A graphics processing unit (GPU) is a specialized electronic circuit designed to accelerate computer graphics and image processing. GPUs can process many pieces of data simultaneously, making them useful for non-graphic calculations involving embarrassingly parallel problems. GPUs were initially designed for accelerating computer graphics and image processing, but with the introduction of new generic stream processing units, they became more generalized computing devices. GPUs are making computational inroads against the CPU, and a subfield of research, dubbed GPU computing or GPGPU for general-purpose computing on GPU, has found applications in fields as diverse as machine learning, oil exploration, scientific image processing, linear algebra, statistics, 3D reconstruction, and stock options pricing.
Traditionally, GPUs are responsible for the rendering of 2D and 3D images, animations, and video. They work by using a method called parallel processing, where multiple processors handle separate parts of the same task. GPUs are used for both professional and personal computing. There are two types of GPUs: integrated and discrete. Integrated GPUs are built into a PCs motherboard, allowing laptops to be thin, lightweight, and power-efficient. They are great for some gaming, light video editing, or working with photos. Discrete GPUs are a separate part that gets plugged into a PC. They are larger than integrated GPUs and use more power, but theyre best for heavy processing tasks like intense photo and video editing, design work, and gaming.
