如何打破循环的opemp？

Question

I have a very ᴄᴘᴜ intensive (50 millions calls and over 100 bilions looping phase) for loop such as :

for(int i=0;i<*string;i++){
    if(!check_some_stuff(string+i)) {
        do_some_stuff(i,string-2);
        if(!string)
            break;
       do_yet_other_stuff(string);
    }
}

As break statements aren't allowed for #pragma omp parallel for odered I thought I could set i to a very large value.

for(int i=0;i<*string;i++){
    if(!check_some_stuff(string+i)) {
        do_some_stuff(i,string-2);
        if(!string)
            i=0x7FFFFFFB;
       do_yet_other_stuff(string);
    }
}

which perfectly works without openmp. But however when I add

#pragma omp parallel for ordered shared(string)
for(int i=0;i<*string;i++){
    if(!check_some_stuff(string+i)) {
        do_some_stuff(i,string-2);
        #pragma omp critical
        if(!string)
            i=0x7FFFFFFB; // it seems the assignment has no effect on the value of i.
       do_yet_other_stuff(*string);
    }
}

the value of i doesn't seems to change, so it turns to an infinite loop.

Answer 1

Does this help?

int abort = 0;
#pragma omp parallel for ordered shared(string, abort)
for(int i=0;i<*string;i++)
{
    #pragma omp flush(abort)
    if(!abort)
    {
        if(!check_some_stuff(string+i))
        {
            #pragma omp flush(abort)
            if(!abort) do_some_stuff(i,string-2);
            if(!string) abort = 1;
            #pragma omp flush(abort)
            if(!abort) do_yet_other_stuff(*string);
        }
    }
}