/*-----------------------------------------------------------------------*/
/* Program: VStream                                                       */
/* Revision: $Id: istream.c,v 1.0 2007/02/19 23:57:39 mccalpin Exp mccalpin $ */
/* Original code developed by John D. McCalpin                           */
/* Programmers: John D. McCalpin                                         */
/*              Joe R. Zagar                                             */
/*              Steve Poole                                              */
/*                                                                       */
/* This program measures memory transfer rates in MB/s for simple        */
/* computational kernels coded in C.                                     */
/*-----------------------------------------------------------------------*/
/* Copyright 1991-2005: John D. McCalpin                                 */
/*-----------------------------------------------------------------------*/
/*                                                                       */
/* This is a hack of the cstream program by John                         */
/*                                                                       */
/* License:                                                              */
/*  1. You are free to use this program and/or to redistribute           */
/*     this program.                                                     */
/*  2. You are free to modify this program for your own use,             */
/*     including commercial use, subject to the publication              */
/*     restrictions in item 3.                                           */
/*  3. You are free to publish results obtained from running this        */
/*     program, or from works that you derive from this program,         */
/*     with the following limitations:                                   */
/*     3a. In order to be referred to as "STREAM benchmark results",     */
/*         published results must be in conformance to the STREAM        */
/*         Run Rules, (briefly reviewed below) published at              */
/*         http://www.cs.virginia.edu/stream/ref.html                    */
/*         and incorporated herein by reference.                         */
/*         As the copyright holder, John McCalpin retains the            */
/*         right to determine conformity with the Run Rules.             */
/*     3b. Results based on modified source code or on runs not in       */
/*         accordance with the STREAM Run Rules must be clearly          */
/*         labelled whenever they are published.  Examples of            */
/*         proper labelling include:                                     */
/*         "tuned STREAM benchmark results"                              */
/*         "based on a variant of the STREAM benchmark code"             */
/*         Other comparable, clear and reasonable labelling is           */
/*         acceptable.                                                   */
/*     3c. Submission of results to the STREAM benchmark web site        */
/*         is encouraged, but not required.                              */
/*  4. Use of this program or creation of derived works based on this    */
/*     program constitutes acceptance of these licensing restrictions.   */
/*  5. Absolutely no warranty is expressed or implied.                   */
/*                                                                       */
/*-----------------------------------------------------------------------*/
/*                                                                       */

# include <stdio.h>
# include <unistd.h>
# include <stdlib.h>
# include <math.h>
# include <float.h>
# include <limits.h>
# include <sys/time.h>

/* INSTRUCTIONS:
 *
 *	1) Stream requires a good bit of memory to run.  Adjust the
 *          value of 'N' (below) to give a 'timing calibration' of 
 *          at least 20 clock-ticks.  This will provide rate estimates
 *          that should be good to about 5% precision.
 */

/*
**  These are defined for the "static" allocations
**  Default is R*8
*/

#if defined (IBY4)
# define MY_MAX_N     2000000
# define NTIMES	      10
# define OFFSET	      0
# define NUM_TESTS    5
# define MY_DATA_SIZE long
# define MY_DATA_TYPE "long"
# define MY_OP        <<
# define MY_ZERO      0L
# define MY_ONE       1L
# define MY_TWO       2L
# define MY_THREE     3L
#elif defined (IBY8)
# define MY_MAX_N     2000000
# define NTIMES	      10
# define OFFSET	      0
# define NUM_TESTS    5
# define MY_DATA_SIZE long long
# define MY_DATA_TYPE "long long"
# define MY_OP        <<
# define MY_ZERO      0LL
# define MY_ONE       1LL
# define MY_TWO       2LL
# define MY_THREE     3LL
#elif defined (RBY4)
# define MY_MAX_N     2000000
# define NTIMES	      10
# define OFFSET	      0
# define NUM_TESTS    4
# define MY_DATA_SIZE float
# define MY_DATA_TYPE "float"
# define MY_ZERO      0.0e0
# define MY_ONE       1.0e0
# define MY_TWO       2.0e0
# define MY_THREE     3.0e0
#elif defined (RBY8)
# define MY_MAX_N     2000000
# define NTIMES	      10
# define OFFSET	      0
# define NUM_TESTS    4
# define MY_DATA_SIZE double
# define MY_DATA_TYPE "double"
# define MY_ZERO      0.0e0
# define MY_ONE       1.0e0
# define MY_TWO       2.0e0
# define MY_THREE     3.0e0
#endif

/*
 *	3) Compile the code with full optimization.  Many compilers
 *	   generate unreasonably bad code before the optimizer tightens
 *	   things up.  If the results are unreasonably good, on the
 *	   other hand, the optimizer might be too smart for me!
 *
 *         Try compiling with:
 *               cc -O stream_omp.c -o stream_omp
 *
 *         This is known to work on Cray, SGI, IBM, and Sun machines.
 *
 *
 *	4) Mail the results to mccalpin@cs.virginia.edu and
 *                             benchmarks@ornl.gov
 *	   Be sure to include:
 *		a) computer hardware model number and software revision
 *              b) compiler used (-v or -version works on many compilers)
 *		c) the compiler flags
 *              d) if possible, as much info on the system as can be obtained.
 *                 On most Linux boxes, /proc/meminfo and /proc/cpuinfo will give
 *                 very useful information. hwinfo is also usefule, if available.
 *                 On a Mac, you can use "system_profiler >& my_info" and include
 *                 that information in the mail.
 *		e) all of the output from the test case(s).
 * Thanks!
 *
 */

# define HLINE "-------------------------------------------------------------\n"

# ifndef MIN
# define MIN(x,y) ((x)<(y)?(x):(y))
# endif

# ifndef MAX
# define MAX(x,y) ((x)>(y)?(x):(y))
# endif

static MY_DATA_SIZE	a[ MY_MAX_N + OFFSET ],
			b[ MY_MAX_N + OFFSET ],
			c[ MY_MAX_N + OFFSET ],
			d[ MY_MAX_N + OFFSET ],
			e[ MY_MAX_N + OFFSET ];

static double	avgtime[5] = {0}, maxtime[NUM_TESTS] = {0},
		mintime[5] = {FLT_MAX,FLT_MAX,FLT_MAX,FLT_MAX,FLT_MAX};

static char	*label[5] = {"Copy:      ", "Scale:     ",
    "Add:       ", "Triad:     ", "SScale     "};

static MY_DATA_SIZE	bytes[5] = {
    				     2 * sizeof(MY_DATA_SIZE) * MY_MAX_N,
    				     2 * sizeof(MY_DATA_SIZE) * MY_MAX_N,
    				     3 * sizeof(MY_DATA_SIZE) * MY_MAX_N,
    				     3 * sizeof(MY_DATA_SIZE) * MY_MAX_N,
    				     2 * sizeof(MY_DATA_SIZE) * MY_MAX_N
    			   	   };

extern double mysecond();
extern void   checkSTREAMresults();
extern int    checktick();

long N=MY_MAX_N;

#ifdef TUNED
extern void tuned_STREAM_Copy();
extern void tuned_STREAM_Add();
extern void tuned_STREAM_Scale(MY_DATA_SIZE scalar);
extern void tuned_STREAM_SScale(MY_DATA_SIZE scalar);
extern void tuned_STREAM_Triad(MY_DATA_SIZE scalar);
#endif

#ifdef _OPENMP
extern int omp_get_num_threads();
#endif

int main(int argc, char** argv)
{
/*
    int				quantum, checktick();
*/
    int				quantum;
    int				BytesPerWord;

    char                	*cvalue = NULL;
    int                 	aflag   = 0;
    int                 	bflag   = 0;
    int                 	index , g;

    register int		j, k;
    register MY_DATA_SIZE 	scalar;
    double			rscalar, t, times[NUM_TESTS][NTIMES];

    /* --- SETUP --- determine precision and check timing --- */

    printf(HLINE);
    printf("VSTREAM version $Revision: 1.0 $\n");
    printf(HLINE);

/*
** Get the options
*/

   opterr = 0;

   while ((g = getopt (argc, argv, "se:")) != -1)
     switch (g)
     {
       case 's':
         aflag = 1;
         break;
       case 'e':
         bflag = 1;
         break;
       case '?':
         if (isprint (optopt))
           fprintf (stderr, "Unknown option `-%c'.\n", optopt);
         else
           fprintf (stderr,
                    "Unknown option character `\\x%x'.\n",
                    optopt);
         return 1;
       default:
         abort ();
     }

/*
**
*/

    BytesPerWord = sizeof(MY_DATA_SIZE);
    printf("The data type is %s\n",MY_DATA_TYPE);
    printf("This system uses %d bytes per Element being tested.\n",
	    BytesPerWord);

    printf(HLINE);
    printf("Array size = %d, Offset = %d\n" , N, OFFSET);
    printf("Total memory required = %.1f MB.\n",
	  (3.0 * BytesPerWord) * ( (float) N / 1048576.0));
    printf("Each test is run %d times, but only\n", NTIMES);
    printf("the *best* time for each is used.\n");

#ifdef _OPENMP
    printf(HLINE);
#pragma omp parallel 
    {
#pragma omp master
	{
	    k = omp_get_num_threads();
	    printf ("OpenMP invoked: This is the MASTER Routine\n");
	    printf ("Number of Threads requested = %i\n",k);
        }
    }
#endif

    printf(HLINE);
#pragma omp parallel
    {
    printf ("Printing one line per active thread....\n");
    }

    /* Get initial value for system clock. */
#pragma omp parallel for
    for (j=0; j<N; j++) {
	a[j] = MY_ONE;
	b[j] = MY_TWO;
	c[j] = MY_ZERO;
	d[j] = MY_ONE;
	e[j] = MY_ZERO;
	}

    printf(HLINE);

    if  ( (quantum = checktick()) >= 1) 
	printf("Your clock granularity/precision appears to be "
	       "%d microseconds.\n", quantum);
    else {
	printf("Your clock granularity appears to be "
	       "less than one microsecond.\n");
	quantum = 1;
    }

    t = mysecond();

#pragma omp parallel for
    for (j = 0; j < N; j++)
	a[j] = MY_TWO * a[j];

    t = 1.0E6 * (mysecond() - t);

    printf("Each test below will take on the order"
	   " of %d microseconds.\n", (long) t  );
    printf("   (= %d clock ticks)\n", (long) (t/quantum) );
    printf("Increase the size of the arrays if this shows that\n");
    printf("you are not getting at least 20 clock ticks per test.\n");

    printf(HLINE);

    printf("WARNING -- The above is only a rough guideline.\n");
    printf("For best results, please be sure you know the\n");
    printf("precision of your system timer.\n");
    printf(HLINE);
    
/*	
**
**  --- MAIN LOOP --- repeat test cases NTIMES times --- 
**
*/

    scalar = MY_THREE;

    for (k=0; k<NTIMES; k++)
    {
	times[0][k] = mysecond();

/*
**  Copy
*/

#ifdef TUNED
        tuned_STREAM_Copy();
#else
#pragma omp parallel for
	for (j=0; j<N; j++)
	    c[j] = a[j];
#endif
	times[0][k] = mysecond() - times[0][k];
	times[1][k] = mysecond();

/*
**  Scale
*/

#ifdef TUNED
        tuned_STREAM_Scale(scalar);
#else
#pragma omp parallel for
	for (j=0; j<N; j++)
	    b[j] = scalar * c[j];
#endif
	times[1][k] = mysecond() - times[1][k];
	times[2][k] = mysecond();

/*
**  Add
*/

#ifdef TUNED
        tuned_STREAM_Add();
#else
#pragma omp parallel for
	for (j=0; j<N; j++)
	    c[j] = a[j] + b[j];
#endif
	times[2][k] = mysecond() - times[2][k];
	times[3][k] = mysecond();

/*
** Triad
*/

#ifdef TUNED
        tuned_STREAM_Triad(scalar);
#else
#pragma omp parallel for
	for (j=0; j<N; j++)
	    a[j] = b[j] + scalar * c[j];
#endif
	times[3][k] = mysecond() - times[3][k];
	times[4][k] = mysecond();

/*
** SScale
*/

#if defined( IBY4) || defined( IBY8 )
#ifdef TUNED
        tuned_STREAM_SScale(scalar);
#else
#pragma omp parallel for
	for (j=0; j<N; j++)
	    e[j] = d[j] << scalar;
#endif
	times[4][k] = mysecond() - times[4][k];
#endif
	
    }

/*
**  End of main loop
*/

/*
** --- SUMMARY --- 
*/

    for (k=1; k<NTIMES; k++) /* note -- skip first iteration */
    {
	for (j=0; j<NUM_TESTS; j++)
	{
	    avgtime[j] = avgtime[j] + times[j][k];
	    mintime[j] = MIN(mintime[j], times[j][k]);
	    maxtime[j] = MAX(maxtime[j], times[j][k]);
        }
    }
    
    printf("Function      Rate (MB/s)   Avg time     Min time     Max time\n");
    for (j=0; j<NUM_TESTS; j++) 
    {
	avgtime[j] = avgtime[j] / (double)(NTIMES-1);

	printf("%s %11.4f  %11.4f  %11.4f  %11.4f\n", 
                label[j],
	           1.0E-06 * (double) bytes[j] / mintime[j],
	                   avgtime[j],
	                           mintime[j],
	                                   maxtime[j]);
    }
    printf(HLINE);

/*
**  --- Check Results ----- 
**  --- For R84 and R*8 ---
*/

#if defined (RBY4) || defined (RBY8)

    checkSTREAMresults();

#endif

    printf(HLINE);

    return 0;
}

/*
**
**  =================== Ancillary Routines ================
**
*/

# define	M	20

int checktick()
{
    int		i, minDelta, Delta;
    double	t1, t2, timesfound[M];

/*  
**  Collect a sequence of M unique time values from the system. 
*/

    for (i = 0; i < M; i++) {
	t1 = mysecond();
	while( ((t2=mysecond()) - t1) < 1.0E-6 )
	    ;
	timesfound[i] = t1 = t2;
	}

/*
 * Determine the minimum difference between these M values.
 * This result will be our estimate (in microseconds) for the
 * clock granularity.
 */

    minDelta = 1000000;
    for (i = 1; i < M; i++) {
	Delta = (int)( 1.0E6 * (timesfound[i]-timesfound[i-1]));
	minDelta = MIN(minDelta, MAX(Delta,0));
    }

   return(minDelta);
}



/* 
**  A gettimeofday routine to give access to the wall
**  clock timer on most UNIX-like systems.  
*/

#include <sys/time.h>

double mysecond()
{
        struct timeval tp;
        struct timezone tzp;
        int i;

        i = gettimeofday(&tp,&tzp);
        return ( (double) tp.tv_sec + (double) tp.tv_usec * 1.e-6 );
}

void checkSTREAMresults ()
{
	double aj,bj,cj,scalar;
	double asum,bsum,csum;
	double epsilon;
	int	j,k;

    /* reproduce initialization */

	aj = (double) MY_ONE;
	bj = (double) MY_TWO;
	cj = (double) MY_ZERO;

    /* a[] is modified during timing check */

	aj = (double) MY_TWO * aj;

    /* now execute timing loop */

	scalar = (double) MY_THREE;

	for (k=0; k<NTIMES; k++)
        {
            cj = aj;
            bj = scalar * cj;
            cj = aj + bj;
            aj = bj + scalar * cj;
        }

	aj = aj * (double) (N);
	bj = bj * (double) (N);
	cj = cj * (double) (N);

	asum = (double) MY_ZERO;
	bsum = (double) MY_ZERO;
	csum = (double) MY_ZERO;

	for (j=0; j<N; j++) {
		asum += (double) a[j];
		bsum += (double) b[j];
		csum += (double) c[j];
	}

#ifdef VERBOSE
	printf ("Results Comparison: \n");
	printf ("        Expected  : %f %f %f \n",aj,bj,cj);
	printf ("        Observed  : %f %f %f \n",asum,bsum,csum);
#endif

#ifndef abs
#define abs(a) ((a) >= 0 ? (a) : -(a))
#endif
	epsilon = 1.e-8;

	if (abs(aj-asum)/asum > epsilon) {
		printf ("Failed Validation on array a[]\n");
		printf ("        Expected  : %f \n",aj);
		printf ("        Observed  : %f \n",asum);
	}
	else if (abs(bj-bsum)/bsum > epsilon) {
		printf ("Failed Validation on array b[]\n");
		printf ("        Expected  : %f \n",bj);
		printf ("        Observed  : %f \n",bsum);
	}
	else if (abs(cj-csum)/csum > epsilon) {
		printf ("Failed Validation on array c[]\n");
		printf ("        Expected  : %f \n",cj);
		printf ("        Observed  : %f \n",csum);
	}
	else {
		printf ("Solution Validates\n");
	}
}

void tuned_STREAM_Copy()
{
	int j;
#pragma omp parallel for
        for (j=0; j<N; j++)
            c[j] = a[j];
}

void tuned_STREAM_Scale(MY_DATA_SIZE scalar)
{
	int j;
#pragma omp parallel for
	for (j=0; j<N; j++)
	    b[j] = scalar*c[j];
}

#if defined( IBY4) || defined( IBY8 )
void tuned_STREAM_SScale(MY_DATA_SIZE scalar)
{
	int j;
#pragma omp parallel for
	for (j=0; j<N; j++)
	    e[j] = d[j] << scalar;
}
#endif

void tuned_STREAM_Add()
{
	int j;
#pragma omp parallel for
	for (j=0; j<N; j++)
	    c[j] = a[j]+b[j];
}

void tuned_STREAM_Triad(MY_DATA_SIZE scalar)
{
	int j;
#pragma omp parallel for
	for (j=0; j<N; j++)
	    a[j] = b[j]+scalar*c[j];
}