- There are a number of synchronization methods in OpenMP,
but for this short intro, I will limit to one:
mutual exclusion.
- Recall that concurrent updates to shared variables
must be done within a pthread_mutex_lock
and pthread_mutex_unlock pair.
- This mutual exclusion effect is achieved in OpenMP using the
following pragma:
#pragma omp critical { ... ... Update share variables ... }
- Consider the following sequential
program that estimate Pi by integrating
2.0 / sqrt(1 - x*x):
-
Example Program:
(Sequential program for Pi) ---
click here
Compile with:
-
g++ compute_pi.C
Run the program with:
-
a.out NumberOfIntervals
(We have seen this program before, so I will not explain it again: click here )
- We will parallelize the for-loop using OpenMP
double f(double a) { return( 2.0 / sqrt(1 - a*a) ); } int main(int argc, char *argv[]) { int i; int N; double sum; double x, w; N = ...; // accuracy of the approximation w = 1.0/N; sum = 0.0; for (i = 1; i <= N; i = i + 1) { x = w*(i - 0.5); sum = sum + w*f(x); } cout << sum; }
-
Example Program:
(Sequential program for Pi) ---
click here
- Parallel Open MP program to estimate Pi in C/C++:
When we parallelize, it is important to know which UPDATES must be SYNCHRONIZED:
- When a variable is updated by different threads, the various updates must be synchronized
- Updates that need to be synchronized:
- The only variable that are updated by different threads is:
sum
- So updates to sum must be synchronized.
- The only variable that are updated by different threads is:
sum
- First Version of the OpenMP program to compute Pi:
-
Example Program:
(First version of OpenMP to compute Pi) ---
click here
- Compile with:
-
g++ -fopenmp openMP_compute_pi-1.C
- Run with:
export OMP_NUM_THREADS=8
a.out 50000000Change OMP_NUM_THREADS and see the difference in performance
double f(double a) { return( 2.0 / sqrt(1 - a*a) ); } int main(int argc, char *argv[]) { int N; double sum; // Shared variable, updated ! double x, w; N = ...; // accuracy of the approximation w = 1.0/N; sum = 0.0; #pragma omp parallel { int i, num_threads; // Non-shared variables !!! double x; num_threads = omp_get_num_threads() ; for (i = omp_get_thread_num(); i < N; i = i + num_threads) { x = w*(i + 0.5); #pragma omp critical { sum = sum + w*f(x); } } } cout << sum; }
-
Example Program:
(First version of OpenMP to compute Pi) ---
click here
- Problem with the first version:
- Too many synchronizations operations !!!
- Notice that the CRITICAL
pragme is
INSIDE
the for-loop
- Too many synchronizations operations !!!
- To eliminate
synchronizations,
we use
private variables
- Improved Version of the OpenMP program to compute Pi:
-
Example Program:
(OpenMP compute Pi) ---
click here
- Compile with:
-
g++ -fopenmp openMP_compute_pi-2.C
- Run with:
export OMP_NUM_THREADS=8
a.out 50000000Change OMP_NUM_THREADS and see the difference in performance
double f(double a) { return( 2.0 / sqrt(1 - a*a) ); } int main(int argc, char *argv[]) { int N; double sum; // Shared variable, updated ! double x, w; N = ...; // accuracy of the approximation w = 1.0/N; sum = 0.0; #pragma omp parallel { int i, num_threads; double x; double mypi; // Private variable to reduce synchronization num_threads = omp_get_num_threads() ; mypi = 0.0; for (i = omp_get_thread_num(); i < N; i = i + num_threads) { x = w*(i + 0.5); mypi = mypi + w*f(x); } #pragma omp critical { sum = sum + mypi; } } cout << sum; } -
Example Program:
(OpenMP compute Pi) ---
click here