Performance of parallel program with openMP + optimization ??

Performance of parallel program with openMP + optimization ??

Hello,

I get a strange problem about the parallel program with openMP+optimization. I compare the performance between parallelized program with openMP and non-parallelized program. I find the performance of parallelized program with openMP+od is better than the performance of non-parallelized program. But the performance of parallelized program with openMP+o1/o2/o3 is worse than the performance of non-parallelized program. I think the optimization doesn't work with openMP. It's strange. The intel compiler is c++ compiler 7. The PC has xeon 2.4 GHz dual-CPU with windows xp system. The follows is the parallelized program. Please kindly help me. Thanks.

NITER= 1000;
XSIZE= 1000;
YSIZE= 1000;

#pragma omp parallel private(k,x,y)
{
for(k = 0; k < NITER; k++){

#pragma omp for
for(x = 1; x <= XSIZE; x++)
for(y = 1; y <= YSIZE; y++)
u[x][y] = (uu[x-1][y] + uu[x+1][y] + uu[x][y-1] + uu[x][y+1])/4.0;
}
}

1 contenuto / 0 nuovi
Per informazioni complete sulle ottimizzazioni del compilatore, consultare l'Avviso sull'ottimizzazione