如何调用CUDA内核中的主机函数？ [英] How to call a host function in a CUDA kernel?

问题描述

正如以下错误所暗示的，在内核中不允许调用主机函数（'rand'），我不知道是否有解决方案，如果我需要这样做。

 错误：不允许从__device __ / __ global__函数（xS_v1_cuda）调用主机函数（rand）
  __ device__的函数。 
 修饰符。如果您在设备代码中需要随机数字，请查看cuda随机生成器 curand   http://developer.nvidia.com/ curand  
 
 
 
如果您有自己的主机函数要从内核调用使用 __ host __ 和 __ device __ 修饰符：
  __ host__ __device__ int add int a，int b）
 {
 return a + b; 
} 
  
 
 
当此文件由NVCC编译器驱动程序编译时，编译：一个可由主机代码调用，另一个可由设备代码调用。这就是为什么现在可以通过主机和设备代码调用此函数。
 
As the following error implies, calling a host function ('rand') is not allowed in kernel, and I wonder whether there is a solution for it if I do need to do that.
error: calling a host function("rand") from a __device__/__global__ function("xS_v1_cuda") is not allowed

解决方案
Unfortunately you can not call functions in device that are not specified with __device__ modifier. If you need in random numbers in device code look at cuda random generator curand http://developer.nvidia.com/curand 

If you have your own host function that you want to call from a kernel use both the __host__ and __device__ modifiers on it:
__host__ __device__ int add( int a, int b )
{
    return a + b;
}
When this file is compiled by the NVCC compiler driver, two versions of the functions are compiled: one callable by host code and another callable by device code. And this is why this function can now be called both by host and device code.

                        
这篇关于如何调用CUDA内核中的主机函数？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！