A Brief History Of The Evolution Of Graphics Processing Units

Words: 2260
Pages: 10

A Brief History of the Evolution of Graphics Processing Units
A graphics processing unit (GPU) is usually a dedicated processor whose main purpose is to do vast amounts of computations in order to build images to be displayed. In order to render the 3D graphics one sees in modern day games, the GPU must perform countless floating-point calculations. GPUs can be found on virtually all commonly used electronics today such as phones, computers, video game consoles, etc. The term “GPU” didn’t actually exist until 1999 when the company NVIDIA used the term while marketing their new graphics card called the GeForce 256 [3]. From the 1980’s until today, GPUs have gone through an exceptional amount of evolution with early graphics cards only
…show more content…
As shown by Figures 3 and 4, after the primitive has been rasterized, with GeForece you had no control over how the pixels were textured. There were just specific texture units that did that for you. With GeForce3, the programmer was able to add texture shaders so that they could control how the pixels were textured. In 2002, NVIDIA released its GeForce FX card, which marked the first fully programmable GPU. This allowed the programmers full access over the graphics pipeline and also allowed per-pixel operations [2]. Before this the programmer would just send data into the pipeline with some vertex programs and they had no control over the rasterization, thus had no control over what the final pixelated product looked like. With a fully programmable GPU it gave control over the rasterization procedure, which in turn let them control the whole graphics pipeline so they could produce better graphics [6]. Then in 2003, Microsoft released DirectX9, which gave developers an API to take advantage of this new hardware. While the fully programmable GPU led to better graphics improvements it was also led to the GPU being able to be used as a complete separate computational processor alongside with the CPU [3]. As figure 5 shows, the programmable fragment processor was added to the GeForce FX, allowing for complete control over the pipeline (GeForce 3 was the same