1.1- Systems Architecture Flashcards
(35 cards)
What does CPU stand for and where is it found?
CPU stands for Central Processing Unit. It is found in the motherboard.
What is the purpose of the CPU?
The purpose of the CPU is to process data and instructions by constantly repeating the fetch-execute cycle.
What are the four main parts of the CPU?
- Control Unit
- Arithmetic and Logic Unit
- Registers
- Cache
What does the control unit do?
The control unit (CU) sends control signals to direct the operation of the CPU. Control signals are sent to the ALU and other components such as RAM. It also decodes instructions as part of the fetch-execute cycle. It controls the timing and flow of data inside the CPU (to registers, cache, ALU) and outside the CPU (to main memory and input/output devices).
What is a register?
A register is a temporary storage space for one instruction or address. Different registers are used during the fetch-execute cycle.
What are the five main registers used in the fetch-execute cycle?
- Program counter (PC)
- Memory Address Register (MAR)
- Memory Data Register (MDR)
- Current Instruction Register (CIR)
- Accumulator (ACC)
What does the program counter do?
This is found in the Control Unit. It tracks the RAM address of the next instruction to be fetched.
What does the MAR do?
This stores the RAM address of the current instruction or data that the CPU needs to access, or the address in memory to which data is to be transferred.
What does the MDR do?
This stores the instruction that has been transferred from the RAM to the CPU. It holds the data that has been retrieved from memory, or that is about to be stored in memory
What does the CIR do?
This stores the instruction that has been fetched from RAM and is about to be decoded or executed.
What does the accumulator do?
This stores the result of mathematical or logical calculations.
What does the Arithmetic and Logic unit do?
The arithmetic and logic unit (ALU) performs simple calculations and logical operations. It contains the accumulator register.
What is Cache memory used for?
Cache memory is used to temporarily store data that is frequently accessed, so that the CPU can access it quickly the next time it is needed. When the CPU requests data, it checks the cache first, then the RAM.
What are the levels of cache memory?
Cache memory is split into different levels (L1 is the fastest but has the lowest capacity, L2 slower but holds more, L3 slower but holds more).
What the comparisons between Cache and RAM?
Cache is much slower to access than registers but much faster than RAM. Caches have a low capacity and are much more expensive compared to RAM.
What is the architecture of a computer?
The way a computer is designed is known as its architecture.
What is the most common type of computer architecture?
The most common type of architecture is Von Neumann architecture. This architecture is named after Jon von Neumann who developed the concept of a stored program computer in the 1940s. Before being able to store programs in memory, instructions had to be manually inputted.
What does a computer with Von Newman architecture do and how does this compare to Harvard architecture?
A computer with von Neumann architecture stores both program instructions and data in the same memory (RAM). Other architectures like Harvard, have two separate memory locations: one for program instructions and one for data.
What are buses?
Data is transferred between components on pathways called buses.
What are the main types of bus and what do they do?
Control bus – carries control signals to tell the memory or processor what to do next, e.g. :
– Memory READ – find out what is in a memory location
– Memory WRITE – change the value in a memory location
– clock signals – time to do the next instruction
Address bus – carries memory addresses from processor to memory
Data bus – carries data and instructions both ways
How does the fetch-execute cycle work?
- The program counter (PC) register displays the address in RAM of the next instruction to be processed.
- This value is copied into the Memory Address Register (MAR).
- These steps happen simultaneously:
a) The contents of the MAR are sent down the address bus. A READ signal is sent down the control bus The main memory looks at what is in that memory location and sends it up the data bus to the Memory Data Register (MDR)
b) The PC register is incremented by 1- preparing the CPU for the next instruction to be fetched. - The instruction in the MDR is copied into the Current Instruction Register (CIR).
- The instruction in the CIR is decoded (understood) and executed (processed). The result of any execution is stored in the Accumulator (ACC) register.
- The cycle repeats by returning to the first step and checking the program counter for the address of the next instruction.
What are the factors that affect CPU performance?
- Cache Memory
- Clock Speed
- Number of cores
What is cache memory?
temporary storage for frequently accessed data.
How does cache memory impact CPU performance?
Cache memory is closer to the CPU than RAM, meaning that it can provide data and instructions to the CPU at a faster rate. A computer with more cache memory (eg 8GB over 4GB) should have a higher performance because repeatedly used instructions can be stored and accessed faster.
