hello CUDA

#include< stdio.h>
#include <iostream>
#include "cuda_runtime.h"  
#include "device_launch_parameters.h"  

// Kernel definition
__global__ void VecAdd(float* A, float* B, float* C)
{
	int i = threadIdx.x;
	C[i] = A[i] + B[i];
}
__global__ void VecSub(float* A, float* B, float* C)
{
	int i = threadIdx.x;
	C[i] = A[i] - B[i];
}
__global__ void VecMul(float* A, float* B, float* C)
{
	int i = threadIdx.x;
	C[i] = A[i] * B[i];
}
int main()  
{  
	float a[3]={86,1,2};
	float b[3]={2,1,7};
	float c[3]={};
	float *A;
	float *B;
	float *C;
	
	cudaMalloc((void**)&A,3*sizeof(float));
	cudaMalloc((void**)&B,3*sizeof(float));
	cudaMalloc((void**)&C,3*sizeof(float));

	cudaMemcpy(A,a,3*sizeof(float),cudaMemcpyHostToDevice);
	cudaMemcpy(B,b,3*sizeof(float),cudaMemcpyHostToDevice);
	VecMul<<<1,3>>>(A, B, C);
	
	cudaMemcpy((void**)&c,C,3*sizeof(float),cudaMemcpyDeviceToHost);
	std::cout<<c[0]<<","<<c[1]<<","<<c[2]<<std::endl;
	printf("Hello CUDA\n");  
	return 0;  
}