CUDA函数可由设备或主机调用 [英] CUDA function call-able by either the device or host

问题描述

我有一个可重用的函数在一些CUDA代码，需要从设备和主机调用。是否有适当的限定符？

I have a re-useable function in some CUDA code that needs to be called from both the device and the host. Is there an appropriate qualifier for this?

例如。在这种情况下，func1的正确定义是什么：

e.g. what's the correct definition for func1 in this case:

int func1 (int a, int b) {
    return a+b;
}

__global__ devicecode (float *A) {
    int i = blockDim.x * blockIdx.x + threadIdx.x;
    A[i] = func1(i,i);
}

void main() {
    // Normal cuda memory set-up

    // Call func1 from inside main:
    int j = func1(2,4)

    // Normal cuda memory copy / program run / retrieve data
}

到目前为止，我只能通过使用函数两次来达到这个效果：一次显式为设备，一次为主机。有没有更好的方法？

So far I can only get this to work by having the function twice: once explicitly for the device and once for the host. Is there a better way?

推荐答案

从CUDA编程指南：

__ device __ 和 __ host __ 限定符可以一起使用，但是在
这种情况​​下，函数是为主机和设备编译的。

The __device__ and __host__ qualifiers can be used together however, in which case the function is compiled for both the host and the device.

这篇关于CUDA函数可由设备或主机调用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！