Please enable JavaScript.
Coggle requires JavaScript to display documents.
Characteristics of contemporary processors - Coggle Diagram
Characteristics of contemporary processors
Structure and function of the processor
Components of a processor
The arithmetic and logic unit
The ALU (arithmetic and logic unit) completes the arithmetical and logical operations
The control unit
The control unit is the component of the processor which directs operations inside the CPU. It has the following jobs:
Controlling and coordinating the activities of the CPU
Managing the flow of data between the CPU and other devices
Accepting the next instruction
Decoding instructions
Storing the result back into memory
Registers
Registers are small memory cells that operate at very high speeds
They are used to temporarily store data
All arithmetic, logical or shift operations occur in these registers
Program counter (PC): Holds the address of the next instruction to be executed
Accumulator (ACC): Stores the results from calculations
Memory address register (MAR): Holds the address of a location that is to be read from or written to
Memory data register (MDR): Temporarily stores data that has been read or data that needs to be written
Current instruction register (CIR): Holds the current instruction being executed, divided up into operand and opcode
Buses
Buses are a set of parallel wires which connect two or more components inside the CPU together
The collection of the data bus, control bus and address bus is called the system bus
The width of the bus is the number of parallel wires the bus has
Data bus:
This is a bi-directional bus (meaning bits can be carried in both directions) used for transporting data and instructions between components
Address bus:
Used to transmit the memory addresses specifying where data is to be sent to or retrieved from
Adding a wire to the address bus doubles the number of addressable locations
Control bus:
This is a bi-directional bus used to transmit control signals between internal and external components
The control signals include:
Bus request: shows that a device is requesting the use of the data bus
Bus grant: shows that the CPU had granted access to the data bus
Memory write: data is written into the addressed location using this bus
Memory read: data is read from a specific location to be placed onto the data bus
Interrupt request: shows that a device is requesting access to the CPU
Clock: used to synchronise operations
Relationship with assembly language
Assembly code uses mnemonics to represent instructions
It is a simplified way of representing machine code
The instruction is divided up into operand and opcode
Opcode is used to determine the type of instruction and what hardware to use to execute it
The operand is the address of where the operation is performed
The fetch-decode-execute cycle is the sequence of operations that are completed in order to execute an instruction
Fetch phase:
Address form the PC is copied to the MAR
Instruction held at the address is copied to MDR by the data bus, simultaneously the contents of the PC are increased by one
The value held in the MDR is copied to the CIR
Decode phase:
The contents of CIR are split into operand and opcode
Execute phase:
The opcode is executed on the operand
Factors affecting CPU performance
Clock speed
Clock speed is determined by the system clock
All processor activities begin on a clock pulse
Each CPU operation starts as the clock changed from 0 to 1
The clock speed is the number of clock cycles completed in a second
Number of cores
A core is an independent processor that is able to execute its own fetch-execute cycle
A computer with multiple cores can complete more than one fetch-execute cycle at any given time
Some programs aren't optimised for the use of more than one core
Amount and type of cache memory
Cache memory is the CPU's onboard memory
Instructions fetched from main memory are copied to the cache, so if required again it can be accessed quicker
As cache fills up, unused instructions get replaced
Level 1 cache: Very fast memory cell. However it also has a small amount of capacity (2-64KB)
Level 2 cache: Relatively fast memory cell with medium sized capacity (256KB-2MB)
Level 3 cache: Much larger and slower memory cell
Pipelining
Pipelining: the process of completing the fetch, decode and execute cycles of three separate instructions simultaneously
Data is held in a buffer in close proximity to the CPU until it's required
Pipelining is aimed to reduced the amount of the CPU which is kept idle
Computer architecture
Von Neumann architecture
Von Neumann includes a single control unit, ALU, registers and memory units
Shared memory and data bus used for both data and instructions
Advantages:
Cheaper to develop since the control is easier to design
Programs can be optimised in size
Harvard architecture
Physically separate memories for instructions and data
More commonly use with embedded processors
Advantages:
Quicker since data and instructions can be fetched in parallel
Both memories can be different sizes
Contemporary processing
The combination of Harvard and Von Neumann architecture
Uses Von Neumann when working with the data and instructions in main memory
Uses Harvard when working with cache
There is an instruction cache and data cache
Types of processor
RISC and CISC processors
Reduced instruction set computers (RISC):
Small instruction set
Each instruction is one line of machine code
Pipelining is possible since each instruction takes one clock cycle
Complex instruction set computers (CISC):
Large instruction set
Instructions are built into the hardware
The compiler has less work to do
Less RAM is required to store the code
Many specialised instructions are made, even though only a few of them are used
Graphics processing unit (GPU)
A co-processor made up of lots of independent processors
Efficient at tasks such as image processing and machine learning
Multi-core and parallel systems
Multi-core CPUs have multiple independent cores that complete separate fetch-execute cycles
Parallel systems complete multiple instructions simultaneously using techniques like pipelining, it can be completed using a single core and threading
Input, output and storage
Input, output and storage devices
Input devices include:
Keyboards
Webcams
Magnetic stripe readers
Barcode readers
Output devices include:
Speakers
Printers
Projecters
A touch screen is both an input and output device. Performance factors for both input and output devices include:
Speed
Accuracy
Cost
Relevance to task
The use of storage
Optical devices:
Read from and written to using lasers
Binary information represented by portions of he disc which either reflect or scatter the incident laser light:
A pit scatters light and represents a 0
A land reflects light and represents a 1
Pits and lands are written in spiral tracks on the disc's surface
CD:
Stands for compact disc
Use optical technology to store small quantities of information
Most commonly used for audio files
Can also be used to store text and digital images
Small, thin and light so very portable
Easily damaged by scratches
Limited storage capacity
Relatively slow transfer speeds
DVD:
Stands for digital versatile disc or digital video disc
Higher storage capacity than CDs
Suited to storing digital videos
Blu-ray:
More than five ties as much storage than traditional DVDs
Useful for storing high-resolution films
Each method of storing information is suited to a particular type of information
Magnetic:
Represent binary information using two magnetic states
Polarised
Unpolarised
Most common type is hard disk drives
Magnetic tape also stores information magnetically
Hard disk drives:
Typically have high capacities of between 500B and 5TB
Rotate magnetic platters at high speeds under a read/write head on an actuating arm
Most will have multiple platters stacked to maximise storage capacity
Have somewhat slow data transfer speeds
Many moving parts introduces tendency to be damaged by movement
Magnetic tape:
First used to record computer data in the 1950s
Popular storage medium through to the 1980s
Long stretches of tape wound onto reels passed through readers
A space consuming way to store data
Floppy disks:
A thin magnetic disk enclosed in plastic to protect the disk from dust and dirt
Thin size and low weight made them extremely portable
Typical storage capacity of 1MB
Flash
Fast and compact
Silicon semiconductors form the logic gates NAND and NOR
Logic gates used to store electrical charge in one of two states: high or low
Information stored in blocks, combined to form pages
Preferred logic gate used for storing small quantities of data is NOR
NAND is the preferred technology for larger files
Can be erased and reprogrammed electronically
Is non-volatile
Flash memory is generally more expensive per gigabyte than other methods of data storage
Solid state drives:
Extremely light and portable
Have no moving parts
Much more resistant to damage from movement than hard disk drives
Renowned for high data transfer rates
Primary disadvantage is cost
Another disadvantage is limited lifespan
RAM and ROM
Two types of primary storage
Store information like code instructions to execute and files which are required by running programs
RAM:
Random access memory
A type of fast, volatile main memory
Used to store data and programs that the computer is currently using
Speeds up the computer's execution
Higher access speeds than even flash memory
More expensive per gigabyte than secondary storage devices
Computers often have only 4 or 8 GB of RAM
ROM:
Read only memory
Non-volatile
Cannot be modified
Once programmed, the state of memory cells inside does not change
Useful for storing fixed sequences of instructions like a computer's startup (bootstrap) routine
Virtual storage
Name given to storing information remotely so that it can be accessed by any computer with access to the same system, for example over the internet
Examples include cloud storage services and networked storage used in offices and schools
As internet speeds increase, virtual storage is becoming more popular
Often as abstraction of multiple devices acting like one
Disadvantages include limitations of a user's network speed and high costs