MindMap Gallery system bus
This is a mind map about system buses. The main contents include: bus communication control, bus structure, bus classification, bus control, bus characteristics, and bus concepts.
Edited at 2024-10-27 10:47:50호흡부전이란 외부 호흡 기능의 심각한 손상으로 인해 동맥의 산소분압(PaO2)이 정상 범위보다 낮거나 이산화탄소(PaCO2) 분압의 상승을 동반하는 병리학적 과정을 말한다.
준비부터 완료까지 프로젝트의 다양한 단계와 주요 작업을 자세히 설명하는 현장 건설 및 비즈니스 문서입니다. 이는 프로젝트 관리자가 프로젝트 진행 상황과 주요 링크를 더 잘 파악하여 프로젝트가 원활하게 진행될 수 있도록 도와줍니다.
지식 포인트를 정리 정리하고, 담배와 술을 멀리하기, 마약을 거부하기, 건강에 주의하기 등의 내용을 소개하여 지식 포인트를 익히고 기억력을 높일 수 있도록 도와줍니다. 도움이 필요한 학생은 저장할 수 있습니다.
호흡부전이란 외부 호흡 기능의 심각한 손상으로 인해 동맥의 산소분압(PaO2)이 정상 범위보다 낮거나 이산화탄소(PaCO2) 분압의 상승을 동반하는 병리학적 과정을 말한다.
준비부터 완료까지 프로젝트의 다양한 단계와 주요 작업을 자세히 설명하는 현장 건설 및 비즈니스 문서입니다. 이는 프로젝트 관리자가 프로젝트 진행 상황과 주요 링크를 더 잘 파악하여 프로젝트가 원활하게 진행될 수 있도록 도와줍니다.
지식 포인트를 정리 정리하고, 담배와 술을 멀리하기, 마약을 거부하기, 건강에 주의하기 등의 내용을 소개하여 지식 포인트를 익히고 기억력을 높일 수 있도록 도와줍니다. 도움이 필요한 학생은 저장할 수 있습니다.
system bus
bus concept
The bus is actually composed of many transmission lines and channels. Each line can transmit binary codes bit by bit. A string of binary codes can be transmitted one by one within a period of time.
Bus structure
CPU-centric single-bus architecture
Advantages: Various I/O devices are connected to the I/O bus through the I/O interface, making it easier to add and delete devices.
Disadvantages: This structure still occupies the CPU when the I/O device exchanges information with the main memory, so it also affects the CPU's work efficiency.
Single bus structure
Advantages: When the I/O device exchanges information with the main memory, in principle, it does not affect the CPU work, and the CPU can still continue to process operations that do not access storage or I/O devices. This improves the efficiency of the CPU
Disadvantages: There is only one set of buses. When each component wants to occupy the bus at a certain time, conflicts will occur.
Memory-centered dual-bus architecture
Advantages: On the basis of the single bus, a bus between the CPU and the main memory is opened up, called the storage bus. This group of buses has high speed and is only used to transmit information between the main memory and the CPU, which not only improves the transmission efficiency , reducing the burden on the system bus, and retaining the feature of exchanging information between I/O devices and memory without going through the CPU.
Disadvantage: conflicts can occur when exchanging information
Dual bus structure
The characteristics of the dual bus structure are to separate the lower I/O equipment from the single line to form a structure that is separated from the storage bus from the I/O bus, and the response speed has changed
Three bus structure
Subtopic storage bus is used for transmission between CPU and storage. I/O bus is used to transfer information between CPU and various I/O devices. DMA bus is used to directly exchange information between high-speed I/O devices and storage. Among the three line structures, only one bus can be used at any time. The storage bus and the DNA bus cannot access the components at the same time. The I/O bus can only be used when the CPU executes I/O instructions.
Classification of buses
According to data transmission method
Parallel transfer bus
serial transmission bus
By transfer width
8-bit transmission bus
16-bit transmission bus
32-bit transfer bus
According to the scope of use
peripheral bus
Measurement and control bus
network communication bus
Differences according to connecting parts
On-chip bus
system bus
communication bus
Different information is transmitted according to the system bus
data bus
address bus
control bus
Bus characteristics
bus performance
①Bus width: usually refers to the number of data buses, expressed in bits, such as 8-bit, 16-bit, 32-bit, 64-bit (i.e. 8, 16, 32, 64).
②Bus bandwidth: Bus bandwidth can be understood as the data transmission rate of the bus, that is, the number of bits of data transmitted on the bus per unit time. It is usually measured by the number of bytes of information transmitted per second. The available unit is MBps (megabytes per second). express. For example, if the bus operating frequency is 33 MHz and the bus width is 32 bits (4B), the bus bandwidth is 33x(32÷8)=132 MBps.
③Clock synchronization/asynchronous: The bus where the data on the bus works synchronously with the clock is called a synchronous bus, and the bus which works asynchronously with the clock is called an asynchronous bus.
④Bus multiplexing: Two signals are transmitted in a time-shared manner on one signal line. For example, usually the address bus and the data bus are physically separate buses. The address bus transmits address codes, and the data bus transmits data information. In order to improve the utilization of the bus and optimize the design, the address bus and the data bus share a set of physical lines, and the address signals and data signals are transmitted in a time-sharing manner on this set of physical lines, which is the multiplexing of the bus.
⑤ Number of signal lines: the sum of the three bus numbers: address bus, data bus and control bus.
⑥Bus control mode: including burst work, automatic configuration, arbitration mode, logic mode, counting mode, etc.
⑦Other indicators: such as load capacity, power supply voltage (whether 5V or 3.3V is used), whether the bus width can be expanded, etc.
bus control
Chained queries: sensitive to circuit faults
Counter timing query: not as sensitive to circuit faults as chain query, but the control is complex
Independent request method: fast response, flexible priority and limit sequence, and complex control
Bus communication control
bus cycle
Application allocation stage
addressing phase
transfer phase
end stage
Communication method
Synchronous communication
Asynchronous communication
(1) No interlocking method After the master module sends the request signal, it does not have to wait for the response signal from the slave module. Instead, after a period of time, it confirms that the slave module has received the request signal and then cancels its request signal; after the slave module receives the request signal, it will cancel the request signal when conditions permit. A reply signal is sent out when the module is running, and after a period of time (the settings of this period are different for different devices), after confirming that the main module has received the reply signal, it automatically cancels the reply signal. It can be seen that there is no interlocking relationship between the communication parties. For example, when the CPU writes information to the main memory, the CPU must successively provide address signals, write commands, and write data, that is, this method is used.
(2) Semi-interlocking method When the master module sends a request signal, it must wait for the reply signal from the slave module before canceling its request signal. There is an interlocking relationship; while the slave module sends a reply signal after receiving the request signal, but it does not have to wait to know that the request signal from the master module has been Cancel, but automatically cancel its reply signal after a period of time, without interlocking relationship. Since one side has an interlocking relationship and the other side does not have an interlocking relationship, it is called a semi-interlocking method. For example, in a multi-machine system, when a CPU needs to access shared memory (memory accessible to all CPUs), after the CPU issues a memory access command, it must receive a response signal that the memory is not occupied before it can actually perform the memory access operation. .
(3) Full interlocking method When the master module sends a request signal, it must wait for the slave module to reply before canceling its request signal; when the slave module sends a reply signal, it must wait until it knows that the master module's request signal has been canceled before canceling its reply signal. There is an interlocking relationship between the two parties, so it is called full interlocking method. For example, in network communication, both communicating parties adopt a fully interlocked method. Asynchronous communication can be used for parallel transfer or serial transfer. Asynchronous parallel communication can be seen in Figure 5.6, in which "Ready" and "Strobe" are contact signals. In asynchronous serial communication, there is no synchronization clock, and there is no need to transmit synchronization signals during data transmission. In order to confirm the transmitted characters, the agreed character format is: 1 start bit (low level), 5~8 data bits (such as ASCII code is 7 bits), 1 parity bit (for error detection) 1 or 1.5 or 2 stop bits (high). When transmitting, the starting bit is followed by the lowest bit of the character to be transmitted, and the end of each character is a high-level stop bit. The start bit to the end bit constitute a frame, and the interval between two frames can be of any length. Figure 3.19 is an asynchronous serial transmission format with two data transmission rates. Figure 3.19(a) has idle bits (high level) between two frames, while Figure 3.19(b) has no idle bits between two frames, so the data The transfer rate is higher.
semi-synchronous communication
Separate communication