main.cu

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

#include "./common/book.h"


#include <iostream>
#include <math.h>
// Kernel function to add the elements of two arrays
__global__
void add(int n, float *x, float *y)
{
    for (int i = 0; i < n; i++)
        y[i] = x[i] + y[i];
}

int main(void)
{
    int N = 20;
    float *x, *y;

    // Allocate Unified Memory – accessible from CPU or GPU
    cudaMallocManaged(&x, N*sizeof(float));
    cudaMallocManaged(&y, N*sizeof(float));

    // initialize x and y arrays on the host
    for (int i = 0; i < N; i++) {
        x[i] = (float)i;
        y[i] = (float)i + (float)i ;
    }

    // Run kernel on 1M elements on the GPU
    add<<<1, 1>>>(N, x, y);
    cudaError_t err = cudaGetLastError();
    if (err != cudaSuccess)
        printf("Error running data: %s\n", cudaGetErrorString(err));

    // Wait for GPU to finish before accessing on host
    cudaDeviceSynchronize();

    // Check for errors (all values should be 3.0f)
    float maxError = 0.0f;
    for (int i = 0; i < N; i++)
//        maxError = fmax(maxError, fabs(y[i]-3.0f));
        std::cout << "data " << i << ":  val: " << y[i] << std::endl;

    // Free memory
    cudaFree(x);
    cudaFree(y);

    return 0;
}