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

void saxpy(int n, float a, float *restrict x, float *restrict y)
{
    #pragma acc parallel loop
    for (int i = 0; i < n; ++i)
              y[i] = a*x[i] + y[i];
}

int main(void)
{
    const int n = 1 << 20;
    float *x = new float[n];
    float *y = new float[n];

    for (int i = 0; i < n; ++i) {
        x[i] = (float)i / (float)n;
        y[i] = (float)i;

        // Perform SAXPY on 1M elements
         saxpy(1<<20, 2.0, x, y);
     }
}