#include <stdio.h>
__global__ void childKernel()
{
printf("Hello ");
}
__global__ void parentKernel()
{
// launch child
childKernel<<<1,1>>>();
if (cudaSuccess != cudaGetLastError()) {
return;
}
// wait for child to complete
if (cudaSuccess != cudaDeviceSynchronize()) {
return;
}
printf("World!\n");
}
int main(int argc, char *argv[])
{
// launch parent
parentKernel<<<1,1>>>();
if (cudaSuccess != cudaGetLastError()) {
return 1;
}
// wait for parent to complete
if (cudaSuccess != cudaDeviceSynchronize()) {
return 2;
}
return 0;
}
This program may be built in a single step from the command line as follows:
$ nvcc -arch=sm_35 -rdc=true hello_world.cu -o hello -lcudadevrt
Read more at: http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#ixzz3XlLde1G5
Follow us: @GPUComputing on Twitter | NVIDIA on Facebook
如上所示，按照上面编译通过，但是不能显示在屏幕，不知哪位大牛帮忙解答一下，小弟初学cuda
