#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include <math.h>
#include <accelmath.h>
#include <openacc.h>
#include "timer.h"

int main( int argc, char* argv[] )
{
    int n;      /* size of the vector */
    float *restrict a;  /* the vector */
    float *restrict r;  /* the results */
    float *restrict e;  /* expected results */
    float s, c;
    struct timeval t1, t2, t3;
    double cgpu, chost;
    int i;
    if( argc > 1 )
        n = atoi( argv[1] );
    else
        n = 100000;
    if( n <= 0 ) n = 100000;

    a = (float*)malloc(n*sizeof(float));
    r = (float*)malloc(n*sizeof(float));
    e = (float*)malloc(n*sizeof(float));
    for( i = 0; i < n; ++i ) a[i] = (float)(i+1) * 2.0f;
    /*acc_init( acc_device_nvidia );*/

	StartTimer();
    #pragma data copyin(a[0:n]), copyout(r)
    {
		#pragma acc kernels
        #pragma acc loop gang, vector(128)
        for( i = 0; i < n; ++i ){
	    s = sinf(a[i]);
	    c = cosf(a[i]);
	    r[i] = s*s + c*c;
	}
    }
	cgpu = GetTimer();
	StartTimer();
        for( i = 0; i < n; ++i ){
	    s = sinf(a[i]);
	    c = cosf(a[i]);
	    e[i] = s*s + c*c;
	}
	chost = GetTimer();
    /* check the results */
    for( i = 0; i < n; ++i )
        assert( fabsf(r[i] - e[i]) < 0.000001f );
    printf( "%13d iterations completed\n", n );
    printf( "%13g microseconds on GPU\n", cgpu*1000 );
    printf( "%13g microseconds on host\n", chost*1000 );
    return 0;
}