📚 IGCSE CIE Computer Science: Computer Architecture Key Points | IGCSE CIE 计算机：计算机体系结构 考点精讲
Computer architecture is the conceptual design and fundamental operational structure of a computer system. Understanding it is essential for the IGCSE CIE Computer Science exam, as it underpins how hardware and software interact. This article breaks down the core topics, from the Von Neumann model to factors affecting CPU performance, ensuring you are fully prepared for Paper 1.
计算机体系结构是计算机系统的概念设计和基本操作结构。理解它对于 IGCSE CIE 计算机科学考试至关重要，因为它揭示了硬件和软件如何交互。本文将剖析核心主题，从冯·诺依曼模型到影响 CPU 性能的因素，确保你为 Paper 1 做好充分准备。
1. The Von Neumann Architecture | 冯·诺依曼架构
The Von Neumann architecture describes a system where a single memory holds both program instructions and data. A central processing unit (CPU) fetches, decodes, and executes these instructions sequentially. This stored-program concept means programs can be easily modified by loading new data into memory.
冯·诺依曼架构描述了一种系统，其中单个存储器同时保存程序指令和数据。中央处理器 (CPU) 顺序地取出、解码并执行这些指令。这种存储程序概念意味着可以通过将新数据加载到存储器中来轻松修改程序。
The key components connected in this architecture include the CPU, memory unit, input/output devices, and the buses that transfer information between them. Almost all modern general-purpose computers still follow this basic design, although with many performance enhancements.
该架构中连接的关键组件包括 CPU、存储单元、输入/输出设备以及它们之间传输信息的总线。几乎所有现代通用计算机仍然遵循这一基本设计，只是增加了许多性能增强。
2. Central Processing Unit (CPU) Components | 中央处理器 (CPU) 组件
The CPU consists of three main parts: the Control Unit (CU), the Arithmetic Logic Unit (ALU), and a set of registers. The CU directs operations, managing the flow of data and decoding instructions. The ALU performs all mathematical calculations and logical comparisons, such as addition, subtraction, AND, OR, and NOT operations.
CPU 由三个主要部分组成：控制单元 (CU)、算术逻辑单元 (ALU) 和一组寄存器。CU 指导操作，管理数据流并解码指令。ALU 执行所有数学计算和逻辑比较，例如加法、减法，以及 AND、OR 和 NOT 操作。
Registers are extremely fast, small memory locations inside the CPU used to hold temporary data and instructions during execution. They are essential for the fetch-decode-execute cycle and the overall speed of processing.
寄存器是 CPU 内部极快的小型存储位置，用于在执行期间保存临时数据和指令。它们对于取指-解码-执行周期以及整体处理速度至关重要。
3. Registers and Their Functions | 寄存器及其功能
You must know several special-purpose registers for the exam. The Program Counter (PC) holds the address of the next instruction to be fetched. The Memory Address Register (MAR) stores the address of the memory location currently being read from or written to.
你需要熟悉几个考试专用的特殊功能寄存器。程序计数器 (PC) 保存下一条要取出的指令的地址。内存地址寄存器 (MAR) 存储当前正在读取或写入的内存位置的地址。
The Memory Data Register (MDR), also called Memory Buffer Register, holds the actual data or instruction that has been fetched from or is about to be written to memory. The Current Instruction Register (CIR) contains the instruction that is currently being decoded and executed. The Accumulator (ACC) temporarily stores the results of ALU calculations.
内存数据寄存器 (MDR)，也称为内存缓冲寄存器，保存着已经从内存中取出或即将写入内存的实际数据或指令。当前指令寄存器 (CIR) 包含当前正在解码和执行的指令。累加器 (ACC) 暂时存储 ALU 计算的结果。
| Register | Function | 功能 |
|---|---|
| PC | Holds address of next instruction | 保存下一条指令的地址 |
| MAR | Holds address of memory location being accessed | 保存正在访问的内存地址 |
| MDR | Holds data/instruction from/to memory | 保存来自/发往内存的数据或指令 |
| CIR | Holds current instruction being executed | 保存当前执行的指令 |
| ACC | Stores intermediate ALU results | 存储 ALU 的中间结果 |
4. The Fetch-Decode-Execute Cycle | 取指-解码-执行周期
The CPU repeats continually the fetch-decode-execute cycle to run programs. In the fetch stage, the address from the PC is copied to the MAR, the control unit initiates a memory read, the instruction is placed into the MDR, and it is then copied to the CIR. Meanwhile, the PC is incremented to point to the next instruction.
CPU 不断重复取指-解码-执行周期以运行程序。在取指阶段，PC 中的地址被复制到 MAR，控制单元发起内存读取，指令被放入 MDR，然后被复制到 CIR。同时，PC 递增以指向下一条指令。
During the decode stage, the control unit interprets the instruction in the CIR, determining what action is required and which operands are involved. Finally, in the execute stage, the ALU carries out the required operation, which may involve reading from or writing to memory, performing a calculation, or changing the flow of the program by modifying the PC.
在解码阶段，控制单元解读 CIR 中的指令，确定需要什么操作以及涉及哪些操作数。最后，在执行阶段，ALU 执行所需的操作，这可能涉及读取或写入内存、执行计算，或通过修改 PC 来改变程序流程。
5. Buses: Data, Address, and Control | 总线：数据总线、地址总线和控制总线
Buses are sets of parallel wires that carry information between components. The address bus is unidirectional, carrying the address of the memory location or I/O port that the CPU wants to access. Its width determines the maximum number of addressable memory locations.
总线是一组并行导线，在组件之间传输信息。地址总线是单向的，传输 CPU 想要访问的内存位置或输入/输出端口的地址。其宽度决定了可寻址内存位置的最大数量。
The data bus is bidirectional, transporting the actual data or instructions between the CPU, memory, and I/O devices. Its width affects the amount of data that can be moved in one operation. The control bus carries timing and control signals, such as read/write signals, to coordinate activities across the system.
数据总线是双向的，在 CPU、内存和 I/O 设备之间传输实际的数据或指令。其宽度影响一次操作中可以移动的数据量。控制总线传输时序和控制信号，例如读/写信号，以协调整个系统的活动。
6. Primary Memory: RAM and ROM | 主存储器：RAM 和 ROM
RAM (Random Access Memory) is volatile memory used to hold programs and data currently in use. It can be read from and written to, but its contents are lost when the power is turned off. More RAM allows more applications to run simultaneously without slowing down the system due to excessive disk swapping.
RAM (随机访问存储器) 是易失性存储器，用于保存当前正在使用的程序和数据。它可读可写，但断电后内容会丢失。更多的 RAM 允许同时运行更多的应用程序，而不会因过多的磁盘交换而导致系统变慢。
ROM (Read Only Memory) is non-volatile and typically stores the firmware or BIOS that boots the computer. Its contents are retained without power and are usually permanently written during manufacture. Unlike RAM, ROM cannot be easily altered by the user.
ROM (只读存储器) 是非易失性的，通常存储启动计算机的固件或 BIOS。其内容在断电时仍会保留，并且通常在制造过程中永久写入。与 RAM 不同，ROM 不能被用户轻易修改。
7. Clock Speed, Cores, and Cache | 时钟速度、核心和缓存
Clock speed, measured in Hertz, determines how many instruction cycles a CPU can perform per second. A higher clock speed generally means faster processing, but it also generates more heat and consumes more power. The CPU’s performance is not solely dependent on clock speed.
时钟速度以赫兹为单位，决定了 CPU 每秒可以执行多少个指令周期。更高的时钟速度通常意味着更快的处理速度，但也会产生更多的热量并消耗更多的功率。CPU 的性能不仅仅取决于时钟速度。
A core is an independent processing unit within the CPU. Multi-core processors can execute multiple instructions simultaneously, improving multitasking and performance on parallel workloads. Cache is a small amount of very fast memory located on or near the CPU, storing frequently accessed data and instructions, reducing the need to fetch from slower main memory.
核心是 CPU 内部独立的处理单元。多核处理器可以同时执行多条指令，从而提高多任务处理能力和平行工作负载的性能。缓存是位于 CPU 上或其附近的一小部分非常快速的内存，存储频繁访问的数据和指令，从而减少从较慢的主存中取指的需要。
Typical cache levels include L1 (fastest, smallest), L2 (larger, slightly slower), and sometimes L3 (shared among cores). The hit rate of cache significantly influences the effective speed of the processor.
典型的缓存级别包括 L1 (最快、最小)、L2 (更大、稍慢)，有时还有 L3 (核心之间共享)。缓存的命中率显著影响处理器的有效速度。
8. Instruction Set and Assembly Language | 指令集与汇编语言
An instruction set is the collection of all operations a particular CPU can execute. Each instruction consists of an opcode (operation code) and often one or more operands (data or addresses). Assembly language uses mnemonics like LOAD, STORE, ADD, and JUMP to represent these machine instructions in a human-readable form.
指令集是特定 CPU 能够执行的所有操作的集合。每条指令由一个操作码 (opcode) 以及通常一个或多个操作数 (数据或地址) 组成。汇编语言使用助记符，如 LOAD、STORE、ADD 和 JUMP，以人类可读的形式表示这些机器指令。
The IGCSE syllabus expects you to understand a simplified assembly language and trace simple programs. For example, ‘LOAD X’ copies the contents of memory location X into the accumulator; ‘ADD Y’ adds the value in Y to the accumulator; ‘STOR Z’ stores the accumulator value into memory location Z.
IGCSE 大纲要求你理解一种简化的汇编语言，并能跟踪简单的程序。例如，‘LOAD X’ 将内存位置 X 的内容复制到累加器；‘ADD Y’ 将 Y 中的值与累加器相加；‘STOR Z’ 将累加器的值存储到内存位置 Z。
9. Embedded Systems | 嵌入式系统
An embedded system is a dedicated computer system designed for a specific function within a larger device. Examples include microwave ovens, washing machines, digital watches, and car engine control units. They typically use a microcontroller that integrates a CPU, memory, and input/output peripherals on a single chip.
嵌入式系统是一种专用计算机系统，设计用于在更大的设备中执行特定功能。例子包括微波炉、洗衣机、数字手表和汽车发动机控制单元。它们通常使用微控制器，将 CPU、内存和输入/输出外设集成在单个芯片上。
Because they are task-specific, embedded systems can be highly optimized for low power consumption, real-time response, and reliability. Their software (firmware) is often stored in ROM or flash memory and is rarely changed after manufacture.
由于它们是特定任务的，因此可以针对低功耗、实时响应和可靠性进行高度优化。它们的软件 (固件) 通常存储在 ROM 或闪存中，并且在制造后很少更改。
10. Factors Affecting CPU Performance | 影响 CPU 性能的因素
Exam questions often ask you to explain how hardware specifications influence overall performance. The three main factors are clock speed, number of cores, and cache size. Increasing clock speed allows the processor to execute more cycles per second, directly speeding up instruction execution.
考试题目经常要求你解释硬件规格如何影响整体性能。三个主要因素是时钟速度、核心数量和缓存大小。提高时钟速度可以使处理器每秒执行更多的周期，直接加快指令执行速度。
Adding more cores enables true parallel processing, meaning multiple instructions can run truly simultaneously, which greatly benefits multi-tasking and programs designed for multiple threads. However, not all software can efficiently use many cores.
增加更多核心可以实现真正的并行处理，这意味着多条指令可以真正同时运行，这对于多任务处理和针对多线程设计的程序大有裨益。然而，并非所有软件都能高效地使用多个核心。
Larger cache reduces the average time to access data by storing frequently used information closer to the CPU. A larger cache can significantly improve performance in tasks that repeatedly use the same data or instructions, while its effect diminishes after a certain size.
更大的缓存通过将频繁使用的信息存储在更靠近 CPU 的位置来减少平均数据访问时间。更大的缓存可以在重复使用相同数据或指令的任务中显著提高性能，但在达到一定大小后其效果会减弱。
Published by TutorHao | IGCSE Computer Science Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
屏轩国际教育cambridge primary/secondary checkpoint, cat4, ukiset,ukcat,igcse,alevel,PAT,STEP,MAT, ibdp,ap,ssat,sat,sat2课程辅导，国外大学本科硕士研究生博士课程论文辅导