Is it necessary to use nvidia(gpu) graphics card to build cuda environment? Is intel or ati graphics card ok?

Nvidia(gpu) graphics card is necessary to build cuda environment.

CUDA is mainly aimed at NVIDIA's GPU. Nvidia also introduced CUDA X86, which made the code of duCUDA executable on X86 processor, although this only improved the code compatibility of CUDA. Neither Intel nor AMD's display chips can be programmed with CUDA.

If you want to build a cuda environment under Windows8. 1 and use GPU to run in parallel, you must have an Nvidia graphics card that supports GPU to run in parallel and install CUDA. Never use Intel or AMD graphics cards on your computer, but write CUDA.

Extended data

CUDA (Compute Unified Device Architecture) is a computing platform launched by NVIDIA, a graphics card manufacturer. CUDA? It is a general parallel computing architecture introduced by NVIDIA, which enables GPU to solve complex computing problems. ?

It includes CUDA instruction set architecture (ISA) and parallel computing engine inside GPU. Can developers do CUDA in C language now? C language is the most widely used advanced programming language.

The program written in this way can support CUDA? Run at ultra-high performance on the processor. Other languages will be supported in the future, including FORTRAN and C++.

Based on the competitive relationship between A and N, A will definitely not get the patent authorization.

Baidu Encyclopedia-NVIDIA