From 8d6b10e983a7bd7741ada07d946cfa74d4a1e0c0 Mon Sep 17 00:00:00 2001
From: Ciro Santilli <ciro.santilli@gmail.com>
Date: Tue, 17 Apr 2018 12:11:10 +0100
Subject: [PATCH] Add MM.c as a test for
 https://www.mail-archive.com/gem5-users@gem5.org/msg15346.html

---
 kernel_module/user/MM.c | 68 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)
 create mode 100644 kernel_module/user/MM.c

diff --git a/kernel_module/user/MM.c b/kernel_module/user/MM.c
new file mode 100644
index 0000000..c15beac
--- /dev/null
+++ b/kernel_module/user/MM.c
@@ -0,0 +1,68 @@
+#include <omp.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#define NRA 64                /* number of rows in matrix A */
+#define NCA 64                 /* number of columns in matrix A */
+#define NCB 64                  /* number of columns in matrix B */
+
+int main () 
+{
+int	tid, nthreads, i, j, k, chunk;
+double	a[NRA][NCA],           /* matrix A to be multiplied */
+	b[NCA][NCB],           /* matrix B to be multiplied */
+	c[NRA][NCB];           /* result matrix C */
+
+chunk = 10;                    /* set loop iteration chunk size */
+
+/*** Spawn a parallel region explicitly scoping all variables ***/
+omp_set_num_threads(4);
+#pragma omp parallel shared(a,b,c,nthreads,chunk) private(tid,i,j,k)
+  {
+  tid = omp_get_thread_num();
+  if (tid == 0)
+    {
+    nthreads = omp_get_num_threads();
+    printf("Starting matrix multiple example with %d threads\n",nthreads);
+    printf("Initializing matrices...\n");
+    }
+  /*** Initialize matrices ***/
+  #pragma omp for schedule (static, chunk) 
+  for (i=0; i<NRA; i++)
+    for (j=0; j<NCA; j++)
+      a[i][j]= i+j;
+  #pragma omp for schedule (static, chunk)
+  for (i=0; i<NCA; i++)
+    for (j=0; j<NCB; j++)
+      b[i][j]= i*j;
+  #pragma omp for schedule (static, chunk)
+  for (i=0; i<NRA; i++)
+    for (j=0; j<NCB; j++)
+      c[i][j]= 0;
+
+  /*** Do matrix multiply sharing iterations on outer loop ***/
+  /*** Display who does which iterations for demonstration purposes ***/
+  printf("Thread %d starting matrix multiply...\n",tid);
+  #pragma omp for schedule (static, chunk)
+  for (i=0; i<NRA; i++)    
+    {
+    printf("Thread=%d did row=%d\n",tid,i);
+    for(j=0; j<NCB; j++)       
+      for (k=0; k<NCA; k++)
+        c[i][j] += a[i][k] * b[k][j];
+    }
+  }   /*** End of parallel region ***/
+
+/*** Print results ***/
+printf("******************************************************\n");
+printf("Result Matrix:\n");
+for (i=0; i<NRA; i++)
+  {
+  for (j=0; j<NCB; j++) 
+    printf("%6.2f   ", c[i][j]);
+  printf("\n"); 
+  }
+printf("******************************************************\n");
+printf ("Done.\n");
+return 0;
+}