/*
 This program is for testing large stride data transfer

I put this program under the GPL.

Contact:Naohiko Shimizu, 
	School of Engineering, Tokai University.
	1117 Kitakaname, Kanagawa 259-12 Japan
	email:nshimizu@keyaki.cc.u-tokai.ac.jp
	TEL: +81-463-58-1211(ext.4084)
	FAX: +81-463-58-8320
	<URL:http://shimizu-lab.et.u-tokai.ac.jp/>
*/


#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <math.h>
#include <string.h>
#include <sys/time.h>
#include <sys/resource.h>

struct rusage rusage;

double dtime()
{
 double q;

 getrusage(RUSAGE_SELF,&rusage);

 q = (double)(rusage.ru_utime.tv_sec);
 q = q + (double)(rusage.ru_utime.tv_usec) * 1.0e-06;
	
 return q;
}

double bench1(double *a, double *b, int dim, int iter) {

 int i,j,kk,idim, jdim;
 double	starttime, endtime;

 for(i=0; i< dim*dim; i++) a[i] = b[i] = 0.0;
 starttime = dtime();
 for(kk=0; kk<iter; kk++) {
        idim=0;
	for(i=0; i<dim; i++) {
                jdim=0;
		for(j=0; j< dim; j++) {
			a[jdim+i] = b[idim+j];
                        jdim+=dim;
		  }
                idim+=dim;
	 }
 }
 endtime = dtime();
return endtime-starttime;
}

double bench2(double *a, double *b, int dim, int iter) {

 int i,j,kk,idim,jdim;
 double	starttime, endtime;

 for(i=0; i< dim*dim; i++) a[i] = b[i] = 0.0;
 starttime = dtime();
 for(kk=0; kk<iter; kk++) {
        jdim=0;
	for(j=0; j< dim; j++) {
                idim=0;
		for(i=0; i<dim; i++) {
			a[jdim+i] = b[idim+j];
                        idim+=dim;
		  }
                jdim+=dim;
	 }
 }
 endtime = dtime();
 return endtime-starttime;
}

int main()
{
 double	*a, *b;
 int    dim,iter;
 double time1,time2;


 for(dim=201; dim<3500; dim+=2) {
 a = (double *)malloc(sizeof(double)*(dim*dim*2));
 b = a + dim*dim;
 iter=3500*3500/(dim*dim);
 if(a==NULL) {
   printf("not enough memory\n");
   exit(1);
 }
 time1=bench1(a,b,dim,iter);
 time2=bench2(a,b,dim,iter);
 free(a);
 printf("%d ", dim);
 printf(" %5.2f", iter*dim*dim*sizeof(double)*1e-6/time1);
 printf(" %5.2f\n", iter*dim*dim*sizeof(double)*1e-6/time2);
 }
 exit(0);
}