--- a/stream_omp.c  2009-03-14 15:02:38.000000000 +0100
+++ b/stream_omp.c  2014-05-23 12:22:05.878737562 +0200
@@ -45,6 +45,8 @@
 # include <float.h>
 # include <limits.h>
 # include <sys/time.h>
+# include <omp.h>
+# include <cpucounters.h>

 /* INSTRUCTIONS:
  *
@@ -54,8 +56,8 @@
  *          that should be good to about 5% precision.
  */

-# define N 2000000
-# define NTIMES    10
+# define N 60000000 // make sure we the matrices do not fit into caches
+# define NTIMES    100 // increase the number of repetitions to increase measurement accuracy
 # define OFFSET    0

 /*
@@ -179,6 +181,9 @@ main()
     printf("For best results, please be sure you know the\n");
     printf("precision of your system timer.\n");
     printf(HLINE);
+
+    PCM::getInstance()->program();
+    long long unsigned readBytes = 0, writtenBytes = 0;

     /* --- MAIN LOOP --- repeat test cases NTIMES times --- */

@@ -216,6 +221,7 @@ main()
    times[2][k] = mysecond() - times[2][k];

    times[3][k] = mysecond();
+   SystemCounterState begin = getSystemCounterState();
 #ifdef TUNED
         tuned_STREAM_Triad(scalar);
 #else
@@ -224,6 +230,12 @@ main()
        a[j] = b[j]+scalar*c[j];
 #endif
    times[3][k] = mysecond() - times[3][k];
+
+   SystemCounterState after = getSystemCounterState();
+   if(k>0) { // skip the first iteration
+       readBytes += getBytesReadFromMC(begin,after);
+       writtenBytes += getBytesWrittenToMC(begin,after);
+   }
    }

     /* --- SUMMARY --- */
@@ -237,6 +249,9 @@ main()
        maxtime[j] = MAX(maxtime[j], times[j][k]);
        }
    }
+
+   printf("TRIAD read bw: %11.4f write bw: %11.4f\n",1.0E-06*readBytes/avgtime[3],1.0E-06*writtenBytes/avgtime[3]);
+   PCM::getInstance()->cleanup();

     printf("Function      Rate (MB/s)   Avg time     Min time     Max time\n");
     for (j=0; j<4; j++) {