CUDA

Nvidia CUDA web site : https://developer.nvidia.com/cuda-downloads

This hello world is a real cuda hello world, as it really test if the compilation worked properly and if the system used the NVIDIA card. All other results than the one expected means that the system did not use the GPU but only the CPU or something else.

// This is the REAL "hello world" for CUDA!
// It takes the string "Hello ", prints it, then passes it to CUDA with an array
// of offsets. Then the offsets are added in parallel to produce the string "World!"
// By Ingemar Ragnemalm 2010
 
#include <stdio.h>
 
const int N = 16; 
const int blocksize = 16; 
 
__global__ 
void hello(char *a, int *b) 
{
	a[threadIdx.x] += b[threadIdx.x];
}
 
int main()
{
	char a[N] = "Hello \0\0\0\0\0\0";
	int b[N] = {15, 10, 6, 0, -11, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 
	char *ad;
	int *bd;
	const int csize = N*sizeof(char);
	const int isize = N*sizeof(int);
 
	printf("%s", a);
 
	cudaMalloc( (void**)&ad, csize ); 
	cudaMalloc( (void**)&bd, isize ); 
	cudaMemcpy( ad, a, csize, cudaMemcpyHostToDevice ); 
	cudaMemcpy( bd, b, isize, cudaMemcpyHostToDevice ); 
 
	dim3 dimBlock( blocksize, 1 );
	dim3 dimGrid( 1, 1 );
	hello<<<dimGrid, dimBlock>>>(ad, bd);
	cudaMemcpy( a, ad, csize, cudaMemcpyDeviceToHost ); 
	cudaFree( ad );
	cudaFree( bd );
 
	printf("%s\n", a);
	return EXIT_SUCCESS;
}