How Do Microprocessors Work?

A microprocessor is a central processing unit composed of one or a few large-scale integrated circuits. These circuits perform the functions of a control unit and an arithmetic logic unit.

The microprocessor can complete instructions fetching, executing instructions, and exchanging information with external memory and logic components. It is the operation control part of the microcomputer. It can form a microcomputer with memory and peripheral circuit chips.

Chinese name: microprocessor
Foreign name: Microprocessor

Meaning: Computing core and control core of computer
Alias: CPU
Field: computer

Microprocessor Overview

Compared with the traditional CPU, the microprocessor has the advantages of small size, light weight and easy modularization. The basic components of a microprocessor are: a register file, an arithmetic unit, a timing control circuit, and a data and address bus.

Since mankind invented the transistor in 1947, semiconductor technology has gone through several generations such as silicon transistors, integrated circuits, very large scale integrated circuits, and very large scale integrated circuits for more than 50 years. The rapid development rate is unprecedented in other industries. Semiconductor technology has a wide-ranging impact on society as a whole, and is therefore called the "seed of the industry." The central processing unit is a component that processes data and controls the processing process inside the computer. With the rapid development of large-scale integrated circuit technology, the chip integration density is getting higher and higher, and the CPU can be integrated on a semiconductor chip. Large-scale integrated circuit devices with central processing unit functions are collectively referred to as "microprocessors". It should be noted that the microprocessor itself is not the same as the microcomputer, but the central processing unit of the microcomputer.

Microprocessors have become ubiquitous. Whether it is home appliances such as video recorders, smart washing machines, mobile phones, or automotive engine controls, as well as CNC machine tools and missile precision guidance, various types of microprocessors must be embedded. Microprocessor is not only the core component of microcomputer, but also the key component of various digital intelligent devices. International high-speed supercomputers, mainframe computers and other high-end computing systems are also built with a large number of general-purpose high-performance microprocessors. ^[1]

Microprocessor internal structure

The 16-bit microprocessor (8086 microprocessor in the figure) can be divided into two parts, one is the execution unit (EU), which is the part that executes instructions; the other is

microprocessor One part is the bus interface unit (BIU), which communicates with the 8086 bus and executes instructions fetched from memory. After the microprocessor is divided into EU and BIU, the operations of fetching and executing instructions can be overlapped. The EU part has a register file consisting of eight 16-bit registers that can be used to store data, index and stack pointers, arithmetic operation logic units (ALU) to perform arithmetic operations and logic operations, and flag registers to register the conditions of these operation results. These components in the execution unit transfer data via the data bus. The bus interface unit also has a register file, where CS, DS, SS, and ES are segment registers for memory space segmentation. IP is the instruction pointer. The internal communication register is also a register that temporarily stores data. The instruction queue stores the pre-fetched instruction stream. The bus interface unit also has an address adder that adds the segment register value and the offset value to obtain a 20-bit physical address. Data and address are connected to the external 8086 system bus through bus control logic. The 8086 has a 16-bit data bus. When the processor transfers data off-chip, it transfers 16-bit binary numbers in one class. 8086 has a primary pipeline structure, which can achieve the overlap of on-chip operations and off-chip operations. ^[2]

Classification of microprocessors

American Intel Corporation According to the application fields of microprocessors, microprocessors can be roughly divided into three categories: general-purpose high-performance microprocessors, embedded microprocessors and digital signal processors, and microcontrollers. Generally speaking, general-purpose processors pursue high performance. They are used to run general-purpose software and are equipped with a complete and complex operating system. Embedded microprocessors emphasize high-performance for handling specific application problems. They are mainly used to run special-purpose programs for specific fields. Equipped with a lightweight operating system, mainly used in consumer electronics such as cellular phones and CD players; microcontrollers are relatively low-priced and have the largest demand in the microprocessor market, mainly used in automotive, air-conditioning, automatic machinery and other fields Automatic control equipment.
CPU is the abbreviation of Central Processing Unit (Central Processing Unit). It is the most important part of a computer and consists of a processor and a controller. If you compare a computer to a human, then the CPU is the human brain. The development of the CPU is very rapid. It took only 21 years for the personal computer to develop from 8088 (XT) to the era of Pentium 4.

Microprocessor development

The CPU has been in development for more than 20 years since its initial development. During this period, according to the word length of the information it processes, the CPU can be divided into: 4-bit microprocessor, 8-bit microprocessor, 16-bit microprocessor, 32 Bit microprocessor and the latest 64-bit microprocessor, it can be said that the development of personal computers is advancing with the development of CPU. Microcomputer refers to a large-scale, ultra-large-scale integrated circuit as the main component, and a microprocessor (Micro Processor) that integrates the main components of the computerthe controller and the computing unit as the core. Development, the development of microprocessors can be roughly divided into:

microprocessor

Microprocessor first generation

The first stage

(1971-1973) is usually a 4-bit or 8-bit microprocessor, typically the US Intel 4004 and Intel 8008 microprocessors. Intel 4004 is a 4-bit microprocessor that can perform 4-bit binary parallel operations. It has 45 instructions and a speed of 0.05 MIPs (Million Instruction Per Second, million instructions per second). Intel 4004 has limited functions. It is mainly used in household appliances such as calculators, electric typewriters, cameras, scales, and televisions to make these electrical appliances intelligent, thereby improving their performance. Intel 8008 is the world's first 8-bit microprocessor. The memory uses a PMOS process. At this stage, the computer works slowly, the microprocessor's instruction system is incomplete, the memory capacity is very small, only a few hundred bytes, there is no operating system, only assembly language. Mainly used in industrial instrumentation and process control.

Microprocessor second generation

(1974-1977) Typical microprocessors are Intel 8080/8085, Z80 from Zilog and M6800 from Motorola. Compared with the first-generation microprocessor, the integration level is increased by 1 to 4 times, the operation speed is increased by 10 to 15 times, the instruction system is relatively complete, and it has the typical computer architecture and interrupt, direct memory access and other functions .

Because microprocessors can be used to perform many computational tasks that previously required larger equipment, and the price is cheap, semiconductor companies have begun competing to produce microprocessor chips. Zilog produced the 8080 enhanced Z80, Motorola produced 6800, and Intel produced the enhanced 8085 in 1976, but these chips basically did not change the basic characteristics of the 8080 and belong to the second-generation microprocessor. They all use NMOS technology, the integration degree is about 9,000 transistors, the average instruction execution time is 1 S ~ 2 S, using assembly language, BASIC, Fortran programming, using a single user operating system.

Microprocessor third generation

The third stage (1978-1984) was a 16-bit microprocessor. In 1978, Intel Corporation first introduced the 16-bit microprocessor 8086. At the same time, in order to facilitate the original 8-bit users, Intel also proposed a quasi-16-bit microprocessor 8088.

The 8086 microprocessor has a maximum clock speed of 8MHz, a 16-bit data channel, and a memory addressing capability of 1MB. At the same time, Intel has also produced a mathematical coprocessor i8087, which is compatible with each other. These two chips use mutually compatible instruction sets, but the i8087 instruction set adds some instructions dedicated to mathematical calculations such as logarithms, exponents and trigonometric functions. These instruction sets are collectively referred to as the x86 instruction set. Although Intel has successively produced more advanced and faster new CPUs such as the second and third generations, they are still compatible with the original x86 instructions, and Intel uses the original x86 sequence in the naming of subsequent CPUs until later Due to trademark registration issues, they abandoned the use of Arabic numerals.

In 1979, Intel Corporation developed the 8088. The 8086 and 8088 both use 16-bit data transmission inside the chip, so they are both called 16-bit microprocessors. However, the 8086 can transmit or receive 16-bit data per cycle, and the 8088 per cycle Only 8 bits are used. Because most of the original devices and chips were 8-bit, the 8088's external 8-bit data transmission and reception can be compatible with these devices. The 8088 is packaged in a 40-pin DIP and operates at 6.66MHz, 7.16MHz, or 8MHz. The microprocessor integrates approximately 29,000 transistors.

After Intel Corporation introduced 8086 and 8088 CPUs, various companies have also launched similar products, such as Zilog Z8000 and Motorola M68000. The 16-bit microprocessor has a larger addressing space, stronger computing power, faster processing speed and a more complete instruction system than the 8-bit microprocessor. Therefore, 16-bit microprocessors have been able to replace some of the functions of minicomputers. Especially in single-task, single-user systems, 16-bit microprocessors such as 8086 have been widely used.

In 1981, the American IBM Corporation used the 8088 chip in the IBM-PC machine it developed, thus creating a new era of microcomputers. It was also from 8088 that the concept of the personal computer (PC) began to develop around the world. From the 8088 application to the IBM PC, the personal computer has truly entered people's work and life, and it also marks the beginning of a new era.

In 1982, Intel Corporation developed the 80286 microprocessor based on the 8086. The maximum frequency of the microprocessor is 20MHz. Both internal and external data transmission are 16-bits. Using 24-bit internal memory addressing, memory The addressing capacity is 16MB. 80286 can work in two ways, one is called real mode, the other is called protection mode.

In real mode, the total amount of memory that the microprocessor can access is limited to 1 megabyte; in protected mode, the 80286 can directly access 16 megabytes of memory. In addition, 80286 works under protection mode, which can protect the operating system from unprotected microprocessors such as real mode or 8086, which will stop the system when it encounters abnormal applications.

The use of the 80286 microprocessor by IBM in advanced technology microcomputers, namely AT machines, has caused a great sensation. 80286 has significant improvements over its predecessors in the following four aspects: support for larger memory; ability to simulate memory space; ability to run multiple tasks simultaneously; and improved processing speed.

The speed of the earliest PC was 4MHz, and the first 80286-based AT machine operated at 6MHz to 8MHz. Some manufacturers also increased the speed by themselves, so that the 80286 reached 20MHz, which means a significant improvement in performance.

The 80286 package is a square package called PGA. PGA is an inexpensive package derived from PLCC. It has an internal and external solid pin. In this package, 80286 integrates about 130,000 transistors.

The bus of the IBM PC / AT microcomputer maintains the three-layer bus structure of XT, and adds high- and low-order byte bus driver conversion logic and high-order byte bus. Like the XT machine, the CPU is soldered to the motherboard.

Microprocessor fourth generation

The fourth stage (1985-1992) is a 32-bit microprocessor. On October 17, 1985, Intel s landmark product, the 80386DX, was officially released. It contained 275,000 transistors and a clock frequency of 12.5MHz. It was gradually increased to 20MHz, 25MHz, and 33MHz, and finally a small number of 40MHz products.

The internal and external data buses of the 80386DX are 32 bits, and the address bus is also 32 bits. It can address 4GB of memory and can manage 64TB of virtual storage space. In addition to its real mode and protected mode, its calculation mode also adds a "virtual 86" working mode, which can provide multiple tasks by simulating multiple 8086 microprocessors at the same time.

The 80386DX has more instructions than the 80286. The 80386 with a frequency of 12.5MHz can execute 6 million instructions per second, which is 2.2 times faster than the 80286 with a frequency of 16MHz. The most classic product of 80386 is 80386DX-33MHz. Generally speaking, 80386 refers to it.

Due to the powerful computing capabilities of 32-bit microprocessors, the application of PCs has expanded to many fields, such as commercial office and computing, engineering design and computing, data centers, and personal entertainment. 80386 makes 32-bit CPUs the standard in the PC industry.

In 1989, Intel introduced the 80386SX, a quasi-32-bit microprocessor chip. This is a cheaper popular CPU introduced by Intel in order to expand market share. Its internal data bus is 32-bit and the external data bus is 16-bit. It can accept 16-bit input / output interface chips developed for 80286. Reduce overall machine costs. After the launch of the 80386SX, it has been widely welcomed by the market, because the performance of the 80386SX is much better than the 80286, and the price is only one-third of the 80386.

In 1989, the 80486 chip that we all know well was launched by Intel. The great thing about this four-year-developed and $ 300 million-funded chip is that it has for the first time broken the boundaries of 1 million transistors, integrated 1.2 million transistors, and used a 1-micron manufacturing process. The clock frequency of the 80486 has gradually increased from 25MHz to 33MHz, 40MHz, and 50MHz.

80486 is a chip that integrates 80386 and math coprocessor 80387 and an 8KB cache. The integrated digital speed of the 80487 in the 80486 is twice that of the previous 80387. The internal cache shortens the waiting time of the microprocessor and slow DRAM. And, for the first time in the 80x86 series, RISC (Reduced Instruction Set) technology is used, which can execute an instruction in one clock cycle. It also uses the burst bus method, which greatly improves the speed of data exchange with memory. Because of these improvements, the performance of the 80486 is four times better than the performance of the 80386 DX with the 80387 math coprocessor.

Microprocessor fifth generation

Phase 5 (1993-2005) was the era of the Pentium series of microprocessors, often referred to as the 5th generation. Typical products are Intel's Pentium series chips and AMD's compatible K6 series microprocessor chips. It uses a superscalar instruction pipeline structure internally and has independent instruction and data caches. With the emergence of MMX (MultiMediaeXtended) microprocessors, the development of microcomputers has reached a higher level in terms of networking, multimedia and intelligence.

The early Pentium 75MHz to 120MHz used a 0.5 micron manufacturing process, and later Pentiums with frequencies above 120MHz switched to a 0.35 micron process. The performance of the classic Pentium is fairly average, and both integer and floating-point arithmetic are good. In order to improve the computer's ability to apply multimedia and 3D graphics, many new instruction sets have emerged. The three most famous ones are Intel's MMX, SSE, and AMD's 3D NOW !. MMX (MultiMedia Extensions) is a multimedia instruction enhancement technology invented by Intel in 1996. It includes 57 multimedia instructions. These instructions can process multiple data at one time. With the cooperation of software, MMX technology can obtain Better performance.

The official name of Pentium MMX is "Pentium with MMX technology", which was released at the end of 1996. Since Pentium Pentium started, Intel has started to lock the multiplier of its CPU, but MMX's CPU has a very strong overclocking capability, and it can also be overclocked by increasing the core voltage. Action. The word overclocking has also become popular since then.

Versatile Pentium is another successful product of Intel after Pentium, and its vitality is also quite tenacious. Duo Pentium has made major improvements on the basis of the original Pentium, adding on-chip 16KB data cache and 16KB instruction cache, 4-way write cache, branch prediction unit and return stack technology. In particular, the newly added 57 MMX multimedia instructions make Multi-Pentium even faster than Pentium CPUs with the same frequency even when running non-MMX optimized programs.

Launched in 1997, the Pentium II processor combines Intel MMX technology, which can process movies, sound effects, and graphics data with extremely high efficiency. For the first time, it uses a Single Edge Contact (SEC) box package with built-in high-speed cache memory. This chip allows computer users to capture, edit, and share digital photos with friends and family over the Internet, edit and add text, make music or make transitions for home movies, use video calls, and connect to the Internet through standard phone lines The video is transmitted over the network. The number of Intel Pentium II processor transistors is 7.5 million.

The Pentium III processor adds 70 new instructions and adds an Internet streaming SIMD extension called MMX, which can greatly improve the performance of advanced imaging, 3D, streaming music, video, speech recognition and other applications. It can greatly improve the performance of the Internet. Using experience, users can browse realistic online museums and stores, and download high-quality videos. Intel introduced 0.25 micron technology for the first time. The number of Intel Pentium III transistors is about 9.5 million.

In the same year, Intel also released the Pentium III Xeon processor. As the successor of the Pentium II Xeon, in addition to adopting a new design on the core architecture, it also inherited the 70 new instruction sets of the Pentium III processor to better execute multimedia and streaming media applications. In addition to facing the enterprise-grade market, Pentium III Xeon strengthens e-commerce applications and advanced business computing capabilities. There have also been many advances in cache speed and system bus structure, which have greatly improved performance and are designed for better multiprocessor collaboration.

The Pentium 4 processor launched in 2000 had 42 million transistors built-in and a 0.18 micron circuit. The initial version of the Pentium 4 was as fast as 1.5 GHz and the number of transistors was about 42 million. In August of the following year, the Pentium 4 processed To reach the 2 GHz milestone. In 2002, Intel introduced the new Intel Pentium 4 processor with innovative Hyper-Threading (HT) technology. Hyper-Threading technology creates a new class of high-performance desktop computers that can execute multiple computing applications quickly, or bring higher performance to software that supports multiple threads. Hyper-Threading technology increases computer performance by 25%. In addition to providing hyper-threading technology for desktop users, Intel has also reached another computer milestone by introducing the Pentium 4 processor, which operates at 3.06 GHz. It is the first commercial microcomputer to perform 3 billion computing cycles per second. The processor, such excellent performance, is attributed to the industry's most advanced 0.13 micron process technology at the time. The Intel Pentium 4 processor with built-in hyper-threading technology reached 3.2 GHz in the following year.

PentiumM: A new mobile CPU specially designed by the Israeli team. Pentium M is an Intel Corporation x86-based microprocessor for notebook personal computers. It was also introduced as part of Centrino in March 2003. The following main frequencies are announced: standard 1.6GHz, 1.5GHz, 1.4GHz, 1.3GHz, low voltage 1.1GHz, ultra-low voltage 900MHz. In order to get high performance at low clock speeds, Banias has made optimizations to increase the number of instructions that can be executed per clock, and reduces the misprediction rate through advanced branch prediction. In addition, the most prominent improvement is that the L2 cache has been increased to 1MB (both P3-M and P4-M are only 512KB). It is estimated that most of the 77 million Banias transistors are used for this.

In addition, there are a series of designs related to reducing power consumption: enhanced Speedstep technology is essential, with multiple supply voltages and calculation frequencies, so that performance can better meet application needs.

Intelligent power distribution can centrally distribute system power where the processor needs and close idle applications; Mobile Voltage Positioning (MVPIV) technology can dynamically reduce voltage based on processor activity, thereby supporting lower thermal design power and smaller Shape design; 400MHz system bus with optimized power; Micro-opsfusion micro-operation instruction fusion technology, in the presence of multiple instructions that can be executed simultaneously, combine these instructions into one instruction to improve performance and power efficiency. Dedicated stack manager, using dedicated hardware that records internal operations, the processor can execute programs without interruption.

Banias' corresponding chipset is the 855 series. The 855 chipset consists of the Northbridge chip 855 and the Southbridge chip ICH4-M. The Northbridge chip is divided into 855PM (codename Odem) without a built-in graphics card and 855GM (codename Montara- GM), supports up to 2GB of DDR266 / 200 memory, AGP4X, USB2.0, two sets of ATA-100, AC97 audio and Modem. Among them, 855GM is optimized for 3D and display engine InternalClockGating. It can supply power to the 3D display engine only when needed, thereby reducing the power of the chipset.

In 2005, Intel launched dual-core processors including Pentium D and Pentium Extreme Edition. At the same time, it introduced the 945/955/965/975 chipset to support the newly launched dual-core processors. The two new dual-core processors produced by 90nm process The core processor uses an LGA 775 interface without pins, but the number of chip capacitors on the bottom of the processor has increased, and the arrangement has also changed.

The core code of the desktop platform, Smithfield, is officially named the Pentium D processor. In addition to getting rid of Arabic numerals and using English letters to represent this generation of dual-core processors, the letter D is also more reminiscent of Dual- The meaning of Core dual core.

Intel's dual-core architecture is more like a dual CPU platform, and the Pentium D processor continues to be produced using the Prescott architecture and 90nm production technology. The Pentium D core is actually composed of two independent 2 independent Prescott cores, each core has an independent 1MB L2 cache and execution unit, the two cores together have a total of 2MB, but because both cores in the processor have Independent cache, so the information in each secondary cache must be completely consistent; otherwise, operation errors will occur.

To solve this problem, Intel assigned the coordination between the two cores to an external MCH (Northbridge) chip. Although the data transmission and storage between the caches is not huge, it needs to be coordinated through an external MCH chip Processing will undoubtedly bring a certain delay to the overall processing speed, which will affect the overall performance of the processor.

Due to the Prescott core, the Pentium D also supports EM64T technology and XD bit security technology. It is worth mentioning that the Pentium D processor will not support Hyper-Threading technology. The reason is obvious: correctly distributing data flow and balancing computing tasks among multiple physical processors and multiple logical processors is not easy. For example, if an application requires two computing threads, it is clear that each thread corresponds to a physical core, but what if there are three computing threads? Therefore, in order to reduce the complexity of the dual-core Pentium D architecture, Intel decided to remove support for Hyper-Threading technology in the Pentium D for the mainstream market.

The same comes from Intel, and the differences in the names of the two dual-core processors of the Pentium D and Pentium Extreme Edition also indicate that the two processors are not the same in terms of specifications. The biggest difference between them is the support for Hyper-Threading technology. Pentium D does not support Hyper-Threading technology, and Pentium Extreme Edition does not have this limitation. With Hyper-Threading technology turned on, the dual-core Pentium Extreme Edition processor can emulate two other logical processors, which can be considered a quad-core system by the system.

The Pentium EE series are labeled with three digits in the form of Pentium EE8xx or 9xx, such as Pentium EE840, etc. The larger the number, the higher the specification or the more features it supports.

Pentium EE8x0: This is a Smithfield core, 1MB L2 cache per core, and 800MHz FSB. The only difference from the Pentium D8x0 series is only the addition of support for hyper-threading technology. In addition, other technical features and parameters are completely the same.

Pentium EE9x5: indicates that this is a Presler core, 2MB L2 cache per core, and 1066MHz FSB. The only difference from the Pentium D9x0 series is the addition of support for hyper-threading technology and the improvement of the front-side bus to 1066 MHz FSB. Other technologies The characteristics and parameters are exactly the same.

Single-core Pentium 4, Pentium 4 EE, Celeron D, and dual-core Pentium D and Pentium EE CPUs are packaged in LGA775. Unlike the previous Socket 478 interface CPU, the LGA 775 interface CPU has no traditional pins at the bottom. Instead, it has 775 contacts, that is, not pin-type but contact-type. The stylus contacts to transmit the signal. The LGA 775 interface can not only effectively improve the signal strength and frequency of the processor, but also improve the yield of the processor and reduce production costs.

Microprocessor sixth generation

Phase 6 (2005-present) is the era of the core family of microprocessors, often referred to as the 6th generation. "Core" is a new energy-saving new micro-architecture. The starting point of the design is to provide outstanding performance and energy efficiency, improve performance per watt, which is the so-called energy efficiency ratio. Early Cores were based on notebook processors. Core 2: The English name is Core 2 Duo, which is a new generation of Core micro-architecture product system introduced by Intel in 2006. Published on July 27, 2006. Core 2 is a cross-platform architecture system, including server, desktop and mobile versions. Among them, the development code of the server version is Woodcrest, the development code of the desktop version is Conroe, and the development code of the mobile version is Merom.

The Core microarchitecture of the Core 2 processor is a new generation of Intel architecture improved by Intel's Israeli design team based on the Yonah microarchitecture. The most significant change is the enhancement in key parts. In order to improve the internal data exchange efficiency of the two cores, a shared second-level cache design is adopted, and the two cores share up to 4MB of second-level cache.

Following the LGA775 interface, Intel first introduced the LGA1366 platform, positioning the high-end flagship series. The first processor to use the LGA 1366 interface is codenamed Bloomfield, uses a modified Nehalem core, is based on a 45-nanometer process and a native quad-core design, and has a built-in 8-12MB L3 cache. The LGA1366 platform once again introduced Intel Hyper-Threading technology, while the QPI bus technology replaced the front-end bus design that has been used in the Pentium 4 era. The most important thing is that the LGA1366 platform is a platform that supports three-channel memory design, which has greatly improved the actual performance. This is also a major difference between the LGA1366 flagship platform and other platforms.

As a representative of high-end flagships, the processors of the early LGA1366 interface mainly include 45nm Bloomfield core Core i7 quad-core processors. As Intel bought a 32nm process in 2010, the representative of the high-end flagship was replaced by the Core i7-980X processor. The new 32nm process addresses six core technologies and has the most powerful performance. For users preparing to set up high-end platforms, LGA1366 still occupies the high-end market, and Core i7-980X and Core i7-950 are still good choices.

Intel Core i7 is a 45nm native quad-core processor with 8MB L3 cache and three-channel DDR3 memory. The processor uses LGA 1366 pin design and supports the second generation of hyper-threading technology, which means that the processor can run in eight threads. According to tests circulated on the Internet, the Core i7 with the same frequency has much higher performance than the Core 2 Quad.

Based on the previous data, Intel will release three Intel Core i7 processors at 3.2GHz, 2.93GHz, and 2.66GHz. The 3.2GHz Intel Core i7 Extreme processor will sell for $ 999. Of course, this top processor is aimed at enthusiasts. The lower frequency of 2.66GHz is priced at 284 US dollars, or about 1940 yuan, and is aimed at ordinary consumers. A new generation of Core i7 processors will be launched in the fourth quarter of 2013.

According to the situation displayed by Intel at the Intel Technology Summit 2008 (IDF2008), the core i7's capability is about three times that of core2 extreme qx9770 (3.2GHz). On IDF, Intel staff demonstrated a CineBench R10 multi-threaded rendering using a core i7 3.2GHz processor, and the results were amazing. After the rendering started, the four cores and eight threads started to work at the same time. After only 19 seconds, the complete picture was presented on the screen with a score of more than 45,800. In contrast, core2 extreme qx 9770 3.2GHz can only get about 12 thousand points, and overclocking to 4.0GHz barely exceeds 15,000 points, less than one third of core i7. The super strength of core i7 can be seen from this.

Core i5 is a quad-core processor based on Nehalem architecture. It adopts integrated memory controller, three-level cache mode, L3 reaches 8MB, and supports new processor computer configurations such as Turbo Boost. The main difference between it and Core i7 (Bloomfield) is that the bus does not use QPI, uses mature DMI (Direct Media Interface), and only supports dual-channel DDR3 memory. Structurally it uses LGA1156 interface, Core i7 uses LGA1366. i5 has Turbo frequency technology, which can be overclocked under certain conditions.

Core i3 can be regarded as a further streamlined version (or castrated version) of Core i5. There will be a 32nm process version (R & D code is Clarkdale, based on Westmere architecture). The biggest feature of the Core i3 is the integrated GPU (graphics processor), which means that the Core i3 will be packaged from two cores: CPU + GPU. Because the integrated GPU has limited performance, users who want to get better 3D performance can add a graphics card. It is worth noting that even in Clarkdale, the manufacturing process of the display core will still be 45nm. The biggest difference between i3 and i5 is that i3 does not have Turbo technology.

In June 2010, Intel once again released the revolutionary processor-the second-generation Core i3 / i5 / i7. The second-generation Core i3 / i5 / i7 belongs to the second-generation smart core family, all based on the new Sandy Bridge microarchitecture. Compared with the first generation products, it mainly brings five important innovations: 1. The new 32nm Sandy Bridge micro Architecture, lower power consumption and stronger performance. 2, built-in high-performance GPU (core graphics card), video encoding, graphics performance is stronger. 3. Turbo Boost Technology 2.0, smarter and more efficient. 4. The introduction of a new ring architecture brings higher bandwidth and lower latency. 5, the new AVX, AES instruction set, strengthen floating-point operations and encryption and decryption operations.

SNB (Sandy Bridge) is a new-generation processor micro-architecture released by Intel in early 2011. The biggest significance of this architecture is to redefine the concept of "integrated platform" and "seamless integration" with processors. "End the era of" integrated graphics ". This initiative benefits from a new 32nm manufacturing process. Because the processor under the Sandy Bridge architecture uses a 32nm manufacturing process that is more advanced than the previous 45nm process, theoretically, further reductions in CPU power consumption and significant optimization of circuit size and performance have been achieved. This is to integrate the graphics core. (Core Graphics) Packaged on the same substrate as the CPU creates favorable conditions. In addition, the second-generation Core has also added a new high-definition video processing unit. The high and low speeds of video transcoding speed are directly related to the processor. Due to the addition of high-definition video processing units, the video processing time of the new generation of Core processors has been improved by at least 30% compared to the old processors. The new generation Sandy Bridge processor uses a new LGA1155 interface design, and is not compatible without the LGA1156 interface. Sandy Bridge is a new microarchitecture that will replace Nehalem, but will still use a 32nm process. The more attractive point is that this time Intel no longer glued the CPU core and GPU core with "glue", but instead achieved the two cores.

In the afternoon of April 24, 2012, Beijing Planetarium, Intel officially released the ivy bridge (IVB) processor. The 22nm Ivy Bridge will double the number of execution units to a maximum of 24, which will naturally bring a further leap in performance. Ivy Bridge will add integrated graphics support for DX11. In addition, the newly added XHCI USB 3.0 controller shares four channels to provide up to four USB 3.0, which supports native USB 3.0. CPU production using 3D transistor technology will reduce the power consumption of the CPU by half.

Microprocessor composition

The microprocessor consists of an Arithmetic Logical Unit (ALU); accumulators and general register groups; program counters (also called instruction indicators); timing and control logic components; data and address latches / buffers; internal buses composition. The arithmetic unit and controller are its main components. ^[3]

Microprocessor arithmetic logic unit

The arithmetic logic unit ALU mainly completes arithmetic operations (+,-, ×, ÷, comparison) and various logic

microprocessor Edit operations (AND, OR, NOT, XOR, Shift) and other operations. ALU is a combination circuit. It does not have the function of registering operands, so it must have two registers to store the operands: the temporary register TMP and the accumulator AC. The accumulator not only provides the operand to the ALU, but also receives the operation results of the ALU.

The register array is actually equivalent to the internal RAM of the microprocessor. It includes two parts: a general-purpose register group and a special-purpose register group. The general-purpose registers (A, B, C, D) are used to store data, intermediate results, or addresses that participate in the operation. They can generally be used as two 8-bit registers. With these registers inside the processor, frequent memory accesses can be avoided, instruction length and instruction execution time can be shortened, the machine's operating speed can be increased, and programming can be facilitated. The special registers include the program counter PC, the stack pointer SP, and the flag register FR. Their functions are fixed and used to store the address or address base value. among them:

A) The program counter PC is used to store the address of the next instruction to be executed, so it controls the execution sequence of the program. Under the condition of sequentially executing instructions, the PC contents are automatically incremented by one each time a byte of the instruction is fetched. When a program transfer occurs, a new instruction address (target address) must be loaded into the PC, which is usually implemented by a branch instruction.

B) The stack pointer SP is used to store the top address of the stack. The stack is a specific area in memory

AMD Athlon . It works in a "last in, first out" manner. When new data is pushed into the stack, the original information in the stack does not change, only the top position of the stack is changed. When data is popped from the stack, the data at the top of the stack is popped. Automatically adjust the top position of the stack. In other words, data is always pushed on the top of the stack when pushing or popping the stack. Once the stack is initialized (that is, the location of the bottom of the stack in memory) is determined, the content of the SP (that is, the top of the stack) is automatically managed by the CPU.

C) The flag register is also called the program status word (PSW) register. It is used to store the characteristics of the results after the execution of arithmetic and logical operation instructions. For example, when the result is 0, a carry or overflow flag is generated.

Timing and control logic is the core control component of the microprocessor. It is responsible for controlling the entire computer, including fetching instructions from memory, analyzing instructions (ie, instruction decoding) to determine instruction operations and operand addresses, fetching operands, and executing instructions. Operation, send the result of the calculation to the memory or I / O port, etc. It also sends corresponding control signals to other components of the microcomputer, so that the internal and external components of the CPU coordinate work.

The internal bus is used to connect various functional components of the microprocessor and transmit data and control signals inside the microprocessor.

It must be pointed out that the microprocessor itself cannot constitute an independent working system or execute programs independently. It must be equipped with memory and input and output devices to form a complete microcomputer before it can work independently. ^[3]

Microprocessor memory

Microcomputer memory is used to store programs and data that are currently in use or frequently used. Memory is divided into random access memory (Random Access Memory) and read-only memory ROM (Read only Memory) according to read and write methods. RAM is also called read / write memory. The CPU can read or write its contents at any time during the work process. RAM is volatile memory, that is, its content will be lost after power off, so it can only store temporary programs and data. The contents of the ROM can only be read but not written. The information stored in the ROM remains unchanged after the power is turned off. It is a non-volatile memory. Therefore, ROM is often used to store programs and data of permanent parts. Such as the initial boot program, monitor program, basic input in the operating system, and output management program BIOS. ^[3]

I/O Microprocessor I / O interface

The input / output interface circuit is an important component of a microcomputer. It is a logic control circuit where a microcomputer connects external input and output devices and various control objects and exchanges information with the outside world. Because the structure, working speed, signal form, and data format of peripheral devices are different, they cannot be directly connected to the system bus. The input / output interface circuit must be used for intermediate conversion to achieve information exchange with the CPU. . I / O interface is also called I / O adapter. Different peripherals must be equipped with different I / O adapters. I / O interface circuit is an indispensable and important part of microcomputer application system. The development and design of any microcomputer application system is actually the development and design of I / O interfaces. Therefore, I / O interface technology is one of the important contents discussed in this course. We will introduce it in detail in Chapter 8. ^[3]

Microprocessor bus

The bus is a common channel for transmitting information between components in a computer system, and is an important component of a microcomputer. It consists of several communication lines and various tri-state gate devices that drive and isolate. The microcomputer always adopts the bus structure in its structural form, that is, the functional components (microprocessor, memory, I / O interface circuit, etc.) constituting the microcomputer are connected through the bus. This is a unique feature of the microcomputer system structure. Office. After using the bus structure, the relationship between the functional components in the system is transformed into a single relationship of the components facing the bus. As long as a component (function board / card) meets the bus standard, it can be connected to a system using this bus standard. Therefore, the system function is easy to expand or update, the structure is simple, and the reliability is greatly improved. In microcomputers, the bus can be divided into the following four levels according to their location and application, as shown in Figure 1.4.

(1) On-chip bus: It is located inside the microprocessor chip, so it is called the chip internal bus. It is used for the interconnection and information transfer between the ALU and various registers and other components in the microprocessor (the internal bus in Figure 1.3 is the on-chip bus). Due to the limitation of the chip area and the number of external pins, most of the on-chip buses adopt a single bus structure, which is conducive to the improvement of chip integration and yield. If it is required to accelerate the internal data transfer speed, a dual bus or three bus structure can also be used. .

(2) Chip bus: Chip bus is also called component-level (chip-level) bus or local bus. Microcomputer motherboard, single trigger, and other plug-in boards and cards (such as various I / O interface boards / cards), which are themselves a complete subsystem. The board / card contains CPU, RAM, ROM, and I / O interfaces. Such as various chips, these chips are also connected through the bus, because this is beneficial to simplify the structure, reduce the connection, improve reliability, and facilitate the transmission and control of information. Generally, the buses that realize the interconnection between chips on various boards and cards are called chip buses or component-level buses.

31.2PCATISAPCI

DBData BusABAddress BusCBControl Bus1.2

DBCPUI/OCPUIntel 80861616

ABCPUI/OCPU8162^16=64KB16202^20=1MBn2^n

CBI/O/CPU Therefore, the transmission direction of the control bus is determined by specific control signals, which are generally bidirectional. The number of bits of the control bus depends on the actual control needs of the system. The actual situation of controlling the bus depends on the CPU.

4IEEE-488VXIRS-232

AMD CPU

K5

K5AMDx86CPU1996K5PentiumAMDK5Cyrix6x86PentiumPentiumCyrixK5K5CPU AMD PentiumCPU1997K6K6CPUMMX64KB L1 CacheMMXMMXPK6K5AMDK6MMXPentium

K6

K632KBL1 Cache,32KBL1 Cache,880,0.35,CMOS,C4,168(68),Socket7 Cyrix CPUx86AMD

K62

AMD19984K620.2568930K6264KB L1 Cache512KB2MB2.2VSocket 7

K62K6100MHz3D Now3D Nowx863DK62MMX100MHzL250% CyrixCyrix M199836x86,MMX2.9V256;3.5X;650,20.664KB

K6

AMD19992Sharptooth()K6Super 7CPGACPU0.2513521302.2V/2.4V

AthlonK7

K62K6256KB128KBCPUK664KB32KB32KB512KB2MB 1999623AMDK7AthlonK70.25K71.6V()0.18K751.7V1.8VK72130200MHz

Athlon128KBL1 Cache(P/P32KB)512KB1MB L2 Cachex86K73DNOW3DFPUK7x862K7Slot 1Slot ADigitalAlphaEV6200MHzAthlonAMDSMPCPUAthlon4 AMD20006ThunderbirdDuronCoppermine

Thunderbird

ThunderbirdAMDAthlon0.18Slot ASocket A128KB256KBCPU1.70V1.75VAthlon;3700120

Thunderbird200MHzAlpha EV6x86

Duron

DuronAMDAthlonSpitfireDuron200MHz128KB64KB1.5VThunderbird1002500K7Athlon300AMDK7DuronP6Intel/

^[4] 1975IBMRISC 801RISCJohn Cocke15Power ,RISCARM

RISCHPHPPA-RISC

19756800 786800 6809 6800 1985MC680108800032RISC1990PowerPC

Z-80IntelFrederico Faggin88080------51Z80

16TI TMS 9900TIDSP19829900

X86Cyrix1983National SemiconductorNS32032RISCRISCPOWERPCRISC

1981MIPSRISC

1982RISC-I32

ARM is a chip design company. It does not produce chips itself, but develops ARM series processors through authorized production. ARM was established in a barn in Cambridge, England, in November 1990. Initially there were only 12 people. After more than 11 years of development, today ARM has more than 700 employees, of which more than 60% are engaged in research and development. ARM It is a company that neither manufactures chips (fabless) nor sells chips (chipless). It has established a new type of microprocessor design, production and sales business model by selling chip technology licenses. More importantly, this business model has achieved great success. Microprocessors using ARM technology IP cores are used in various electronic products: automotive, consumer electronics, imaging, industrial control, mass storage, networking, security and wireless markets. ARM technology is almost everywhere. ARM licenses its technology to many famous semiconductor, software and OEM manufacturers in the world, and each manufacturer gets a unique set of ARM-related technologies and services. With this partnership, ARM quickly became the creator of many global RISC standards. A total of 30 semiconductor companies have signed hardware technology license agreements with ARM, including large companies such as Intel, IBM, LG Semiconductor, NEC, SONY, Philips and National Semiconductor. As for software system partners, it includes a series of well-known companies such as Microsoft, Sun and MRI.

Microprocessor China R & D

On February 18, 2004, the 32-bit microprocessor THUMP chip independently developed by Tsinghua University finally received the "identity card" issued by the Ministry of Education: a typical operating frequency of 400 MHz, power consumption of 1.17 mW / MHz, and 40 chip particles , The highest working frequency can reach 500MHz, is currently the highest operating frequency of the domestic microprocessor. "This marks a substantial step in China's independent research and development of CPU chips." The Ministry of Education spoke highly of the birth of THUMP.

On the basis of Loongson 1 and Loongson 2, China is independently developing a new generation of Loongson 3.

Godson 3A's operating frequency is 900MHz ~ 1GHz, power consumption is about 15W. At 1GHz, the peak value of double precision floating point operation speed reaches 16 billion times per second, and the peak value of single precision floating point operation speed is 32 billion times per second. Godson 3A is produced by STMicroelectronics' 65-nm CMOS process. The number of transistors reaches 425 million. The chip is in a BGA package. The number of pins is 1121 and the power consumption is less than 15 watts. Loongson 3A integrates four 64-bit superscalar processor cores, 4MB of secondary cache, two DDR2 / 3 memory controllers, two high-performance HyperTransport controllers, one PCI / PCIX controller, and LPC, SPI, UART, Low-speed I / O controller such as GPIO. Loongson 3A's instruction system is compatible with MIPS64 and supports X86 binary translation through instruction extension. Godson-3 has broad market application prospects in products including servers, high-performance computers, low-energy data centers, personal high-performance computers, high-end desktop applications, high-throughput computing applications, industrial control, digital signal processing, and high-end embedded applications. .