Slow performance in OpenMP

Question

I am trying to understand openmp code from here . You can see the code below.

• To measure the acceleration, the difference between the serial version and the omp version, I use time.h, do you find the right approach?

• The program runs on a 4-core computer. I indicate export OMP_NUM_THREADS="4", but do not see noticeable acceleration, usually I get 1.2 - 1.7. What problems do I face in this parallelization?

• Which debug / performace tool can be used to view performance loss?

code (I use to compile xlc_r -qsmp=omp omp_workshare1.c -o omp_workshare1.exe)

#include <omp.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/time.h>
#define CHUNKSIZE   1000000
#define N       100000000

int main (int argc, char *argv[]) 
{
    int nthreads, tid, i, chunk;
    float a[N], b[N], c[N];
    unsigned long elapsed;
    unsigned long elapsed_serial;
    unsigned long elapsed_omp;
    struct timeval start;
    struct timeval stop;


    chunk = CHUNKSIZE;

    // =================    SERIAL     start =======================
    /* Some initializations */
    for (i=0; i < N; i++)
        a[i] = b[i] = i * 1.0;
    gettimeofday(&start,NULL); 
    for (i=0; i<N; i++)
    {
        c[i] = a[i] + b[i];
        //printf("Thread %d: c[%d]= %f\n",tid,i,c[i]);
    }
    gettimeofday(&stop,NULL);
    elapsed = 1000000 * (stop.tv_sec - start.tv_sec);
    elapsed += stop.tv_usec - start.tv_usec;
    elapsed_serial = elapsed ;
    printf ("   \n Time SEQ= %lu microsecs\n", elapsed_serial);
    // =================    SERIAL     end =======================


    // =================    OMP    start =======================
    /* Some initializations */
    for (i=0; i < N; i++)
        a[i] = b[i] = i * 1.0;
    gettimeofday(&start,NULL); 
#pragma omp parallel shared(a,b,c,nthreads,chunk) private(i,tid)
    {
        tid = omp_get_thread_num();
        if (tid == 0)
        {
            nthreads = omp_get_num_threads();
            printf("Number of threads = %d\n", nthreads);
        }
        //printf("Thread %d starting...\n",tid);

#pragma omp for schedule(static,chunk)
        for (i=0; i<N; i++)
        {
            c[i] = a[i] + b[i];
            //printf("Thread %d: c[%d]= %f\n",tid,i,c[i]);
        }

    }  /* end of parallel section */
    gettimeofday(&stop,NULL);
    elapsed = 1000000 * (stop.tv_sec - start.tv_sec);
    elapsed += stop.tv_usec - start.tv_usec;
    elapsed_omp = elapsed ;
    printf ("   \n Time OMP= %lu microsecs\n", elapsed_omp);
    // =================    OMP    end =======================
    printf ("   \n speedup= %f \n\n", ((float) elapsed_serial) / ((float) elapsed_omp)) ;

}

Answer 1

, , , , c = a + b - , (a ) (2 ), , .

, :

c[i] = exp(sin(a[i])) + exp(cos(b[i]));

$ ./apb

 Time SEQ= 17678571 microsecs
Number of threads = 4

 Time OMP= 4703485 microsecs

 speedup= 3.758611 

, , 4x, .

: , - gettimeofday(), , , , xlc, - AIX? peekperf , . x86 cachegrind/valgrind ( ), scalasca OpenMP OpenSpeedShop .