CUDA是硬件需要在编译时？ [英] Is CUDA hardware needed at compile time?

问题描述

是与 NVCC 编译CUDA程序必须（在Linux中）安装CUDA的显卡？或者，我们可以随处编译方案，只有在这样的系统上运行？

Is installed CUDA capable graphics card necessary (in Linux) for compiling CUDA programs with nvcc? Or one can compile programs everywhere and run only on such systems?

推荐答案

没有，显卡是没有必要的编译。

No, a graphics card is not necessary for compilation.

您甚至不需要一个运行的程序;你可以把它的软件仿真。

You don't even need one to run the program; you can have it emulated in software.

更新确定，很显然，SW仿真之后，还没有CUDA 3.0的支持。

UPDATE Ok, apparently, SW emulation hasn't been supported since CUDA 3.0.

这篇关于CUDA是硬件需要在编译时？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！