C OpenMP parallel sorting of bubbles

Question

I have an implementation of an algorithm for sorting parallel bubbles ( Odd Parity Sort ) in C using OpenMP. However, after I tested it, it is slower than the serial version (about 10%), although I have a processor with 4 cores (2 real x 2 due to Intel hyper-thread). I checked if the kernels are really used, and I can see them at 100% when the program starts. Therefore, I think that I was mistaken in the implementation of the algorithm.

I am using linux with 2.6.38-8-generic kernel.

This is how I compile:

gcc -o bubble-sort bubble-sort.c -Wall -fopenmp or

gcc -o bubble-sort bubble-sort.c -Wall -fopenmp for serial version

This is how I run:

./bubble-sort < in_10000 > out_10000

#include <omp.h>
#include <stdio.h>
#include <time.h>
#include <stdlib.h>

int main()
{
        int i, n, tmp, *x, changes;
        int chunk;
        scanf("%d ", &n);
        chunk = n / 4;
        x = (int*) malloc(n * sizeof(int));
        for(i = 0; i < n; ++i)
            scanf("%d ", &x[i]);
    changes = 1;
    int nr = 0;
    while(changes)
    {
    #pragma omp parallel private(tmp)
    {
            nr++;
            changes = 0;
            #pragma omp for \
                    reduction(+:changes)
            for(i = 0; i < n - 1; i = i + 2)
            {
                    if(x[i] > x[i+1] )
                    {
                            tmp = x[i];
                            x[i] = x[i+1];
                            x[i+1] = tmp;
                            ++changes;
                    }
            }
            #pragma omp for \
                    reduction(+:changes)
            for(i = 1; i < n - 1; i = i + 2)
            {
                    if( x[i] > x[i+1] )
                    {
                            tmp = x[i];
                            x[i] = x[i+1];
                            x[i+1] = tmp;
                            ++changes;
                    }
            }
    }
    }

    return 0;

}

Next edit:

, , , , . ( 8 → 21- 150 . , , ). , OMP_SCHEDULE, ...

Answer 1

, .

, ; OpenMP, , , , .

, :
- ok , i<n-1;
- - -, , ; -, OpenMP ; - while:

#pragma omp parallel private(tmp)
{
    #pragma omp for bla-bla
    for (i=0; i<n-1; i+=2 ) {...}

    #pragma omp for bla-bla
    for (i=1; i<n-1; i+=2 ) {...}
}