Can I call CUDA runtime function from C++ code not compiled by nvcc?

Question

Is there any way I can call CUDA runtime function calls such as

cudaMemcpy(...);

in a .cpp file, compiled with a regular C++ compiler?

Answer 1

EDIT: There was an example here but it's not longer found, but most of the example was copied below.

The caller C (but could be C++)

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <cuda.h>

extern void kernel_wrapper(int *a, int *b);

int main(int argc, char *argv[])
{
   int a = 2;
   int b = 3;

   kernel_wrapper(&a, &b);

   return 0;
}

The Callee (CUDA)

__global__ void kernel(int *a, int *b)
{
   int tx = threadIdx.x;

   switch( tx )
   {
case 0:
    *a = *a + 10;
    break;
case 1:
    *b = *b + 3;
    break;
default:
    break;
   }
}

void kernel_wrapper(int *a, int *b)
{
   int *d_1, *d_2;
   dim3 threads( 2, 1 );
   dim3 blocks( 1, 1 );

   cudaMalloc( (void **)&d_1, sizeof(int) );
   cudaMalloc( (void **)&d_2, sizeof(int) );

   cudaMemcpy( d_1, a, sizeof(int), cudaMemcpyHostToDevice );
   cudaMemcpy( d_2, b, sizeof(int), cudaMemcpyHostToDevice );

   kernel<<< blocks, threads >>>( a, b );

   cudaMemcpy( a, d_1, sizeof(int), cudaMemcpyDeviceToHost );
   cudaMemcpy( b, d_2, sizeof(int), cudaMemcpyDeviceToHost );

   cudaFree(d_1);
   cudaFree(d_2);
}