Simple Integer ADD program error Result is always zero

Accelerated Computing CUDA CUDA Programming and Performance
1

For all my CUDA programs i am getting the result as zero. I tested with simple integer as shown below. Can any one please see whats going wrong ?

#include <stdio.h>
#include <cuda.h>
#include <conio.h>

// Kernel that executes on the CUDA device

global void add(int a,int b,int* c)
{
*c=a+b;
}

// main routine that executes on the host

int main(void)
{
int c;
int* c_d;
size_t size = sizeof(int);
cudaMalloc((void **) &c_d, size);
//cudaMemcpy(c_d, c, size,cudaMemcpyHostToDevice);

add<<<1,2>>>(2,7,c_d);
cudaMemcpy(&c, c_d, size,cudaMemcpyDeviceToHost);  

printf("%d",c);
cudaFree(c_d);

getch();

}

Many thanks
Sheshank Kodam

2

you code works on my machine.

I think that you should check error code and
make sure that your kernel is executed.

3

hey chein

My kernel is not executed for some reason. I will check that and will get back.

Thanks

Sheshank Kodam