1.1.2 Types of Processors Flashcards
What does RISC stand for?
- Reduced Instruction Set Computing
What does CISC stand for?
- Complex Instruction Set computing
What is an instruction set?
- An instruction set is written in machine code and are instructions recognisable by the CPU and executable
- Different CPU designs have different core instruction sets
What are some of the characteristics of CISC?
- Used in laptops/desktops
- Has more complex hardware
- Multiple machine cyces per instruction
- Physically larger in size and requires more silicon (expensive)
- Greater energy consumption
- More intensive tasks will do better with CISC
- Cant support pipelining
- Support a wider range of addressing modes
What are some of the characteristics of RISC?
- Used in smartphones and tablets
- Single machine cycle per instruction
- Smaller in size, less complex circuitry required, less silicon needed = cheaper
- Lower energy requirements (‘sleep mode when not processing)
- Small number of simple instructions and hardware
- Run at lower clock speed, simpler tasks faster
- Supports Pipelining
Exam Question: As well as a CPU the console contains a GPU for 3D graphics. Explain why a GPU is more suitable than a CPU for this task.
- CPUs are general purpose processors (1) whereas GPUs are designed specifically for graphics (1).
- And so likely to have built in circuitry / instructions for common graphics operations (1).
- GPUs are able to perform an instruction on multiple pieces of data at one time (1) often we want to do this when processing graphics (e.g. transforming points in a polygon or shading pixels) (1)
What is Pipelining?
- The output of 1 instruction is the input of the next
- While one instruction is being executed, another can be decoded and another fetched.
- Pipelining is aimed to reduce the amount of the CPU which is kept idle.
What are Multi-core systems
- 1 method of Increasing Processing Speed is to increase the number of cores. There are 2 ways to organise cores:
- Parallel Systems
- Co-Processors
In a Parallel System the computational problem should be able to:
- 2 or more processors work together to complete a task
- Be broken apart into discrete pieces of work and can be solved simultaneously
- Execute multiple program instructions at any time
- Be solved in less time with multiple computer resources
Parallel Systems can be placed into 1 of 3 categories:
- Single instruction, multiple data (SIMD system)
- Multiple Instruction, single data (MISD system)
- Multiple Instructions, multiple data (MIMD system)
What is a Single Instruction, Multiple Data
- Single Instruction - Multiple processors follow/ execute the same set of instructions at any given clock cycle
- Multiple Data - Each processing unit takes a different set of data.
SIMD process lots of different data concurrently using the same algorithm.
What is Multiple Instruction, Single Data
- Multiple Instruction - Multiple processors. Each one operates on the data independently via separate instruction streams
- Single Data - A single data stream is fed into multiple processing units
perform different operations on the same data.
What is Multiple Instruction, Multiple Data
- Multiple Instruction - Multiple processors. Each one could be executing a different instruction stream independently of the others
- Multiple data - Every processor may be working with a different data stream
Can process a number of different instructions simultaneously. Currently the most common type of parallel computers
What is a Co- Processor
- Are additional processors which are designed for very specific tasks only (graphics processing or mathematical operations.
- The co-processor and central processor operate on different tasks at the same time which speeds up the overall execution
- However a co-processor operate on its own right. A CPU can
What are the advantages of Multi-Core Systems
- More jobs can be done in a shorter time = executed simultaneously
- Tasks can be shared to reduce the load on individual processors + avoid bottlenecks
What are the disadvantages of Multi-Systems
- Difficult to write programs, ensuring each task has the correct input data to work on.
- Results from different processors need to be combined adds to time taken to execute program
- Not all tasks can be split across multiple processors
- Additional complexity of implementing
What are examples of co-processors
- Floating point units (FPU) : Built into the main CPU and run floating point mathematical operations.
- Digital Signal Processor (DSP) : Commonly used to to process sound effects and merge sound channels ao they can output in stereo and surround sound.
- Graphics Processing unit (GPU) : Complete big 3D calculations needed for games and effects.
Exam Question: Describe 1 difference between RISC and CISC.
- More than one clock cycle for each instruction in CISC … …one clock cycle for each instruction in RISC
- CISC architecture has complex circuitry and is therefore more expensive to manufacture… …RISC architecture has simple circuitry minimising manufacture cost.
- Some instructions in CISC will rarely get used … … In RISC instructions are used regularly
Exam Question: Explain two reasons why games designed for other companies’ consoles may not work on this machine
-
Different consoles will have different processors
- each with their own instruction sets and word sizes.
-
Different consoles have different operating systems
- and so games may be dependent on libraries in one operating system that don’t exist in another or may make different system calls
-
Games might be on a different media
- for example, might be on Blu-ray when console may only have a DVD player
Exam Question: Describe 1 advantage to the company of using RISC over CISC.
Programs run faster… …due to simpler instructions
Costs less to design/produce
Cause it has fewer/ simpler instructions
Exam Question: Compare a Complex Instruction Set Computer (CISC) architecture with a Reduced Instruction Set Computer (RISC) architecture.
- CISC:
- Each instruction may take multiple cycles.
- Single register set Instructions have variable format
- Many instructions are available
- Many addressing modes are available
- Complicated processor design Integrated circuit is expensive
- RISC:
- An instruction performs a simple task
- Limited number of instructions available
- Complex tasks can only be performed by combining multiple instructions
- Simple processor design
Discuss the different approaches that can be taken to provide increasingly larger amounts of computing power and the types of problem they are suited to
- Knowledge:
- Processors can have multiple cores
- Processors have increasingly large clock speeds and can be overclocked
- GPUs can be applied to problems other than graphics processing
- Application
- Having multiple cores can speed up smaller problems but this will not be enough for larger problems
- GPUs tend to have large number of cores so can run on highly paralleliseable problems… …but only where the same instruction is being applied to multiple pieces of data
- Evaluation:
- Increased clock speed is limited to smaller problems
- Parallel processing isn’t suited to all problems - writing algorithms = hard
- GPUs only good where the same calculation is repeated on multiple data sets
Exam Question: Explain why using a RISC processor rather than a CISC processor is likely to result in increased battery life.
- RISC has a smaller instruction set (than CISC)
- Requires fewer transistors / less complex circuitry
- Means less power is required.
