1.1 Systems architecture

1.1 Systems architecture

1. Embedded Systems

   • An embedded system is a system that has software embedded into hardware, usually for a specific purpose
   • Examples
     • Washing Machine
     • Mobile Phones
     • ATMs
     • Thermostats
     • Vending Machines
     • Modern Dashboards in Cars
     • Supermarket checkouts

2. What is a CPU?

   • The CPU is the brain of the computer
   • The CPU is where the processing takes place, and modern processors based on von Neumann architecture or structure.
   • Also known as a microprocessor

3. Von Neumann architecture:

   • Program Counter
     • This continuously provides the CPU with the memory address of the next instruction in the cycle to be carried out.
   • MDR
     • Memory Data Register
     • An instruction or piece of data that is fetched from memory is temporarily stored here until it is used.
   • MAR
     • Memory Address Register
     • This is the location address in the memory of the next piece of data or instruction that the CPU needs to fetch or execute.
   • Accumulator
     • This is where the results of calculations carried out by the ALU are temporarily stored until they are needed.
   • These are used to store numbers .

4. CPU components

   • ALU
     • Arithmetic Logic Unit
     • The ALU is divided into two units, an arithmetic unit (AU) and a logic unit (LU).
     • This is where calculations are carried out, including mathematical tasks, logic tests, and data comparisons.
   • CU
     • Control Unit
     • This tells different parts of the CPU what to do.
   • Cache
     • This stores frequently requested instructions.
     • There are 3 levels
       • Level One (2KB – 64KB) Instructions are first searched in this cache. L1 cache very small in comparison to others, thus making it faster than the rest.
       • Level Three (1MB -8MB) With each cache miss, it proceeds to the next level cache. 3 is the largest among the all the cache, so it's slower, but it's still faster than the RAM.
       • Level Two (256KB - 512KB) If the instructions are not present in the L1 cache then it looks in the L2 cache, which is a slightly larger pool of cache, thus accompanied by some latency.

5. Fetch Execute Cycle

   • This cycle does exactly as it says. It fetches the instructions, decodes them, then executes them.
   • The CPU can differentiate between data and instructions. Each opcode will consist of an instruction of N bites, which then expects the subsequent M bytes to be data. So the CPU uses each opcode to determine how many of the following bytes are data, and how many are instructions.

6. Performance of a CPU

   • Performance of a CPU is the amount of work accomplished by a computer system.
   • Clock Speed
     • CPUs have a clock, which keeps all operations in sync. The clock speed refers to the number of times per second the clock “ticks”. Clock speed is measured in Hertz “Hz”.
   • Cache Size
     • Cache size refers to how big the cache memory is. The more there is, the more frequently-accessed instructions can be stored.
   • Number of Cores
     • Number of cores refers to the number of processors inside a CPU chip. There are two main types of cores: Physical + Logical
   • More expensive, high tech computers often have a higher clock speed, larger cache sizes and a higher number of cores

Bilder und Dateien der Mindmap