graphics-processing-unit-gpu

Graphics Processing Unit (GPU)

What is a GPU?

• In A Level Computer Science, a GPU is responsible for processing graphics within the computer to reduce the load on the CPU

• CPUs are general purpose processors whereas GPUs are designed specifically for graphics

• GPUs are likely to have built in circuitry or instructions for common graphics operations

• GPUs can perform an instruction on multiple pieces of data at one time

• This is useful when processing graphics (e.g. transforming points in a polygon or shading pixels) which means it can perform transformations to on screen graphics quicker than a CPU

• The GPU can either be part of the graphics card or embedded in the CPU

• Modern GPUs typically contain hundreds or even thousands of smaller processing cores, allowing them to perform many operations in parallel

What can a GPU be used for besides graphics?

• Besides graphics processing, a GPU can also be used for:

  • 3D modelling

    • The GPU can be used to render lighting effects, textures and shadows

  • Data modelling

    • As GPUs can handle many calculations simultaneously, they can handle large datasets and complex operations like sorting and filtering data

  • Financial modelling

    • GPUs are used to simulate different scenarios in risk modelling, option pricing and other financial modelling types

    • Lots of simulations can be run in parallel

  • Data Mining

    • Data mining is the process of analysing large amounts of data to find patterns

    • The main computational tasks are sorting, searching, pattern recognition, statistical analysis and graph algorithms

  • Performing Complex Numerical Calculations

    • Matrix multiplication and inversion can be done in parallel

    • Numerical Simulations – Physics and engineering simulations often involve solving complex maths models, which can be done in parallel

    • Solving Differential equations

    • Solving differential equations involves computations which can be performed in parallel

  • Machine learning

    • This involves training a computer on a massive amount of data which can be done in parallel. There are lots of matrix multiplications and other computations which can be performed

    • After the training, GPUs can be used to speed up the process of making predictions on new data

  • Calculations on multiple data at the same time

    • There are a number of scenarios where calculations will be needed to be carried out on multiple data at the same time e.g. insurance pricing, modelling risk, calculating bills

    • This is done by GPUs rather than CPUs due to being set up for parallel processing

What types of task are GPUs suited for?

• GPUs are suited to certain tasks that utilise:

  • Specialist instructions

    • GPUs are designed to execute specialist instructions which are common in 3D graphics rendering such as operations on matrices, vectors and geometric transformations

    • These capabilities have been expanded over time and have been generalised which makes GPUs suitable for a wide range of complex calculations besides graphics processing

  • Multiple cores 

    • Although a CPU can have multiple cores, these are optimised for serial processing

    • GPUs have smaller cores but these are optimised for parallel processing

    • GPUs can perform many calculations simultaneously – ideal for tasks that can be broken down into smaller parts

    • This is useful in machine learning and situations where large amounts of data need to be processed

  • SIMD processing

    • Single Instruction Multiple Data (SIMD) processing is computers that have multiple processing elements which perform the same operation on multiple data points simultaneously

    • GPUs support SIMD processing as they were originally designed to perform the same operations on multiple pixels or vertices simultaneously – this is a common requirement in image processing, simulations and machine learning

What are the benefits of using a GPU?

• There are a number of benefits to using a GPU as well as a CPU (it isn’t possible to only use a GPU as the CPU assigns tasks to the GPU)

  • Parallel processing

    • GPUs can handle many tasks simultaneously as they are multicore processors

  • Speed

    • As GPUs can use parallel processing, this speeds up tasks, particularly those involving large amounts of data or complex computations

  • Efficiency

    • GPUs can perform more calculations per unit of power consumed in comparison to CPUs making them more energy efficient when it comes to parallel tasks