not a well-known in the circle of people. Yes, they will speak about it in the circles of IT professionals, but here that of simple users can be wondering what kind of processor is located in their computer?

Apparently, Intel was important that all people on the planet knew this company, and they did so that a company that no one knew at the very beginning of the 90s could become one of the most famous brands at the beginning of the XXI century. According to some ratings, Intel is among the top ten of the most famous brands. The thing is that since the 90s Intel, the Intel began a campaign on the inmpirDing, which has already entered many marketing textbooks. Intel has spent hundreds of millions of dollars on this campaign. The essence of the company's branding was that in advertising of ordinary personal computers constantly mentioned the fact that they work on the Intel processor (Naturally, advertising of these computers was paid among other things). In addition, Intel very actively used television advertising, driven into the mass consciousness, which must be sure to make sure that the computer works on the Intel processor.

In October 1992, Intel announced that the processors of the fifth generation, previously carrying the code name P5, will be called Pentium, and not 586, as many people assumed. This was due to the fact that many firms producing processors actively mastered the production of "clones" (and not only) processors 486. Intel was going to register the name "586" as a trademark, so that no one could exercise the production of processors with such a name. But it's not enough: it turned out that it was impossible to register numbers as a trademark (to the huge regret Intel), therefore it was decided to name new Pentium processors. On March 22, 1993, a presentation of the new microprocessor was held, after a few months the first computers appeared on their basis. And this processor literally conquered the whole world. He stood in all computers, and many people around the world demanded a computer with the Pentium processor.

In the late 90s, Intel faced the most serious competition in his entire history. All the same AMD produced at that time excellent processors, which also cost significantly less than Intel's. But 2006 Intel bit off a big piece of cake. For a long time, Apple Macintosh computers are supplied with processors, and then IBM. And with just 2006, all MACs are now operating under the control of Intel processors. At the time, when Apple from 2006 to 2007 passed to the Intel architecture, Intel itself had a whole line of processors for different segments of devices. "Selerona", "Pentiums", "Kseona" - each processor was intended for their needs: if "Kseona" were for professional machines and servers, then Selerons put in very budget systems.

In the same, as it seems, in the distant 2006, Intel has released an equally well-known processor called Core 2 Duo, we all know them, and many still stand on cottages with a heart of Core 2 Duo. And in mid-2009, Intel conducted restructuring of the product line of its processors, thereby created the Core I family in which we already include all the well-known Core I7, I5 and I3. At the moment, about 85% of modern computers and laptops are running the Intel Core I processor family. The rest are either working on Pentium and Celeron processors, or on competitor processors.

Now the company, in addition to processors, also produces solid-state drives, motherboards and components for servers. The company does not cease to experiment with modern technologies and even recently installed a record for the number of managed drone drifts. Intel specialists launched a hundred quadrocopters with LED elements that were used as a light-music system. Drones depict color figures in the air, accompanying the orchestra who plays Beethoven. In general, we hope that Intel, as well as the past 50 years, will determine the future in computer technologies and successfully develop the computer industry and thus all humanity as a whole.