/* ======================================================
   cpu-add-vector.c:

      add 2 vectors of 10000000 elements

   ====================================================== */

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

#include <sys/time.h>
struct timeval start_time, stop_time;
int    elapsed;


int main(int argc, char *argv[])
{
   int i, N;

   if ( argc == 1 )
   {
      printf("Usage: %s #elements_in_vector\n", argv[0]);
      exit(1);
   }

   N = atoi( argv[1] );     // N = # elements in vector

   float *x, *y, *z;

   /* ==========================================
      Allocate arrays to store vector x and y
      ========================================== */
   x = malloc( N*sizeof(float) );
   y = malloc( N*sizeof(float) );
   z = malloc( N*sizeof(float) );


   // initialize x and y arrays on the host
   for (i = 0; i < N; i++) 
   {
     x[i] = 1.0f;
     y[i] = 2.0f;
   }

   gettimeofday(&start_time, NULL);   // Record current sys time as start_time

   /* ===============================================
      CPU version of the vector addition algorithm
      =============================================== */
   for (i = 0; i < N; i++)
      z[i] = x[i] + y[i];

   gettimeofday(&stop_time, NULL);   // Record current sys time as stop_time

   elapsed = (stop_time.tv_sec*1000000 + stop_time.tv_usec) -
                (start_time.tv_sec*1000000 + start_time.tv_usec);
   printf("Elasped time = %d micro secs\n", elapsed);


   /* ==================================================
      Check for errors (all values should be 3.0f)
      ================================================== */
   int nErrors = 0;
   for (int i = 0; i < N; i++)
   {
      if ( fabs(z[i]-3.0f) > 0.001 )
         nErrors++;
   }

   printf("#errors = %d\n", nErrors);

   if ( N < 10 )
   {
      printf("Vector sum = ");
      for (i = 0; i < N; i++)
         printf("%f ", y[i]);
      printf("\n\n");
   }

   // Free memory
   free(x);
   free(y);
  
   return 0;
}