Hello dear readers of the blog site. Very often on the Internet, you can find a lot of all kinds of computer terminology, in particular - such a thing as "System bus". But few people know what exactly this computer term means. I think today's article will help clarify.
The system bus (backbone) includes the data, address and control bus. Each of them transmits its own information: data bus - data, addresses - respectively, address (devices and memory cells), control - control signals for devices. But now we will not delve into the jungle of the theory of organization of computer architecture, we will leave it to university students. Physically, the trunk is represented as (contacts) on the motherboard.
It is no coincidence that I pointed to the inscription "FSB" in the photo for this article. The point is that for connection of the processor to the chipset it is the FSB bus that is responsible, which stands for "Front-side bus" - that is, "front" or "system". And, which is usually guided by when overclocking a processor, for example.
There are several types of FSB, for example, on motherboards with Intel processors, the FSB is usually a type of QPB, in which data is transferred 4 times per clock. If we are talking about AMD processors, then data there is transmitted 2 times per cycle, and the bus type is called EV6. And in the latest CPU models from AMD, there is no FSB at all, its role is played by the latest HyperTransport.
So, data is transferred between and the central processor at a frequency that is 4 times higher than the FSB frequency. Why only 4 times, see the paragraph above. It turns out that if the box says 1600 MHz (effective frequency), in reality the frequency will be 400 MHz (actual). Later, when it comes to overclocking the processor (in the following articles), you will learn why you need to pay attention to this parameter. For now, just remember, the higher the frequency, the better.
By the way, the inscription "O.C." means literally "overclocking", this is an abbreviation for English. Overclock, that is, it is the maximum possible frequency of the system bus that the motherboard supports. The system bus can easily operate at a frequency significantly lower than that indicated on the package, but not higher than it.
The second parameter that characterizes the system bus is. This is the amount of information (data) that it can pass through itself in one second. It is measured in Bits / s. The bandwidth can be independently calculated using a very simple formula: bus frequency (FSB) * bus width. You already know about the first factor, the second factor corresponds to the processor capacity - remember, x64, x86 (32)? All modern processors are already 64-bit.
So, we substitute our data into the formula, in the end it turns out: 1600 * 64 = 102 400 MB / s = 100 GB / s = 12.5 GB / s. This is the bandwidth of the trunk between the chipset and the processor, or rather, between the north bridge and the processor. That is system bus, FSB, processor bus are all synonyms... All connectors of the motherboard - video card, hard disk, RAM, "communicate" with each other only through the trunk. But FSB is not the only one on the motherboard, although the most important, of course.
As you can see from the figure, the Front-side bus (the thickest line) basically connects only the processor and the chipset, and already from the chipset there are several different buses in other directions: PCI, video adapter, RAM, USB. And it is not at all a fact that the operating frequencies of these sub-buses should be equal or multiples of the FSB frequency, no, they can be completely different. However, in modern processors, the RAM controller is often moved from the north bridge to the processor itself, in which case it turns out that a separate RAM line does not seem to exist, all data between the processor and the RAM is transmitted via the FSB directly with a frequency equal to the FSB frequency.
That's all for now, thanks.
What is the modular approach to building a computer?
The architecture of modern personal computers is based on a modular principle. It allows the consumer to complete the required computer configuration and, if necessary, upgrade it. The modular organization of the computer is based on the trunk (bus) principle of information exchange between modules. Information exchange between individual computer devices is carried out over three multi-bit buses connecting all modules: data bus, address bus and control bus.
What is the backbone way of exchanging information?
The backbone method provides the exchange of information between functional and structural modules of different levels using highways that combine input and output buses.
Distinguish between one-, two-, three- and multi-line communications.
What is microprogrammability?
Microprogrammability is a way of implementing the principle of programmed control. Its essence lies in the fact that the principle of program control extends to the implementation of the control device. In other words, the control device is built in exactly the same way as the entire computer, only at the micro level, i.e. The control device has its own memory, called control memory or microinstruction memory, its own "processor", its own control device.
What does the architecture of a computer with a single-bus structure look like?
Single-bus architecture - the architecture of a microprocessor system with a shared memory of data and commands and a common bus for exchange with memory.
Reading of command codes from the system memory is performed using read cycles. Therefore, in the case of a single-bus architecture, the cycles of reading commands and cycles of transferring (reading and writing) data are alternated on the system bus, but the exchange protocols remain unchanged regardless of what is transmitted - data or commands. In a single-bus architecture, the same bus is used to communicate with memory and VU.
What does the architecture of a computer with a multi-bus structure look like?
The main feature of this architecture is that for each method of exchanging information with the control panel, a separate group of buses is used: separate buses for the programmed mode of information exchange with or without interruptions and for the input-output of information in the direct memory access mode, which transmit data blocks with high speed.
The communication protocols, bus structure and communication speed for each of the bus groups can be optimally adapted to the CP in accordance with the selected method.
What is a von Neumann machine made of?
A von Neumann machine consists of memory, input / output devices, and a central processing unit (CPU). The central processor, in turn, consists of a control unit (CU) and an arithmetic logic unit (ALU)
Generalized algorithm of von Neumann's computer functioning.
With the help of an external device, a program is entered into the computer's memory.
The control unit reads the contents of the memory cell where the first instruction (command) of the program is located and organizes its execution. The command can set:
Performing logical or arithmetic operations;
Reading data from memory to perform arithmetic or logical operations;
Recording results into memory;
Entering data from an external device into memory;
Data output from memory to an external device.
The control unit starts executing the command from a memory location immediately behind the command just executed. However, this order can be changed using control transfer (jump) commands. These commands indicate to the control device that it needs to continue the execution of the program, starting from the command contained in another memory location.
The results of the program execution are output to an external computer device.
The computer goes into standby mode for a signal from an external device.
Multi-bus structure of a computer. Advantages, disadvantages.
The main feature of its organization is that for each method of exchanging information with the control panel, a separate group of buses is used: separate buses for the program mode of information exchange with or without interruptions and for the input-output of information in the direct memory access mode, which transmit data blocks with high speed. The communication protocols, bus structure and communication speed for each of the bus groups can be optimally adapted to the CP in accordance with the selected method.
The disadvantages are greater complexity than a single bus structure and less standardization of the tires.
Single-bus structure of a computer. Advantages, disadvantages.
In this case, the computer blocks are combined by means of one bus group, which includes subsets of data buses, addresses and control signals. With such an organization of the bus system, the exchange of information between the processor, peripheral devices and memory is carried out according to a single rule, there are no separate I / O commands for accessing the CP in the command system. This makes it possible to increase the flexibility and efficiency of the computer, since the entire set of instructions for accessing memory can be used to transfer and process the contents of the CP registers. In addition, another important advantage is the simplicity of the bus structure and the minimization of the number of connections for the exchange of information between computer devices.
The disadvantages are: the presence of slow devices on the bus, limitation on the simultaneous exchange of data (no more than two devices at the same time).
13. List the requirements for modern computers.
Requirements for modern computers are as follows:
Cost-to-performance ratio.
Reliability and resiliency.
Scalability.
Software compatibility and portability.
What is reliability?
The reliability of a computer is the ability of a machine to maintain its properties under specified operating conditions for a certain period of time. The following indicators can serve as a quantitative assessment of the reliability of a computer containing elements, the failure of which leads to the failure of the entire machine:
Probability of failure-free operation for a certain time under given operating conditions;
Computer operating time between failures;
Average recovery time for a car, etc.
15. How does the concept of "reliability" differ from the concept of "fault tolerance"?
Unlike reliability - the ability of a machine to maintain its properties under given operating conditions for a certain period of time, fault tolerance is the property of a machine to maintain its performance after the failure of one or more of its component components. Fault tolerance is determined by the number of any consecutive single component failures, after which the system as a whole remains operational.
What is scalability?
Scalability characterizes the ability of a computer to smoothly increase the computing power without degrading the performance of the computer as a whole. A system is called scalable if it can increase performance in proportion to the additional resources.
What is Compatibility?
Hardware compatibility refers to the ability of one device to logically replace another device of the same type, or the ability of one device to both physically and logically interface with others. In the latter case, the terms "full (hardware) compatibility" and "connector compatibility" are also used as synonyms for hardware compatibility.
Software compatibility of one computer with another is understood as the ability of the first to execute programs that were developed for the second computer. Different models of the same family of computers have, as a rule, "one-way" compatibility, since computers of later (older) models are usually more powerful (that is, they are able to execute additional instructions, have more memory, etc.) ... In this case, it is said that a computer of an older model is upward compatible with a computer of a younger model, emphasizing the fact that the first can execute programs prepared for the second, but not vice versa.
What are X terminals?
An X terminal is dedicated hardware that runs an X server and serves as a thin client. They are useful in cases where many users are using one large application server at the same time.
What is a mainframe?
Mainframe (Mainframe) - a high-performance computer with a significant amount of random access and external memory, designed for organizing centralized data storage of large capacity and performing intensive computational work. Mainframes are usually used for integer operations that require data exchange speed, reliability, and the ability to simultaneously process multiple processes.
SPEC tests.
The main output of SPEC is test suites. These kits are being developed by SPEC using codes from various sources. SPEC is working to port these codes to different platforms, and is also creating tools to generate meaningful workloads from the codes selected as tests. Therefore, SPEC tests are different from free software.
Currently, there are two basic SPEC benchmarks, which are computationally intensive and measure the performance of the processor, memory system, and compiler's code generation efficiency. Typically, these tests target the UNIX operating system, but they have also been ported to other platforms. The percentage of time spent on operating system and I / O functions is generally negligible.
Functional diagram of ROM.
Classification of ROM.
ROMs are divided into:
Mask ROM
Electrically one-time programmable ROM
Reprogrammable (EPROM, EPROM)
Uf. RPZU
Email RPZU
54. Physical foundations of the memory element of a one-time programmable ROM (diagram).
When the jumper is present, current flows through the transistor and a high level is read. If Uп is high, then when the transistor opens, the current burns through the wire.
55. Physical foundations of the reprogrammed ROM storage element (diagram).
The Rewritable ROM uses a floating-gate magnetic induction MOSFET.
56. Purpose and device PLM (diagram).
PLM is a functional block created on the basis of semiconductor technology and designed to implement the logical functions of digital systems. They are used in control and decryption devices.
57. Vertical build-up of memory (scheme) and its purpose.
Vertical growth is used to increase the addressable storage space.
58. Horizontal memory expansion (scheme) and its purpose.
Horizontal growth is used to increase the bit capacity of the RAM.
What buses does the system bus consist of?
The system bus includes three multi-bit buses:
Data Bus - Used to transfer data between the CPU and memory, or the CPU and I / O devices.
Address bus - serves to select devices or memory cells where data is sent or read from via the data bus. Unidirectional bus.
Control bus - serves to transmit control signals that determine the nature of the exchange of information along the highway, intended for memory and input / output devices.
A complex consisting of a bundle of wires and electronic circuits that ensure the correct transfer of information inside a computer is called a backbone, a system bus, or simply bus. The tire is characterized by capacity and frequency.
The maximum amount of simultaneously transmitted information is called bus width... The bus width is determined by the processor capacity and is currently 64 bits. The higher the bus width, the more information it can transmit per unit of time.
The processor searches for a device or memory cell. Each device or cell has its own address. The address is transmitted over the address bus, which signals are transmitted in one direction from the processor to the main memory and devices. The width of the address bus determines the address space of the processor, i.e. number of memory cells. The number of addressable memory cells is calculated by the formula: N = 2i, where i- bit width of the address bus. If the width of the address bus is 32 bits, then the maximum possible number of addressable memory cells is 232 = 4,294,967,296 cells.
Information on the bus is transmitted in the form of pulses of electric current. The bus does not work continuously, but in cycles. The number of bus cycles per unit of time is called bus frequency.
The bus connects with each other not only the processor and RAM, in fact all computer devices - disks, keyboard, display, etc. - one way or another, they receive and transmit data through the bus. For this, the bus provides standard connectors to which one or another computer device is connected. If there is only one bus, then the I / O bandwidth is limited. The bus speed is limited by physical factors - the length of the bus and the number of connected devices. Therefore, modern large systems use a set of interconnected buses. Traditionally, buses are divided into buses that provide the organization of communication between the processor and memory and I / O buses.
I / O buses can be long, support the connection of many types of devices, and usually follow one of the bus standards. The processor-to-memory buses are relatively short, high-speed, and match the organization of the memory system to maximize the memory-to-processor channel bandwidth.
Some computers have a single bus for memory and I / O devices. This bus is called systemic. Local A bus is a bus that electrically goes directly to the contacts of the microprocessor. It usually integrates the processor, memory, buffering circuits for the system bus and its controller, as well as some auxiliary circuits.
Initially, the ISA bus (8- and 16-bit, frequency - 8 MHz) was used, which was created in the early 80s and had a low bandwidth. Now the ISA bus is sometimes used to connect low-speed devices (keyboards, mice, etc.).
Currently, the most commonly used:
ü PCI bus (Peripheral Component Interconnect bus);
ü graphics bus AGP (Accelerated Craphic Port - accelerated graphics port);
ü HyperTransport is a high-speed bus for connecting the internal devices of a computer system. The clock frequency reaches 800 MHz. The bandwidth is up to 6.4 GB / s;
ü USB is designed to connect up to 256 external devices (such as a mouse, printer, scanner, camera, FM tuner, etc.) to one USB channel (using the common bus principle). Throughput up to 480 Mbps (in USB 2.0 version).
In modern computers, the processor frequency can exceed the system bus frequency (the processor frequency is 1 GHz, and the bus frequency is 100 MHz).
"What are tires"? Strange question, anyone can say. We see tires since childhood - bicycle, passenger, truck tires - i.e. what is “put on” on the wheels. But it turns out that not everyone knows that there are computer buses. Now you won't surprise anyone with a computer, it is almost a "desktop" subject for any student. But what is inside - few enthusiasts, amateur schoolchildren, and workers of service centers know this.
So, Wikipedia says that "a computer bus (from the English computer bus, bidirectional universal switch) is a subsystem in the architecture of a computer that transfers data between functional blocks of a computer." That. we can say that if the heart of the PC is the processor, then the PC buses are the arteries through which the electrical signals run. And those connectors where hard drives, video cards, network cards are usually inserted - these are not buses, these are only slots-interfaces, and with their help! and there is a connection to the buses. Those. in other words, buses are used by computing devices to exchange information. The buses are monitored by special controllers.
There are two types of buses: the system bus and the expansion bus. The system bus (or processor bus) is necessary for the exchange of information between the processor and the main and external memory. The second bus is used to connect peripheral devices and is, as it were, a continuation of the processor bus, connecting it with external devices. In addition to the controller, each bus includes components of address, data, control.
If truck tires have their own characteristics (size, type of pattern, structure for the arrangement of cords, type of sealing), then computer tires have their own characteristics. What are they?
The main characteristics of computer buses can be considered
- The bit depth that determines the number of data bits that can be simultaneously transmitted. Those. if the bus is 16-bit, then it has 16 channels for simultaneous data transmission.
- Clock frequency.
- Maximum data transfer rate per second.
Computer buses are constantly being improved. If in the 80s of the last century the IBM PC / XT system bus was popular, which provided the transfer of 8 bits of data, then with the advent of the i286 processor, a new system bus ISA (Industry Standard Architecture) appeared. But as time went on, the i386, i486 and Pentium processors appeared and the ISA system bus is gradually becoming the "bottleneck" of personal computers based on these processors.
Currently, the range of tires is quite wide and their quantity and quality is constantly growing. Each tire has its own specific advantages, and possibly disadvantages. Often modern computers use their own "proprietary" buses.
Comments:
Dell has officially unveiled a new generation of Inspiron 5000 notebooks powered by AMD R ...
The official announcement of the new smartphone Lenovo K6 Enjoy, which the company refers to the middle class ...
For a long time, the Panasonic Lumix GH-5 camera was in incredible demand in the market, as it allowed ...
TECNO officially launched the affordable CAMON 11S smartphone today. Its main advantage is ...
The performance of the entire system depends on them. On the motherboard for each device, floppy drives, etc., there is a control electronic circuit - an adapter, or a controller. Some controllers can control several devices at once.
All computer controllers interact with the processor and through the system data transmission line, which is also called the system bus... In addition to the system bus, modern motherboards have several buses and their corresponding connectors for connecting devices:
- memory bus - for the exchange of information between the RAM and the central processor;
- AGP bus - for connecting a video adapter.
- the cache memory bus - for the exchange of information between the cache memory and the central processor;
- I / O buses (interface buses) - used to connect various devices.
There are three main indicators of a computer's bus: clock frequency, bit width, data transfer rate, or bandwidth.
The operation of any computer depends on the clock frequency determined by a crystal oscillator, which is a tin container with a quartz crystal placed in it. Under the influence of an electric voltage, electrical vibrations arise in the crystal. The frequency of these oscillations is called the clock frequency. All changes in logical signals in any computer microcircuit occur at regular intervals, called clock cycles. Thus, the smallest unit of time for most logical devices in a computer is the clock period. Each operation requires at least one clock cycle, although some modern devices manage to perform several operations in one clock cycle. The clock speed of a computer is measured in megahertz (MHz or GHz). There are so-called empty clock cycles (wait cycles) when a device is in the process of waiting for a response from some other device. This is how the work of the RAM and the computer processor is organized, the clock frequency of which is much higher than the clock frequency of the RAM.
The buses use multiple channels to transmit electrical signals. If 32 channels are used, then buses are considered 32-bit, if 64 channels are used, then buses are 64-bit. In fact, buses of any width have more channels. Additional channels are intended for the transmission of specific information.
Each computer bus differs from a simple conductor in that it has three types of lines: data lines, address lines, control lines.
The data bus is exchanged between the central processor, expansion cards installed in the slots and the computer's RAM.
The process of data exchange is possible only if the sender and recipient of this data is known. Each component of a personal computer and each have its own address and are included in the general address space. For addressing to any device, the address bus is used, through which the unique address of the device is transmitted. The maximum amount of random access memory depends on the width of the address bus of the computer (the number of lines) and is equal to 2 to the power of n, where n is the number of lines on the address bus. For example, computers with an 80486 or higher processor have a 32-bit address bus that can address 4GB of memory.
For successful data transfer on the bus, it is not enough to install them on the data bus and set the address on the address bus. A number of service signals are also required, which are transmitted over the control bus of the computer.
The speed of each bus of a computer is characterized by its bandwidth, the maximum possible, transmitted over the bus per unit of time, and is measured in MB / s or GB / s. The bus bandwidth is determined by the product of the bit width of the data line and the clock frequency. The higher the throughput, the higher the performance of the entire system.
In fact, many different factors affect the bandwidth of a computer bus: ineffective conductivity of materials, design and assembly flaws, and much more. The difference between theoretical and practical data rates can be up to 25%.
