Advertisement

Graphics Processing Unit (GPU)

Last updated: November 9, 2021

What Does Graphics Processing Unit (GPU) Mean?

A graphics processing unit (GPU) is a parallel processor that allows repetitive calculations within an application to run simultaneously. GPUs were introduced towards the end of the last century to help central processing units (CPUs) keep up with the huge number of calculations required by animated video games. The GPU carried out repetitive calculations concurrently, while the rest of the application continued to run on the CPU.

As the demand for graphic applications increased towards the end of the last century, GPUs became more popular. Eventually, they became not just an enhancement but a necessity for optimum performance of a PC.

Today, GPUs are powerful enough to perform rapid mathematical calculations in parallel for deep learning algorithms and are used in just about every type of computing device, including mobile phones, tablets, display adapters, workstations and game consoles.

Advertisement

Techopedia Explains Graphics Processing Unit (GPU)

GPUs play an important role in processing redundant calculations in everything from virtual reality (VR) applications to self-driving cars. While each core in the CPU works autonomously on a different task, the GPU cores work in parallel on the iterative calculations that power machine learning (ML).

GPUs can either be embedded or discrete. Embedded GPUs, also called integrated GPUs, are located on the same chip as the CPU and share the CPU’s memory. Discrete GPUs have their own substrate and memory. When GPUs are embedded in the CPU, they connect to a computing device's random access memory (RAM) through an accelerated graphics port (AGP) or peripheral component interconnect express (PCI-Express) bus.

History of the GPU

The first GPU was developed by NVidia in 1999 and called the GeForce 256. This GPU model could process 10 million polygons per second and had more than 22 million transistors. The GeForce 256 was a single-chip processor with integrated transform, drawing and BitBLT support, lighting effects, triangle setup/clipping and rendering engines.

Features included:

  • Tast rendering of polygons in 2-D and 3-D graphics
  • Digital output to flat panel display monitors
  • Texture mapping
  • Application support for high-intensity graphics software such as AutoCAD
  • Support for YUV color space
  • Hardware overlays
  • MPEG decoding
Advertisement

Synonyms

Visual Processing Unit (VPU)

Share this Term

  • Facebook
  • LinkedIn
  • Twitter

Related Reading

Tags

HardwareArtificial Intelligence Machine LearningDeep Learning

Trending Articles

Go back to top