CSC/ECE 506 Spring 2015/37 mr

1. Example 1

1. Example 2

Parallelize the code below using loop distribution

---

for (i=0; i<n; i++) { 
S1:  a[i] = b[i-1] * a[i+1];
S2:  b[i] = b[i] * 3;
S3:  c[i] = .2 * (c[i-1] * c[i]);
} 

After loop distribution

---

for(i=0; i < n; i++)  
 S1: a[i] = b[i-1] * a[i+1]; 
for(i=0; i < n; i++) 
 S3: c[i] = .2* c[i-1] * c[i];
for(i=0; i < n; i++) 
 S2: b[i] = b[i] * 3;

---

Now write the parallelized code in openMP using C++

---

#pragma omp parallel shared(a,b,c)private(i) {
 #pragma omp sections nowait
 {
       #pragma omp section
       for(i=0; i < n; i++)
         a[i] = b[i-1] * a[i+1];
       #pragma omp section
       for(i=0; i<n; i++)
        c[i] = .2* c[i-1]*c[i];
       #pragma omp section
       for(i=0; i < n; i++)
        b[i] = b[i] * 3;
  }//end omp sections
} //end omp parallel