Saturday, September 3, 2011

OpenMP with GCC


std::vector < int >  a(N, 1), b(N, 2), c(N, 0);
   
#pragma omp parallel for
for (i=0; i < N; ++i)
    c[i] = a[i] + b[i];

g++ test.cc -fopenmp -o parallel_for

On a dual-core machine, it was up to 80% faster than the normal for loop.





No comments:

Post a Comment