When considering computers, it is customary to distinguish between their architecture and structure.

What computer characteristics are standardized to implement the principle of open architecture?

Only a description of the principle of computer operation and its configuration (a certain set of hardware and compounds between them) is regulated and standardized. Thus, the computer can be collected from individual nodes and parts developed and manufactured by independent manufacturers. The computer easily expands and is upgraded by the presence of internal expansion jets, in which the user can insert a variety of devices, and thereby establishing the configuration of its machine in accordance with its personal preferences.

Specify the distinctive features of the classical architecture ("background-neimanovskaya")?

Architecture background Neymanan. One arithmetic and logical device (ALU) through which the data flow passes, and one control device (UU) through which the flow stream passes is the program. This is a single processor computer. This type of architecture also includes the architecture of a personal computer with a common tire. All functional blocks here are interconnected by a common tire, also called the system mainstream.

Physically, the highway is a multi-wire line with jacks for connecting electronic circuits. The totality of the wires of the highway is divided into separate groups: the address bus, the data bus and the control bus.

Peripherals (printer, etc.) are connected to the computer equipment through special controllers - peripheral control devices.

Controller- A device that binds peripheral equipment or communication channels with a central processor, freeing the processor from direct control of the operation of this equipment.

Name the advantages of standard and non-standard computer architectures.

Standard architectures are focused on solving a wide range of various tasks. In this case, the advantage in the performance of multiprocessor and multi-pharmaceutical computing systems before single-processor is obvious. When solving some specific tasks, non-standard architecture allows you to get greater performance.

Name the most characteristic areas of applying standard and non-standard computer architectures.

1. Classic architecture. This is a single processor computer. This type of architecture also includes the architecture of a personal computer with a common tire. Peripherals (printer, etc.) are connected to the computer equipment through special controllers - peripheral control devices.

2. Multiprocessor architecture. The presence in the computer multiple processors means that a lot of data streams can be organized in parallel and many command streams. Thus, several fragments of one task can be performed in parallel.

3. Multimaric computing system. There are several processors included in the computing system, do not have a common RAM, and each other (local). Each computer in a multimarous system has a classic architecture, and such a system is applied quite wide. The effect of applying such a computing system can only be obtained when solving problems with a very special structure: it should be divided into so many poorly related subtasks, how many computers in the system. The advantage in the performance of multiprocessor and multi-stage computing systems before single-processor is obvious.

4. Architecture with parallel processors. Here several Alu work under the control of one yoo. This means that the set of data can be processed according to one program - that is, one stream of commands. The high speed of such architecture can only be obtained on tasks in which the same computing operations are performed simultaneously on various single-type datasets. Modern machines are often present elements of various types of architectural solutions. There are also such architectural solutions that are radically different from those discussed above.

Specify the advantages of open and closed computer architectures.

Advantages of open architecture:

Competition between manufacturers led to the reduction of computer components, which means the computers themselves.

The emergence of a large number of computer equipment allowed buyers to expand their choice, which also contributed to lower prices for components and improve their quality.

The modular structure of the computer and the simplicity of assembly allowed users to independently choose the devices they need and easily produce their installation, also made possible without special difficulties at home to collect and upgrade their computer.

The possibility of upgrades led to the fact that users were able to choose a computer based on their real needs and pocket thicknesses, which again contributed to the increasing popularity of personal computers.

The advantage of closed architecture:

Closed architecture does not allow other manufacturers to release additional external devices for computers, respectively, there is no problem of compatibility of devices from different manufacturers.

Why are the hardware and software configuration of the computer are considered separately?

Position 13 Basic Personal Computer Hardware Configuration

Questions for independent presentation

Describe the functions of the processor. Specify the main characteristics of the processor and their typical values.

The main functions of the processor:

Sampling (read) of the commands performed;

Input (read) data from memory or input / output device;

Output (recording) of data into memory or in I / O device;

Data processing (operands), including arithmetic operations on them;

Memory addressing, i.e., the task of the memory address with which will be exchanged;

Processing interrupts and direct access mode.

Processor characteristics:

Number of data bus discharges

The number of discharges of its bus tire

The number of control signals in the control bus.

The data bus bit determines the system speed. The bit of the address bus determines the permissible complexity of the system. The number of control lines determines the variety of exchange modes and processor exchange efficiency with other system devices.

In addition to the conclusions for the signals of the three main tires, the processor always has an output (or two outputs) to connect an external clock signal or quartz resonator (CLK), since the processor is always a tactable device. The greater the clock frequency of the processor, the more works faster, that is, the faster the commands perform. However, the speed of the processor is determined not only by the clock frequency, but also the characteristics of its structure. Modern processors perform most teams for one clock and have means for parallel execution of several commands. The clock frequency of the processor is not linked directly and rigidly with the speed of the line of the line, since the speed of the line of the line is limited by the delays in the propagation of signals and the distortions of signals on the highway. That is, the processor clock frequency determines only its internal speed, and not external. Sometimes the clock frequency of the processor has the lower and upper limits. When the upper frequency limit is exceeded, the processor is possible, as well as failures, and that the most unpleasant, arising is not always irregular.

RESET RESET SIGNAL. When the power is turned on, during an emergency or the processor hangs, this signal leads to the initialization of the processor, causes it to start executing the initial start program. Emergency situation can be caused by interference on the supply chains and "land", malfunctions in memory, external ionizing radiation and many more reasons. As a result, the processor can lose control over the program being executed and stay in some address. To exit this state, the initial reset signal is just used. The same initial reset input can be used to notify the processor that the supply voltage has become below the set limit. In this case, the processor proceeds to execute a program to save important data. In fact, this input is a special kind of radial interrupt.

Sometimes the processor chip has another one or two inputs of radial interrupts for processing special situations (for example, for interrupting the external timer).

The power bus of the modern processor usually has one supply voltage (+ 5V or + 3.3V) and the overall wire ("earth"). The first processors often demanded several supply voltages. Some processors have reduced power consumption. In general, modern processor chips, especially with high clock frequencies, consume quite greater power. As a result, to maintain the normal operating temperature of the case, they often have to install radiators, fans, or even special micrococoles.

To connect the processor to the highway, buffer chips are used, providing, if necessary, demultiplexing signals and electrical buffering signals of the highway. Sometimes the exchange protocols for the system line and the processor tires do not coincide with each other, then the buffer chips will also agree on these protocols with each other. Sometimes there are several highways (system and local) in the microprocessor system, then its buffer node is used for each of the highways. Such a structure is characteristic, for example, for personal computers.

After turning on the power, the processor proceeds to the first address of the initial start program and performs this program. This program is pre-recorded in a permanent (non-volatile) memory. After the initial start-up program is completed, the processor begins to perform the basic program that is in constant or RAM, for which it selects all the commands. From this program, the processor can distract external interrupts or queries on the PDP. Commands from the memory processor selects with the help of reading cycles on a highway. If necessary, the processor records data into memory or in an I / O device using recording cycles or reads data from memory or from I / O devices using reading cycles.

Specify that it is based on the internal and external memory. List what is included in the internal memory?

The internal memory of the computer is designed for storing programs and data with which the processor works directly while the computer is turned on. In modern computers, the elements of the internal memory are manufactured on chips. The external memory of the computer is designed for long-term storage of large amounts of information. Turning off the computer does not lead to data loss in external memory. Internal memory includes RAM, cache memory and special memory.

Describe the RAM functions. Specify the main characteristics of RAM and their typical values.

RAM - (RAM, English. RAM, Random Access Memory - Common Access Memory) - This is a quick storage device not very large volume, directly related to the processor and intended for recording, reading and storing the programs and data processed by these programs.

RAM is used only for temporary storage of data and programs, since when the machine turns off, everything that was in RAM disappears. Access to the direct memory elements - this means that each memory byte has its own individual address.

The RAM volume is usually from 32 to 512 MB. For simple administrative tasks, there are enough 32 MB of RAM, but complex tasks of computer design may require from 512 MB to 2 GB of RAM.

Usually, RAM is executed from the integrated SDRAM memory chips (synchronous dynamic RAM). Each information bit in SDRAM is remembered in the form of an electrical charge of a tiny capacitor formed in the structure of a semiconductor crystal. Due to the leakage currents, such capacitors are quickly discharged, and their periodically (approximately every 2 milliseconds) are recharged special devices. This process is called memory regeneration (Refresh Memory). SDRAM microcircuits have a capacity of 16 - 256 Mbps and more. They are installed in the housing and are collected in memory modules.

What is the purpose of external memory? List a variety of external memory devices.

The external memory (loss) is intended for long-term storage of programs and data, and the integrity of its content does not depend on whether the computer is turned on or off. Unlike RAM, the external memory does not have a direct connection with the processor.

The external memory of the computer includes:

Drives on rigid magnetic disks;

Storage devices on flexible magnetic disks;

Storage devices on CDs;

Storage devices on magneto-optical CDs;

Magnetic tape drives (streamers), etc.

Describe the principle of hard disk operation. Specify the main characteristics of the hard disk and their typical values.

Drive on hard magnetic disks - (eng. HDD - Hard Disk Drive) or winchester drive - This is the most massive storage device of a large capacity in which the carriers of the information are round aluminum plates - platers, Both surfaces of which are covered with a layer of magnetic material. Used for constant storage of information - programs and data.

Like a floppy disk, the working surfaces of the plotters are divided into ring concentric paths, and the tracks are on the sectors. The read-write heads together with their supporting design and disks are enclosed in a hermetically closed case, called the data module. When you install the data module to the drive, it automatically connects to the system, pulling the purified cooled air. The surface of the plotter has a magnetic coating with a thickness of only 1.1 μm, as well as a layer of lubricant for preventing the head of damage when lowering and lifting on the go. When the plotter rotates over it, the air layer is formed, which provides an airbag for hanging the head at an altitude of 0.5 μm above the disk surface.

Winchester drives have a very large capacity: from 10 to 100 GB. In modern models, the spindle speed (rotating shaft) is usually 7200 rpm, the average data search for 9 ms, the average data transfer rate up to 60 MB / s. Unlike a floppy disk, the hard disk rotates continuously. All modern drives are supplied with built-in cache (usually 2 MB), which significantly increases their performance. The Winchester drive is associated with the processor through the hard disk controller.

What are the devices ports? Describe the main types of ports.

The main characteristics of computing equipment include its operational and technical characteristics, such as speed, memory capacity, calculation accuracy, etc.

Specification of EUM. considered in two aspects. On the one hand, it is characterized by the number of elementary operations performed by the central processor per second. Under the elementary operation it is understood as any simple operation of type of addition, shipping, comparisons, etc. On the other hand, speed

EUM significantly depends on the organization of its memory. The time spent on the search for the necessary information in memory is noticeably affected by computer speed.

Depending on the scope of application, a computer is issued with speed from several hundred thousand to billion operations per second. To solve complex tasks, it is possible to combine several computers into a single computing complex with the required total speed.

Along with speed, often use the concept performance . If the first is due to the mainly used in the EMM system, the second is associated with its architecture and varieties of solved tasks. Even for one "computer, such a characteristic, as a speed, is not the magnitude of constant. In this regard, distinguish:

peak speeddetermined by the clock frequency of the processor without taking into account the access to RAM;

nominal speed determinedtaking into account the time of accessing RAM;

system speed,defined taking into account system costs for the organization of the computing process;

operational,defined, taking into account the nature of the tasks (composition, operations or their "mixture").

Capacity, or memory size determined by the maximum number of information that can be placed in the memory of the computer. Typically, the memory capacity is measured in bytes. As already noted, the memory of the computer is divided into inner and external. Internal, or RAM, in terms of different machines, various machines are different and is determined by the EMM addressing system. The capacity of external memory due to the block structure and removable storage designs are almost unlimited.

Accuracy of calculations depends on the number of discharges used to represent one number. Modern computers are completed with 32- or 64-bit microprocessors, which is enough to ensure the high accuracy of calculations of a wide variety of applications. However, if this is not enough, you can use a military or tripled discharge mesh.

Team system - This is a list of commands that are capable of performing a computer processor. The command system establishes which specifically the operation can perform the processor, how many operands it is required to specify in the command, what kind of (format) should have a command for its recognition. The number of major team species is small, with their help, computer is able to perform additions, subtracts, multiplied by division, comparisons, memory entries, transmission of a number from register to register, transformations from one numbering system to another, etc., if necessary, perform command modifications taking into account the specifics of computing. Usually, the computer uses from tens to hundreds of commands (taking into account their modification). At the modern stage of development of computing technology, two main approaches are used in the formation of the processor command system. On the one hand, it is a traditional approach, a set of processors with a complete set of commands - architecture CIS(Complete Instruction Set Computer is a computer with a complete set of commands). From the other side, this is an implementation of a reduced set of simplest, but often consumable commands, which makes it possible to simplify the hardware processor and increase EI speed - architecture RISCREDUCED INSTRUCTION SET COMPUTER - computer abbreviated command set).

Cost of EUM. depends on a plurality of factors, in particular from speed, memory capacity, teams, etc., a particular effect on the cost is provided by a specific complusion of the computer and, first of all, external devices included in the machine. Finally, the cost of software significantly affects the cost of the computer.

Reliability of EUM. - This is the ability of the machine to maintain its properties under specified operating conditions for a certain period of time. A quantitative assessment of the reliability of a computer containing elements whose refusal leads to the failure of the entire machine, the following indicators can serve as:

probability of trouble-free operation for a certain time under these operating conditions;

eMM operation for refusal;

average recovery time of the machine, etc.

For more complex structures such as a computing complex or system, the concept of "refusal" does not make sense. In such systems, the failures of individual elements lead to a certain decrease in the efficiency of functioning, and not to the complete loss of working capacity as a whole.

Other characteristics of computing equipment are important, for example: versatility, software compatibility, weight, dimensions, power consumption, etc. They are taken into account when evaluating specific applications of computers.

Computational system composition. Computational system composition view hardware and software configuration T. Interfaces of any computing system can be divided into successive and parallel. The system level of transient ensures the interaction of other computer system programs as with the basic level programs and directly with the hardware in particular with the central processor.

If this job does not come up at the bottom of the page there is a list of similar works. You can also use the Search button.

Lecture 4. The history of the development of computing technology. Classification of computers. Computational system composition. Hardware and software. Classification of service and applied software

History of development of computing

The first countable devices were mechanical devices. In 1642, the French mechanicBlaise Pascal Developed a compact summation device -mechanical calculator.

In 1673, German mathematician and philosopherLeibnits improved it by addingmultiplication and division operations. Over the 18th century, more advanced, but still mechanical computing devices based on gear, rush, lever and other mechanisms are still developed.

The idea of \u200b\u200bprogramming computing operations came fromhourly Industry. Such programming was tough: the same operation was performed at the same time (an example is the operation of the machine on the copier).

The idea of \u200b\u200bflexible programming Computing operations was expressed by English mathematicianCharles Babbird In 1836-1848 A feature of his analytical machine was the principle of separation of information oncommands and data. However, the project was not implemented.

Calculation programs on the Babyja car made up by the daughter of the poet ByronaAda Lavleis (1815-1852), very similar to the programs compiled subsequently for the first computers. This wonderful woman was calledthe first programmer of the world.

When moving from registration modeprovisions Mechanical device to regimeregistration states of elements of the electronic devicethe decimal system beganuncomfortable, because of the states of elements onlytwo : Included and off.

The possibility of representing anybinary numbers It was first expressed by Leibnitsa in 1666.

The idea of \u200b\u200bencoding logical statements in mathematical expressions:

• True (True) or False (false);
• in binary code 0 or 1,

was implemented by English Mathematics George Bul (1815-1864) in the first halfXIX century.

However, the algebra of the logic of the Bul algebra developed by them was used only in the next century, when it took a mathematical apparatus for designing a computer schemes using a binary number system. "Connected" mathematical logic with a binary surge system and electrical chains American scientist Claude Shannon in his famous dissertation (1936).

In a logical algebra, when creating a computer used inbasic 4 operations:

• And (intersection or conjunction - a^ B);
• Or (association or disjunction -AVB);
• No (inversion - | a);
• Excluding or (A * | B + | A * B).

In 1936, English Mathematician A. Turing and, regardless of him, E. Post, put forward and developed the conceptabstract computing machine. They proved the principal possibility of solving by machine guns of any problem, subject to its algorithm.

In 1946, John Von Neumanan, Goldstayn and Berx (Princeton Institute of Perspective Studies) was drawn up a report, which contained a detailed descriptionprinciples for building digital computerswhich are still used.

1. The architecture of the computer John von Neumanan includes:
   1. cPUconsisting of a control device (UU) and an arithmetic and logical device (ALU);
   2. memory : operational (RAM) and external;
   3. input Devices;
   4. output devices.
2. Principles of operation of the computer proposed by Neumyan:
   1. uniformity of memory;
   2. software Management;
   3. addressibility.
3. It is possible to highlight the main generation of computer and their characteristics:

The rapid development of computing systems began in the 60s of the 20th century with the refusal to electronic lamps and development semiconductorand then I. Laser technology.

Efficiency EUM (computers) has grown significantly in the 70s of the 20th century with the development of processors based on integrated chip.

High-quality jump in the development of computers occurred in the 1980sXX Century with the inventionpersonal computer and the development of the World Information Network -internet.

Computer classification

1. For appointment:
   • supercomputers;
   • servers;
   • built-in computers (microprocessors);
   • personal computers (PC).

Supercomputers are computing centers - created to solve extremely complex computing problems (modeling complex phenomena, processing super-high volumes of information, predictions, etc.).

Servers (from the English word Serve, manage, manage) - Computers providing the operation of a local or global network specializing in the provision of information services and maintain computers of large enterprises, banks, educational institutions, etc.

Built-in computers (microprocessors) obtained mass distribution in production and household appliances, where control can be reduced to the execution of a limited command sequence (robots on the conveyor, onboard, integrated into household appliances, etc.)

Personal computers (PC. ) Designed to work one person, so used everywhere. Their birth is considered on August 12, 1981, when IBM submitted their first model. PC made a computer revolution in the lives of millions of people and had a huge impact on the development of human society.

PC. We are divided into bulk, business, portable, entertainment, as well as workstations.

PC standards:

• Consumer PC (mass);
  • Office PC (business);
  • Entertainment PC (entertainment);
  • Workstation PC (workstation);
  • Mobile PC (portable).

Most PC are massive.

Business (office)PC. Contain professional programs, but they minimized the requirements for graphics and sound reproduction tools.

In entertainmentPC. Widely represented fundsMultimedia.

Workstations have increased data storage requirements.

For portable mandatory is the availability of access tools in a computer network.

1. In terms of specialization:
   • universal;
   • specialized (examples: file server,Web. -Server, print server, etc.).
2. By sizes:
   • desktop (Desktop);
   • wearable (Notebook, iPad);
   • pocket (Palmtop);
   • mobile Computing Devices (PDA -p ESONAL D IGITAL A SSIST A nT), combining the functions of Palmtop and cell phones.
3. Hardware compatibility:
   • IBM PC;
   • Apple Macintosh.
4. According to the processor type:
   • Intel (in IBM personal computers);
   • Motorola (in Macintosh personal computers).

Computational system composition

Consider hardware and software configuration, since. Often the solution of the same tasks can be provided with both hardware and software. The criterion in each case is the efficiency of work.

It is believed that improving the efficiency of work at the expense of hardware development is on average, it is more expensive, but the implementation of solutions will require high qualifications of personnel.

Hardware

To hardware ensuring computing systems relatedevices and devices (Used block-modular design).

By the method of placing devices relative to the central processor device, the internal and external devices differ. External is an I / O devices (peripheral devices) and additional devices designed for long-term storage.

Approval between individual blocks and nodes is carried out using transient hardware and logic devices - hardware interfaces operating in accordance with the approved standards.

Interfaces of any computing system can be divided intoconsecutive and parallel.

Parallel interfaces are more complicated, require synchronization of transmitting and receiving devices, but have a higher productivity that is measured.bytes per second (byte / s, Krib / s, MB / s). Apply (now rarely) when the printer is connected.

Consistent - easier and slower, they are calledasynchronous interfaces. Due to the lack of synchronization of parcels, useful data is preceded and completed by sending service data (1 byte - 1-3 service bits), performance is measuredbits per second (BIT / C, KBIT / C, Mbit / s).

Used to connect the input, output and storage devices, keyboard, flash memory, sensors, voice recorders, video cameras, communication devices, printers, etc.

Standards Called hardware interfaces protocols. The protocol is a set of technical conditions that must be provided by the developers of computer equipment to successfully harmonize the operation of devices.

Software

Software (software) or software configuration is programs (ordered command sequences). There is a relationship between programs: some work, relying on other (lower level), i.e., you should talk about the interprogrammer interface.

1. Basic Level (BIOS) - The lowest level. Basic security is responsible for interaction with basic hardware. Basic software are stored in the chippermanent storage device -ROM (Read Only Memory (ROM)).

If the parameters of the basic means must be changed during operation, usereprogrammed Herage or Programmable (Erasable and Programmable Read Only Memory (EPROM ). The implementation of the PPZ is carried out using a "non-volatile memory" chicircuit orCMOS. which also works when the computer is started.

1. System level - transitional, ensuring the interaction of other computer system programs, both with the basic level programs and directly with the hardware, in particular with the central processor.

The system of system support includes:

• drivers devices - programs that ensure computer interaction with specific devices;
• installation facilities programs;
• standard user interface tools,providing efficient user interaction, data entry into the system and obtaining results.

The combination of system level programs forms core of the operating systemPC.

If the computer is equipped with system level software, it has already been prepared:

• to the interaction of software with equipment;
• to install higher levels;
• and the most important thing is to interact with the user.

compulsory and mainly sufficient Condition for securitywork man on computer.

1. Service level Software makes it possible to work with the basic level programs and system level programs. The main purpose of service programs (utilities) is in automation of work on checking, adjusting and configuring PC. In addition, they are used to expand and improve the functions of system programs. Some of the service level programs are initially included in the operating system, as standard.

In the design and operation of service programs, there are two alternative destinations: integration with the operating system and offline functioning.

In the second case, they provide the user more opportunities for personalizing their interaction with hardware and software.

1. Applied level - This is a set of application programs, with which specific tasks are performed at this workplace. The spectrum is very wide (from production to entertainment).

Availability of applied software and latitude of functionalityPC. Directly depends on the operating system used, i.e. what system tools contains its kernel and, therefore, as it provides interaction: a person - programs - equipment.

Classification of service software

1. File dispatchers (File managers). Using them, you are copied, moving and renaming files, creating directories, deleting files and directories, search for files and navigating in a file structure (for example, conductor (Windows Explorer)).
2. Archivers - File Compression Tools
3. View and playbacks. Simple and universal viewing tools that do not provide editing, but allow you to view (reproduce) documents of different types.
4. Diagnostic tools - To automate the process of diagnosing software and hardware. Used not only to troubleshoot, but also to optimize the computer.
5. Control means (monitoring) Or monitors - allow you to monitor the processes occurring in the computer. Two modes are used: real-time monitoring and monitoring results in the protocol file (used when monitoring must be automatically remotely).
6. Installation Monitors - Provide software installation monitoring, follow the state of the surrounding environment, allow you to restore connections, lost as a result of the removal of previously installed programs.

The simplest monitors are usually included in the operating system and are placed at the system level.

1. Means of communication (Communication Programs) - Connections with remote computers, serve the transfer of emails and so on.
2. Computer security tools (active and passive). Passive protection tools are backup programs. Anti-virus software is used as active protection tools.
3. Electronic digital signature (EDS).

Classification of applications

1. Text editors (NotePad, WordPad , Lexicon, editorNorton Commander, etc.).
2. Text processors (Allow not only to enter and edit texts, but also to format, i.e. make them). Thus, text processors include interaction toolstext, graphics , tables, as well as tools for automating the formatting process (Word).
3. Graphic editor. These are raster (spot), vector Editors and means to createthree-dimensional Graphs (3D editors).

In raster editors (Paint. ) The graphic object is represented as a combination of points, each of which has brightness and color properties. This option is effective in cases where the image has many halftones, and information about the color of the object elements is more important than information about their form. Raster editors are widely used for retouching images, creating photo effects, but they are not always convenient to create new images and uneconomical, because Images have greater redundancy.

In vector editors (CorelDraw. ) The elementary object of the image is not a point, but a line. This approach is characteristic of drawing and graphic works when the shape of the lines is greater than the information about the color of individual points, its components. This view is much more compact than raster. Vector editors are convenient for creating images, but practically not used to handle ready drawings.

The editors of three-dimensional graphics allow you to flexibly control the interaction of the surface properties of objects with the properties of light sources, as well as create a three-dimensional animation, so they are also called 3D - Inimators.

1. Database Management Systems (DBMS). The main functions of them are:

• creating an empty database;
• providing funds to fill it and import data from the tables of another database;
• ensuring access to data, search and filtering tools.

1. Spreadsheets. These are integrated data storage and data processing (Excel ). Provide a wide range of methods for working with numeric data.
2. Automated Design Systems (CAD systems). Designed to automate design work, and can also produce elementary calculations and choosing structural elements from databases.
3. Desktop publishing systems. Designed to automate the process of laying printing publications. Occupy an intermediate position between text processors and automatic design systems. Typical use of use - Application to documents that have passed preliminary processing in text processors and graphic editors.
4. Expert systems (analysis of data contained in knowledge bases). The characteristic of their feature is the ability to self-development (if necessary, it is generating a sufficient set of questions to the expert and automatically increase its quality).
5. Web editors . Combine the properties of text and graphics editors and are intended to create and editWeb documents.
6. Browers (ViewersWeb documents).
7. Integrated system of office work. Basic functions - editing and formatting the simplest documents, centralization of e-mail, facsimile and telephone communication, dispatching and monitoring of enterprise documents.
8. Accounting systems - combine the functions of text and tabular editors, ensure the automation of the preparation and accounting of primary documents, maintain accounts of the accounting plan, the preparation of regular reporting.
9. Financial analytical Systems. Used in bank and stock exchange structures. Allow you to monitor and predict the situation on financial, stock and commodity markets, analyze, prepare reports.
10. Geoinformation Systems (GIS). Designed to automate cartographic and geodesic work.
11. Video editing systems - processing of video materials.
12. Educational, educational, reference and entertainment programs. Their feature is increased requirements for media (musical compositions, graphic animation and video).

In addition to hardware and software allocateinformation Support (Check spelling, dictionaries, thesauruses, etc.)

In specialized computer systems (onboard), the combination of software and information support is calledmathematical support.

Page 7.

The concept of computing system

The specific set of interacting devices and programs intended for servicing one desktop is called computing system.

A combination of devices intended for automatic or automated data processing is called computer equipment or hardware. Computational system composition is called configuration. Hardware and software of the computing system are considered separately.

The criteria for choosing a hardware and software solution is performance and efficiency.

The central device of the computing system is a computer. A computer - This is an electronic device designed to automate the creation, storage, processing and transportation of data. Although hardware and software are treated separately, it should be noted that these funds of the computing system are working in an inseparable connection and in continuous interaction.

History of development of computing equipment. Generation computers.

(Offered to students for independent study).

EU classification

The mass of use of the PC should not obstruct the fact that there are other multi-time more powerful computing systems in addition to PCs:

· Supercomputers;

· Large computer (mainframe);

· Minicomputers;

· Microcomputers (they include personal PCs).

These computers are different:

· Performance;

· Sizes;

· Functional purpose.

Architecture and structure of computer

When considering computer devices, it is customary to distinguish their architecture and structure.

Architecture The computer is called its description at some general level, including a description of user programming capabilities, command system, addressing systems, memory organization, etc. The architecture defines the principles of operation, information links and the mutual connection of the main logical components of the computer: the processor, operational memory, external memory and peripheral devices. The community of architecture of different computers provides their compatibility from the user's point of view.

Structure Computer is a combination of its functional elements and connections between them. Elements can be the most different devices - from the main logical nodes of the computer to the simplest schemes. The structure of the computer is graphically represented in the form of structural schemes with which you can give a description of the computer at any level of detail.

Classical architecture (Neumanna von architecture) - one arithmetic-logical device (Allu), through which the data flow passes, and one control device (UU) through which the flow stream passes - the program. it single-processor computer. This type of architecture also includes the architecture of a personal computer with common tire. All functional blocks here are interconnected with a common tire called also system highway. Physically, the highway is a multi-wire line with jacks for connecting electronic circuits. The totality of the wires of the highway is divided into separate groups: the address bus, the data bus and the control bus.

Classification of computing equipment

1. Hardware

The composition of the computing system is called configuration. Hardware and software of computing technology are customary separately. Accordingly, separately consider the hardware configuration of computing systems and their software configuration. This principle of separation is of particular importance for informatics, since very often the decision of the same tasks can be provided with both hardware and software. The criteria for choosing a hardware or software solution are performance and efficiency. It is usually assumed that the hardware solutions on average are more expensive, but the implementation of software solutions requires higher personnel qualifications.

The hardware provision of computing systems includes devices and instruments that form hardware configuration. Modern computers and computing complexes have a block-modular design - a hardware configuration necessary to perform specific types of work, which can be collected from finished nodes and blocks.

The main hardware components of the computing system are: Memory, CPU and peripheral devices, which are interconnected by the system highway (Fig. 1.) The main memory is designed to memorize programs and data in binary form and is organized in the form of an ordered array of cells, each of which has Unique digital address. As a rule, the cell size is 1 byte. Typical operations on the main memory: reading and writing the contents of the cell with a specific address.

2. Central processor

The central processor is a central computer device that performs data processing operations and controls computer peripheral devices. The central processor includes:

The control device - organizes the program execution process and coordinates the interaction of all the computing system devices during its operation;

Arithmetic and logical device - performs arithmetic and logical operations on the data: addition, subtraction, multiplication, division, comparison, etc.;

A storage device is an internal processor memory, which consists of registers, when used, the processor performs calculations and retains intermediate results; To speed up the operation with the RAM, the cache memory is used in which the commands and data from RAM, the necessary processor for subsequent operations, are thrown off;

Clock frequency generator - generates electrical impulses, synchronizing the operation of all computer nodes.

The central processor performs various data transactions using specialized cells for storing key variables and temporal results - internal registers. Registers are divided into two types (Fig. 2):

General purpose registers are used to temporarily storing key local variables and intermediate results of calculations, include data registers and indicator registers; The main function is to ensure quick access to frequently used data (usually without memory access).

Specialized Registers are used to control the processor operation, the most important of them: a register of commands, a stack pointer, a register of flags and a register containing information about the status of the program.

The data registers programmer can use any objects (data or addresses) and perform the required operations on its discretion. Index registers as well as data registers can be used arbitrary; Their main purpose is to store indexes or data displacements and commands from the start of the base address (when selecting operands from memory). The address of the base can be in basic registers.

Segment registers are an essential element of the processor architecture, providing addressing a 20-bit targeted space using 16-bit operands. Basic segment registers: CS - code segment register; DS - data segment register; SS - Stack segment register, ES is an additional segmental register. The appeal to the memory is carried out by means of segments - logical formations imposed on any sections of the physical address space. The initial address of the segment divided by 16 (without the youngest hexadecimal number) is entered into one of the segment registers; After that, access to the memory site starting from a given segment address is available.

The address of any memory cell consists of two words, one of which determines the location in the memory of the corresponding segment, and the other is the displacement within this segment. The size of the segment is determined by the amount of data contained in it, but can never exceed 64 KB, which is determined by the maximum possible displacement. The segment address of the command segment is stored in the CS register, and the offset to the addressable byte - in the register of the IP command pointer.

Fig.2. Registers of 32-bit processor

After downloading the program in the IP, the first program of the program is entered. The processor, considering it from memory, increases the contents of the IP exactly for the length of this command (the Intel processor commands may have a length of 1 to 6 bytes), as a result of which IP indicates the second program of the program. By completing the first command, the processor reads the second from the memory, increasing the value of the IP again. As a result, the regular command is always in IP, the command following performed. The described algorithm is violated only when executing commands, calls for subroutines and interrupt maintenance.

The segment address of the data segment is stored in the DS register, the offset may be in one of the general purpose registers. An additional segment register ES is used to access the data fields that are not included in the program, such as the video card or system cells. However, if necessary, it can be configured to one of the segments of the program. For example, if the program works with a large amount of data, you can envisage two segments for them and access the DS register to one of them, and to the other - through the ES register.

SP stack register SP is used as a stack vertex pointer. The stack is called the program area for temporary storage of arbitrary data. The convenience of stack is that its area is used repeatedly, and saving them from there using PUSH and POP commands without specifying names in the data stack and sample. The stack is traditionally used to save the contents of the registers used by the program before calling the subroutine, which, in turn, will use the processor registers for their personal purposes. The initial contents of the registers are removed from the stack after returning from the subroutine. Another common reception is the transfer of the subprogramme of the parameters required by it through the stack. The subroutine, knowing, in what order are placed on the stack of parameters, can pick them out from there and use when performing it.

A distinctive feature of the stack is a peculiar order of the sample of the data contained in it: only the upper element is available on the stack at any time, that is, the element loaded to the stack of the latter. Unloading from the stack of the upper element makes the following element available. Stack elements are located in the memory area allotted under the stack starting from the bottom of the stack (from its maximum address) on consistently decreasing addresses. The address of the upper, available element is stored in the SP stack indicator register.

Special registers are only available in privileged mode and are used by the operating system. They control the various blocks of cache, basic memory, I / O devices and other computing system devices.

There is one register, which is available both in privileged and user modes. This PSW register (Program State Word is the word status word), which is called flag. The flag register contains the various bits required by the central processor, the most important - codes of the conditions that are used in comparisons and conditional transitions they are installed in each cycle of the arithmetic and logical processor device and reflect the state of the result of the previous operation. The contents of the flag register depends on the type of computing system and may include additional fields that indicate the machine mode (for example, user or privileged); trace bit (which is used for debugging); Processor priority level; Interrupt resolution status. The flag register is usually read in user mode, but some fields can be recorded only in privileged mode (for example, a bit that indicates the mode).

Register The command pointer contains the address of the next in line to execute the command. After selecting the command from the memory, the command register is adjusted, and the pointer moves to the next team. The command pointer monitors the program execution of the program, indicating at each moment the relative address of the command following the executable one. The register is programmatically unavailable; Establishing the address in it performs a microprocessor, taking into account the length of the current command. Complaus commands, interrupts, calls to the subroutines and return of them change the contents of the pointer, thereby carrying out the transitions to the required points of the program.

Register The battery is used in the overwhelming number of commands. Frequently used commands that use this register have a shortened format.

For information processing, data transmission from memory cells to general-purpose registers is usually organized, the operation of the operation by the central processor and the transmission of results into the main memory. Programs are stored as a sequence of machine commands that the central processor must perform. Each command consists of an operation field and operand fields - data on which this operation is performed. A set of machine commands is called a machine language. Programs is performed as follows. The machine command specifies the program meter is read from the memory and copied to the command register, where it is decoded, after which it is executed. After its execution, the program counter indicates the following command, etc. These actions are called a machine cycle.

Most central processors have two modes of operation: the kernel mode and user, which is set by the processor status bar (flag register). If the processor is running in kernel mode, it can execute all commands from the instruction set and use all the equipment features. The operating system operates in kernel mode and provides access to all equipment. User programs work in user mode, which allows the execution of multiple commands, but makes only part of the hardware.

To communicate with the operating system, the user program should form a system call that provides a transition to kernel mode and activates the operating system functions. The Trap command (emulated interrupt) switches the mode of operation of the processor from the user to the kernel mode and transmits control of the operating system. After completing the work, the Office returns to the user program, to the command following the system call.

In computers, in addition to the instructions for performing system calls, there are interruptions that are called hardware to prevent exclusive situations, for example, an attempt to divide on zero or overflow during floating point operations. In all such cases, control proceeds to operating systems that must decide what to do next. Sometimes you need to complete the program with an error message, sometimes you can ignore (for example, with a loss of significance of the number, it can be accepted with zero) or transfer the control of the program itself for processing some types of conditions.

By the method of arrangement of devices relative to the central processor, internal and external devices distinguish. External, as a rule, are most of the data input devices (they are also called peripheral devices) and some devices intended for long-term storage.

Approval between individual nodes and blocks are performed using transient hardware and logic devices called hardware interfaces. Standards for hardware interfaces in computing technology are called protocols - a set of technical conditions that must be provided by developers of devices to successfully agree on their work with other devices.

Numerous interfaces present in the architecture of any computing system can be divided into two large groups: sequential and parallel. Through the serial interface, the data is transmitted sequentially, bit beyond the bit, and through parallel - at the same time groups of bits. The number of bits involved in one premise is determined by the interface's bit, for example, eight-bit parallel interfaces transmit one bytes (8 bits) per cycle.

Parallel interfaces usually have a more complex device than consecutive, but provide higher performance. They are used where the data transfer rate is important: to connect printing devices, enable graphics information devices, data recording devices for external media, etc. The performance of parallel interfaces is measured by bytes per second (byte / s; Krib / s; MB / s).

The device of serial interfaces is simpler; As a rule, it is not necessary to synchronize the operation of the transmitting and receiving device to synchronize (therefore they are often called asynchronous interfaces), but the bandwidth is less and the efficiency is lower. Since data exchange through serial devices is made not by bytes, but bits, their performance is measured by bits per second (bit / s, kbps, Mbps). Despite the seeming simplicity of the transfer of units of measurement of the sequential transmission rate into a unit of measuring the velocity of parallel data transmission by mechanical division by 8, such recalculation is not performed, since it is not corrected due to the availability of service data. As a last resort, with an amendment for service data, sometimes the speed of serial devices is expressed in signs per second or in symbols per second (C / s), but this value has not a technical, but reference, consumer character.

Serial interfaces are used to connect slow devices (simple low-quality printing devices: input and output devices for sign and signal information, control sensors, low-performance communication devices, etc.), as well as in cases where there are no significant limitations on the duration of data exchange (Digital Cameras).

The second main component of the computer is the memory. The memory system is designed as a hierarchy of the layers (Fig. 3.). The upper layer consists of internal registers of the central processor. Internal registers provide the ability to store 32 x 32 bits on a 32-bit processor and 64 x 64 bits on a 64-bit processor, which is less than one kilobyte in both cases. Programs themselves can manage registers (that is, to decide what to store them) without the intervention of equipment.

Fig.3. Typical hierarchical memory structure

The following layer contains cache memory, mainly controlled by equipment. The RAM is divided into a cache line, usually 64 bytes, with the addressing from 0 to 63 in the zero line, from 64 to 127 in the first line, etc. The most frequently used cache lines are stored in high-speed cache, located inside the central processor or very close to it. When the program should read the word from memory, the cache chip checks if the desired string is in the cache. If this is the case, then an effective appeal to the cache memory occurs, the request is satisfied entirely from the cache and the request to memory on the bus is not exhibited. A successful appeal to the cache, as a rule, takes about two clocks by time, and the unsuccessful leads to referring to memory with a significant time loss. Cash memory is limited in size due to its high cost. In some machines there are two or even three levels of cache, each subsequent slower and more than the previous one.

Next, RAM should be followed (RAM - operational storage device, English RAM, Random Access Memory - memory with arbitrary access). This is the main working area of \u200b\u200bthe storage device of the computing system. All queries of the central processor that cannot be made cache memory are received for processing in the main memory. When working multiple programs on a computer, preferably complex programs are placed in RAM. Protection of programs from each other and their movement in memory is implemented through the computer equipment with two specialized registers: the basic register and the limit register.

In the simplest case (Fig. 4.A), when the program starts to work, the address of the starting program executable program is loaded into the base register, and the limit register indicates how much the executable program module is held with the data. When selecting a command from the memory, the instrument checks the command meter, and if it is smaller than the limit register, it adds the value of the base register to it, and the amount transmits memory. When the program wants to read the word data (for example, from the address 10,000), the equipment automatically adds the contents of the basic register (for example, 50000) to this address and transmits the amount (60,000) memory. The basic register enables the program to refer to any part of the memory following the address stored in it. In addition, the limit register prohibits the program appeal to any part of the memory after the program. Thus, with this scheme, both tasks are solved: protection and movement of programs.

As a result of checking and converting data, the address generated by the program and called the virtual address is translated to the address used by the memory and called the physical address. A device that performs checking and converting is called a memory management device or Memory Manager (MMU, Memory Management Unit). Memory dispatcher is located or in the processor diagram, or close to it, but is logically between the processor and memory.

A more complex memory manager consists of two pairs of basic and limit registers. One pair is designed for the text of the program, another pair - for data. The command register and all references to the text of the program work with the first pair of registers, the data links use the second steam registers. Thanks to this mechanism, it is possible to divide one program between several users when stored in RAM only one copy of the program, which is excluded in a simple scheme. When the program No. 1 is running, four registers are arranged as shown in Fig. 4 (b) on the left, when the program No. 2 is running on the right. Memory Dispatcher Control is the function of the operating system.

The next in the memory structure is a magnetic disk (hard disk). Disk memory is two orders of magnitude cheaper RAM in terms of bit and more in magnitude, but access to data posted on the disk takes about three orders of magnitude longer. The cause of low hard disk speed is the fact that the disc is a mechanical design. The hard disk consists of one or more metal plates rotating at a speed of 5400, 7200 or 10,800 revolutions per minute (Fig.5.). Information is recorded on plates in the form of concentric circles. The read / write heads in each specified position can read the ring on the plate, called the track. All the paths together for a given position of the fork form a cylinder.

Each track is divided into a certain number of sectors, usually 512 bytes on the sector. On modern disks, external cylinders contain a greater number of sectors than internal. Moving the head from one cylinder to another takes about 1 ms, and moving to an arbitrary cylinder requires from 5 to 10 ms, depending on the disk. When the head is located above the desired path, you need to wait until the engine turns the drive so that the required sector becomes under the head. It takes additionally from 5 to 10 ms, depending on the speed of the disk rotation. When the sector is under the head, the reading or recording process occurs at a speed of 5 MB / s (for low-speed discs) to 160 MB / s (for high-speed discs).

The last layer occupies a magnetic tape. This media was often used to create backup copies of the hard disk space or to store large data sets. To access the information, the tape was placed in a device for reading magnetic tapes, then it was rewound before the requested block with information. The whole process lasted a minute. The described memory hierarchy is typical, but in some embodiments, not all levels or other types of their types may be present (for example, an optical disk). In any case, when the hierarchy is moving from top to bottom, the arbitrary access time is significantly increased from the device to the device, and the capacity is growing equivalent to the access time.

In addition to the species described above, many computers have a permanent memory with arbitrary access (ROM is a permanent memory device, ROM, read only Memory - read-only memory), which does not lose its contents when the computing system is turned off. The ROM is programmed in the production process and after that its content cannot be changed. On some computers in the ROM, the boot programs used when starting the computer, and some I / O cards to control low-level devices.

Electrically erasable ROM (EEPROM, Electrically Erasable Rom) and Flash RAM (Flash Ram) are also non-volatile, but in contrast to the ROM, their contents can be erased and rewrite. However, the data record on them requires much more time than recording in RAM. Therefore, they are used in the same way as ROM.

There is another memory type - CMOS memory, which is volatile and used to store the current date and the current time. Memory receives power from the battery built into the computer, may contain configuration parameters (for example, an indication from which hard disk is loaded).

3. I / O devices

Other devices that are closely interacting with the operating system are I / O devices that consist of two parts: controller and device itself. The controller is a microcircuit (chipset) on the board inserted into the connector, which receives and executes the operating system commands.

For example, the controller receives a read command to a specific sector from the disk. To execute the command, the controller converts the line number of the disc sector in the cylinder number, sector and heads. The transformation operation is complicated by the fact that external cylinders may have more sectors than internal. The controller then determines the cylinder at the moment the head is at the moment, and gives a sequence of pulses to move the head to the required number of cylinders. After that, the controller is waiting for the disc, placing the required sector under the head. Then, the processes of reading and saving bits are sequentially performed as they arrive from the disk, the control processes and calculate the checksum. Next, the controller collects the received bits to words and saves them in memory. To carry out this work, controllers contain built-in firmware.

The I / O Device itself has a simple interface that must comply with the Unified IDE standard (IDE, Integrated Drive Electronics - Built-in drive interface). Since the device interface is hidden by the controller, the operating system sees only the controller interface that may differ from the device interface.

Since controllers for different I / O devices differ from each other, then the appropriate software is required to manage them - drivers. Therefore, each manufacturer of controllers must supply drivers for operating systems supported by it. To install the driver in the operating system, there are three ways:

Reconnect the kernel along with the new driver and then restart the system, there are many UNIX systems;

Create an entry in a file included in the operating system that the driver is required and restart the system, during the initial boot, the operating system will find the desired driver and load it; So the Windows operating system works;

Take new drivers and quickly install them by the operating system during its operation; The method is used by removable USB and IEEE 1394 tires, which always need dynamically downloaded drivers.

For communication with each controller there are certain registers. For example, the minimum disk controller may have registers to determine the address on the disk, the address in memory, the sector number and the direction of operation (read or record). To activate the controller, the driver receives the command from the operating system, then translates it in values \u200b\u200bsuitable for recording to the device registers.

On some computers, the registers of I / O devices are displayed in the address space of the operating system, so they can be read or recorded as conventional words in memory. Addresses of registers are placed in the RAM outside the reach of users' programs to protect users from equipment (for example, using basic and limit registers).

On other computers, the registers of devices are located in special I / O ports, and each register has its own port address. On such machines in a privileged mode, in and out commands are available that allow the drivers to read and write registers. The first scheme eliminates the need for special I / O commands, but uses a number of targeted space. The second scheme does not affect the address space, but requires special commands. Both schemes are widely used. Input and data output is carried out in three ways.

1. The user program issues a system query that the core broadcasts the procedure for the appropriate drive. The driver begins the I / O process. At this time, the driver performs a very short program cycle, constantly polishing the readiness of the device with which it works (usually there is a bit of a bit that indicates that the device is still busy). Upon completion of the I / O operation, the driver places the data where it is required, and returns to its original state. Then the operating system returns the control of the call program. This method is called readiness waiting or active expectation and has one drawback: the processor must interview the device until it completes its work.

2. The driver starts the device and asks it to issue an interrupt at the end of I / O. After that, the driver returns the data, the operating system blocks the call program, if necessary, and starts to perform other tasks. When the controller detects the ending data transfer, it generates an interrupt to signal the completion of the operation. The mechanism for implementing I / O is as follows (Fig.6.A):

Step 1: The driver transmits the controller command, recording information to the device registers; The controller starts the I / O device.

Step 2: After reading or writing, the controller sends the interrupt controller microcircuit signal.

Step s: If the interrupt controller is ready for an interrupt reception, it will give a signal to a certain contact of the central processor.

Step 4: The interrupt controller sets the number of the input-output device to the bus so that the central processor can read it and find out which the device has completed work. When receiving a central interrupt processor, the contents of the command meter (PC) and the processor status words (PSW) is placed in the current stack, and the processor switches to the privileged operation mode (operating system kernel operation mode). The I / O device number can be used as a memory part index that serves to search for the interrupt handler address of this device. This part of the memory is called interrupt vector. When the interrupt handler (part of the device driver, sent interrupt) starts its work, it removes the command meter located on the stack and the processor state word saves them and requests the device to obtain information about its condition. After the interrupt processing is completed, the control returns to the user who worked before this command, to which the execution of which has not yet been completed (Fig. 6 b).

3. For I / O information is used by the direct memory access controller (DMA, Direct Memory Access), which controls the battling flow between the RAM and some controllers without the constant intervention of the central processor. The processor calls the DMA chip, tells it how many bytes need to be transferred, reports the addresses of the device and memory, as well as the direction of data transfer and allows the microcircuit to act itself. Upon completion of the DMA, it initiates an interrupt that is processed accordingly.

Interrupts can occur in inappropriate moments, for example, while processing another interrupt. For this reason, the central processor has the ability to prohibit interrupts and resolve them later. While interrupts are prohibited, all devices that have completed work continue to send their signals, but the operation of the processor is not interrupted until the interrupts are permitted. If you finish working at once several devices at a time when interrupts are prohibited, the interrupt controller decides which of them should be processed first, usually based on static priorities assigned to each device.

The Pentium computing system has eight tires (cache tire, local bus, memory bus, PCI, SCSI, USB, IDE and ISA). Each tire has its own data transfer speed and its functions. In the operating system for managing a computer and its configuration, information should be about all tires.

ISA tire (Industry Standard Architecture, industrial standard architecture) - for the first time appeared on IBM PC / AT computers, operates at 8.33 MHz and can transmit two bytes for tact with a maximum speed of 16.67 MB / s.; It is included in the system for backward compatibility with old slow I / O charges.

PCI bus (Peripheral Component InterConnect, Peripheral Interface) - created by Intel as the ISA bus succession, can work at a frequency of 66 MHz and transmit 8 bytes for tact with a speed of 528 MB / s. Currently, the PCI bus uses most of the high-speed I / O devices, as well as computers with processors other than Intel, since it is compatible with a lot of I / O boards.

The local bus in the Pentium system is used to transmit the PCI-bridge microcircuit with a central data processing processor, which refers to the memory on a dedicated memory bus, often operating at 100 MHz.

The cache bus is used to connect an external cache, since the Pentium system has a first-level cache (Cache L1), built into the processor, and a large external second-level cache (L2 cache).

The IDE bus is used to attach peripherals: disks and devices for reading CDs. The bus is a descendant of the disk controller interface on PC / AT, is currently included in a standard set of all systems based on Pentium processors.

UNIVERSAL SERIAL BUS, universal serial bus) is designed to connect to a computer slow I / O devices (keyboard, mice). It uses a small four-wire connector, two wires of which supply power to USB devices.

The USB bus is a centralized bus along which the main device every millisecond interrogates the I / O devices to find out if they have data. It can control the data load at a speed of 1.5 MB / s. All USB devices use one driver, so they can be attached to the system without rebooting it.

SCSI bus (Small Computer System Interface, a system interface of small computers) is a high-performance tire used for fast disks, scanners and other devices that need significant bandwidth. Its performance reaches 160 MB / s. SCSI bus is used in Macintosh systems, popular in UNIX systems and other systems based on Intel processors.

The IEEE 1394 (FireWire) bus is a bit sequential bus and supports batch data transfer with a speed reaching 50 MB / s. This property allows you to connect portable digital video cameras to a computer and other multimedia devices. Unlike the USB tire, the IEEE 1394 bus does not have a central controller.

The operating system should be able to recognize the hardware components and be able to configure them. This requirement led by Intel and Microsoft to develop a personal computer system called Plug and Play ("Inclined and Work"). Before this system appears, each I / O board had fixed I / O registers and interrupt request levels. For example, the keyboard used interrupt 1 and addresses in the range from 0x60 to 0x64; A flexible disk controller used interrupt 6 and addresses from 0x3F0 to 0x3F7; The printer was interrupted 7 and addresses from 0x378 to 0x37a.

If the user bought a sound card and modem, it happened that these devices accidentally used the same interrupt. There was a conflict, so the devices could not work together. A possible solution was to embed a set of DIP switches (jumpers, jumper - jumper) to each board and configure each fee so that the port addresses and interrupt numbers of various devices conflict with each other.

Plug and Play allows the operating system to automatically collect information about I / O devices, centrally assign interrupt levels and an I / O address, and then report this information to each board. Such a system works on Pentium computers. Each computer with the Pentium processor contains a motherboard on which the program is the BIOS system (Basic Input Output System - the basic I / O system). BIOS contains low-level I / O programs, including procedures: To read from the keyboard, to display information on the screen, to enter data from the disk, etc.

When the computer is booting, the BIOS system starts, which checks the number installed in the RAM system, the connection and correctness of the keyboard and other main devices. Next BIOS checks the ISA and PCI tires and all devices attached to them. Some of these devices are traditional (created before the release of the Plug and Play standard). They have fixed interrupt levels and an I / O port address (for example, specified using switches or jumpers on an I / O board without the possibility of changing their operating system). These devices are recorded, then undergo registration of the Plug and Play device. If the present devices differ from those that were during the last boot, the new devices are configured.

The BIOS then defines the device from which the load will occur, trying to try each other from the list stored in the CMOS memory. The user can change this list by entering the BIOS configuration program immediately after loading. Usually an attempt is attempting to boot from a flexible disk. If it fails, the CD is running. If there is no flexible disk in the computer, and the CD, the system is loaded from the hard disk. From the boot device is read in memory and the first sector is performed. In this sector, there is a program that checks the partition table at the end of the boot sector to determine which partitions is active. Then from the same partition read the secondary bootloader. It reads the operating system from the active partition and starts it.

After that, the operating system polls the BIOS to obtain information about the configuration of the computer and checks the availability of the driver for each device. If the driver is missing, the operating system asks the user to insert a flexible disk or a CD containing the driver (these discs are supplied by the device manufacturer). If all drivers are in place, the operating system loads them into the kernel. Then it initializes the driver tables, creates all the necessary background processes and launches the password input program or a graphical interface on each terminal.

5. History of development of computing equipment

All IBM-compatible personal computers are equipped with Intel-compatible processors. The history of the development of microprocessors of the Intel family is brief. Intel's first universal microprocessor appeared in 1970. It was called Intel 4004, was the four-bit and had the ability to enter / output and process four-bed words. His speed was 8000 operations per second. The Intel 4004 microprocessor was designed to be used in the programmable calculators with a memory of 4 KB.

After three years, Intel has released the 8080 processor, which could already perform 16-bit arithmetic operations, had a 1B-bit address bus and, therefore, could be addressed to 64 KB of memory (2 516 0 \u003d 65536). 1978 marked the release of the 8086 processor with a word size of 16 bits (two bytes), a 20-bit tire and could already operate with 1 MB of memory (2 520 0 \u003d 1048576, or 1024 KB), divided into blocks (segments) 64 KB everyone. The 8086 processor includes computers compatible with IBM PC and IBM PC / XT. The next major step in the development of new microprocessors was the 8028B processor appeared in 1982. He possessed a 24-bit targeted tire, could dispose of 16 megabytes of the address space and was put on computers compatible with IBM PC / AT. In October 1985, 80386dd was released from a 32-bit address of the address (maximum address space - 4 GB), and in June 1988 - 80386SX, cheaper compared to 80386dx and possessed a 24-bit targeted tire. Then in April 1989, a microprocessor 80486dx appears, and in May 1993 - the first version of the Pentium processor (both with a 32-bit address bus).

In May 1995, in Moscow at the international exhibition Comtek-95, Intel introduced a new processor - P6.

One of the most important goals set in the development of P6 was the doubling of performance compared to the Pentium processor. At the same time, the production of the first versions of P6 will be carried out according to the already debugged "Intel" and used in the production of recent versions of the Pentium semiconductor technology (O, 6 μM, s, s).

The use of the same production process gives a guarantee that the mass production P6 will be established without serious problems. At the same time, this means that the doubling of performance is achieved only by comprehensive improvement in the microarchitecture of the processor. When developing microarchitecture P6, a carefully thought-out and configured combination of various architectural methods was used. Some of them were previously tested in the processors of "large" computers, part was proposed by academic institutions, the remaining developed by the engineers of the company "Intel". This unique combination of architectural features that "Intel" define the words "dynamic execution", allowed the first P6 crystals to exceed the originally planned level of performance.

When compared with alternative "Intel" processors of the X86 family, it turns out that the microarchitecture P6 has a lot in common with the NX586 processor microarchitecture of the company AMD, and, although to a lesser extent, with the M1 of Cyrix. This community is explained by the fact that engineers of four companies solved the same task: the introduction of RISC-technology elements while maintaining compatibility with Intel X86 CISC architecture.

Two crystals in one case

The main advantage and a unique feature of P6 is placed In one case with the processor, the secondary static cache memory of 256 KB, connected to a specially dedicated tire processor. Such a design should significantly simplify the design of systems based on P6. P6 is the first intended for mass production of a microprocessor containing two chips in one case.

CPU crystal in P6 contains 5.5 million transistors; Crystal second-level cache - 15.5 million. For comparison, the last model Pentium included about 3.3 million transistors, and the second level cache was implemented using an external set of memory crystals.

Such a large number of transistors in the cache is explained by its static nature. The static memory in P6 uses six transistors to memorize one bit, while the dynamic memory would be enough one transistor to the bit. Static memory is faster, but more expensive. Although the number of transistors on a crystal with a secondary cache is three times more than on the processor crystal, the physical sizes of the cache size: 202 square millimeters against 306 at the processor. Both crystals together are concluded in the ceramic housing with 387 contacts ("Dual Cavity Pin-Drid Array"). Both crystals are manufactured using the same technology (0.6 μm, 4-layer metal-bikmop, 2.9 V). The estimated maximum energy consumption: 20 W at a frequency of 133 MHz.

The first reason for combining the processor and secondary cache in one case - facilitating the design and production of high-performance systems based on P6. The performance of the computing system built on the rapid processor is very dependent on the accurate setting of the processor environment chips, in particular the secondary cache. Not all computer manufacturers can afford the relevant research. In P6, the secondary cache is already configured to the processor in an optimal way, which facilitates the design of the motherboard.

The second reason for combining is an increase in productivity. The second-level csch is associated with a processor specially dedicated bus 64 bits wide and runs on the same clock frequency as the processor.

The first Rentium processors with a clock frequency of 60 and 66 MHz appealed to the secondary cache on the 64-bit bus with the same clock frequency. However, with the growth of the Pentium clock frequency for designers, it was too difficult and expensive to maintain such a frequency on the motherboard. Therefore, frequency dividers began to be applied. For example, at 100 MHz Pentium, the external tire operates at 66 MHz (in 90 MHz Pentium - 60 MHz, respectively). Pentium uses this bus both to appeal to secondary cache and to access the main memory and other devices, such as the set of PCI chips.

The use of a specially isolated tire to access the secondary cache improves the performance of the computing system. First, the complete synchronization of the processor and tire speeds is achieved; Secondly, competition with other I / O operations and related delays is excluded. The second-level cache bus is completely separated from the outer tire through which access to memory and external devices occurs. The 64-bit outer tire can operate at a speed equal to half, one third or one fourth of the processor speed, while the secondary cache bus works independently at full speed.

Combining the processor and secondary cache in one case and their connection through a dedicated tire is a step towards methods for improving the performance used in the most powerful RISC processors. Thus, in the Alpha 21164 processor, the company "Digital" a second-level cache size 96 KB is located in the CPU kernel, like the primary cache. It provides very high cache performance due to an increase in the number of transistors on a crystal to 9.3 million. Performance Alpha 21164 is 330 Specint92 at a clock frequency of 300 MHz. P6 performance below (estimated "Intel" - 200 Specint92 with a clock frequency of 133 MHz), however P6 provides better value / performance ratio for its potential market.

When assessing the ratio cost / performance, it should be borne in mind that, although P6 can be more expensive than its competitors, most of the other processors must be surrounded by an additional set of memory chips and a cache controller. In addition, to achieve comparable performance with cache, other processors will have to use a larger cache than 256 KB of size.

"Intel", as a rule, offers numerous variations of its processors. This is done in order to satisfy the diverse requirements of system designers and leave less space for competitors models. Therefore, it can be assumed that shortly after the start of the release of P6 will appear both modifications with an increased amount of secondary cache memory, as well as cheaper modifications with the external arrangement of the secondary cache, but with the stored selected bus between the secondary cache and the processor.

Pentium as a reference point

Pentium processor with its conveyor and supercal Architecture has reached an impressive performance level. Pentium contains two 5-stadium conveyors that can work in parallel and perform two integer commands for the machine tact. At the same time, only a pair of commands following in the program may be performed in parallel and satisfying certain rules, for example, the lack of register dependences of the type "recording after reading".

In P6, a transition to one 12-stage conveyor was carried out to increase bandwidth. An increase in the number of steps leads to a decrease in the work performed at each stage and, as a result, to a decrease in the time of the team at each stage by 33 percent compared to Pentium. This means that the use of the same technology in the production of P6 as the production of 100 MHz Pentium will result in the preparation of P6 with a clock frequency of 133 MHz.

The possibilities of the supercalar architecture of Pentium, with its ability to fulfill two teams for the tact, it would be difficult to surpass without a completely new approach. The new approach used in P6 eliminates the rigid dependence between the traditional phases of the "sample" and "execution", when the sequence of passing commands through these two phases corresponds to the command sequence in the program.

A new approach is associated with the use of the so-called team pool and with new efficient methods of foresight of the future behavior of the program. In this case, the traditional phase "execution" is replaced by two: "Dispatch / execution" and "rollback". As a result, the command can begin to be executed in an arbitrary order, but completing their execution always in accordance with their initial order in the program. The P6 kernel is implemented as three independent devices that interact through the pool of the commands (Fig. 1).

The main problem on the way of increasing productivity

The decision to organize P6 as three independent and interacting devices through the pool of devices was taken after a thorough analysis of factors that limit the performance of modern microprocessors. The fundamental fact, fair for Pentium and many other processors, is that when performing real programs, the processor power is not fully used.

While the processor speed over the past 10 years has grown by at least 10 times, the access time to the main memory has decreased by only 60 percent. This is an increasing lag of the speed of working with memory in relation to the speed of the processor and was the fundamental problem that had to be solved when designing P6.

One of the possible approaches to solving this problem is to transfer it to the center of gravity to develop high-performance components surrounding the processor. However, the mass production of systems, including a high-performance processor, and high-speed specialized surrounding chips, would be too expensive.

It was possible to try to solve the problem using coarse strength, namely to increase the size of the second-level cache to reduce the percentage of cases of the absence of the necessary data in the cache.

This solution is effective, but also extremely expensive, especially considering today's high-speed requirements for the second-level cache components. P6 was designed from the point of view of the effective implementation of a holistic computing system, and it was necessary that the high performance of the system as a whole was achieved using a cheap memory subsystem.

In this way, The combination of such architectural methods that is implemented in P6 as an improved transition prediction (almost always the upcoming command sequence is almost always determined), analysis of data streams (the optimal command execution order is determined) and the advanced execution (the foreseeless command sequence is performed without downtime at an optimal order) allowed In relation to Pentium when using the same production technology. This combination of methods is called dynamic execution.

Currently, Intel has been developing a new 0.35 micron production technology, which will give the opportunity to produce P6 processors with a yard clock frequency over 200 MHz.

P6 as a platform for building powerful servers

Among the most significant Computer development trends in recent years can be distinguished as ever increasing use of systems based on the CH86 family processors as applications servers and the growing role of "Intel" as a supplier of non-processor technologies, such as tires, network technologies, video compression, flash memory and means system administration.

The Issue of the P6 processor continues the "Intel" conducted by the policies of the possibilities that previously possessed only more expensive computers on the mass market. For internal registers, P6 provides for parity, and the core of the processor and the second-level kernel, the 64-bit bus is equipped with a means of detection and error correction. Built in P6 new diagnostic features allow manufacturers to design more reliable systems. The P6 provides for the possibility of obtaining processor through contacts or using software information about more than 100 processor variables or events occurring in it, such as the lack of data in the cache, the contents of the registers, the appearance of the modifting code and so on. The operating system and other programs can read this information to determine the state of the processor. In P6, improved support for control points is also implemented, that is, the ability to roll back the computer into a fixed state in case of an error occurs.

Similar documents

The means of computing technology have long appeared, since the need for various calculations existed even at the dawn of the development of civilization. Stormy development of computing equipment. Creation of the first PC, mini-computers since the 80s of the twentieth century.

abstract, added 09/25/2008


Characteristics of technical and preventive maintenance of computing equipment. Diagnostic programs of operating systems. The relationship of automated control systems. Protecting a computer from external adverse effects.

abstract, added 03/25/2015


Development of an information and analytical analysis system and optimizing the configuration of computing technology. Structure of automated control of computing equipment. Software, justification of the economic efficiency of the project.

thesis, added 05/20/2013


Manual stage of development of computing equipment. Position system number. Development of mechanics in the XVII century. Electromechanical stage of development of computing equipment. Computers of the fifth generation. Parameters and distinctive features of the supercomputer.

course work, added 04/18/2012


The device and principle of the personal computer (PC). PC performance diagnostics and malfunction definition. Tasks for maintenance of computing equipment. Development of techniques for maintaining equipment in a working condition.

course work, added 07/13/2011


The study of foreign, domestic practices for the development of computing equipment, as well as the prospects for the development of a computer in the near future. Computer use technologies. Stages of the development of the computing industry in our country. Merge PC and communications.

coursework, added 04/27/2013


Classification of project procedures. History of synthesis of computing equipment and engineering design. Functions of automated design systems, their software. Features of the use of three-dimensional scanners, manipulators and printers.

abstract, added 12/25/2012


Data processing automation. Computer science and its practical results. The history of the creation of digital computing equipment. Electromechanical computing machines. The use of electronic lamps and computers of the first, third and fourth generation.

thesis, added 06/23/2009


The concept and characteristics of a personal computer, its main parts and their purpose. Tools of computer science and features of the organization of work in the office of computing equipment. Equipment for jobs and application of software.

abstract, added 07/07/2012


Computational system composition - computer configuration, its hardware and software. Devices and devices that form a hardware configuration of a personal computer. Basic memory, I / O ports, peripheral adapter.