1.1 systems architecture

• CPU


  Fetches, decodes and executes instructions
• Fetch


  1. The address of the next instruction is copied from the program counter and placed in the MAR

  2. The MAR now contains a memory address, the data that is stored at that address is copied to the MDR

  3. The program counter is incremented to point to the next instruction to be processed in the program, ready for the next cycle
• Decode


  The MDR now contains either data fetched from memory or an instruction. The control unit decodes the instruction to see what to do
• Execute


  The decoded instruction is executed. This might mean performing a calculation using the ALU
• ALU


  • Add, subtract, repeated addition (multiply), repeated subtraction (division)
  • AND, OR, XOR, NOT operations
  • Binary shift operations
• Control Unit


  • Co-ordinate the activity of the CPU
  • Sending out control signals to control/synchronise how data moves around the parts of the CPU and memory
  • Decoding instructions
• Cache Memory


  • Most frequently used instructions are copied here to reduce the time needed to fetch instructions from the RAM
• Registers


  • Memory locations within the CPU that hold specific pieces of data temporarily and can be accessed very quickly
• Von Neumann architecture


  A computer in which the data and instructions are stored in the same area of memory
• Memory address register (MAR)


  • Stores the address of the data to be fetched from, or the address where the data is to be stored
• Memory data register (MDR)


  • Stores the data itself which has been read from main memory or is about to be written to main memory
• Program Counter


  • Stores the address of the next instruction to be fetched from memory. (Which sends the value to the MAR) This counter increments by 1 in each FDE cycle
• Accumulator


  • Stores the results of calculations
• Clock Speed


  The speed at which the CPU fetches and executes instructions, measured in hertz (Hz) or number of times per second
• CPU's usually work at speeds of up to 4GHz (or 4 billion instructions per second)
• Faster clock speed


  More instructions can be executed every second, meaning the program takes less time to run
• Cache Size


  • Cache memory is located between the main memory and the CPU, it is used to hold data that needs to be accessed very quickly
  • Accessing cache memory is much faster than accessing main memory (RAM)
  • The more data that can be stored in cache memory rather than main memory, the faster and more efficient the process
  • Cache memory is very expensive
• Number of processor cores

  • Each core can fetch and execute instructions independently so a multiple core processor can handle several instructions at the same time
  • Multiple cores can work on separate programs or parts of a program at the same time, but this is only possible if the program has been written to take advantage of multiple cores
• Embedded system


  • A computer system that has been designed for a dedicated function
  • Embedded systems are often manufactured as a single chip
  • The dedicated hardware and software make embedded systems more robust and reliable than general-purpose computers
  • Designed and engineered to perform a limited set of tasks to reduce size and improve performance
  • Low power consumption to operate from a small power source
  • Small in size and low cost