Changes

a specialized processor primarily intended for [https://en.wikipedia.org/wiki/Video_card graphic cards] to rapidly manipulate and alter [[Memory|memory]] for fast [https://en.wikipedia.org/wiki/Image_processing image processing], usually but not necessarily mapped to a [https://en.wikipedia.org/wiki/Framebuffer framebuffer] of a display. GPUs have more raw computing power than general purpose [https://en.wikipedia.org/wiki/Central_processing_unit CPUs] but need a limited, specialized and massive parallelized way of programming, not that conform with the serial nature of [[Alpha-Beta|alpha-beta]] if it is about a massive [[Parallel Search|parallel search]] in chess. Instead, [[Best-First|Best-first]] [[Monte-Carlo Tree Search|Monte-Carlo Tree Search]] (MCTS) approaches in conjunction with [[Deep Learning|deep learning]] proved a successful way to go on GPU architectures.

There are various frameworks for [https://en.wikipedia.org/wiki/General-purpose_computing_on_graphics_processing_units GPGPU], General Purpose computing on Graphics Processing Unit.Despite language wrappers and mobile devices with special APIs, there are in main three ways to make use of GPGPU.