amker at gcc dot changed:

           What    |Removed                     |Added
                 CC|                            |amker at gcc dot

--- Comment #4 from amker at gcc dot ---
Looks like generic loop unrolling code used by predcom spends quite a lot
maintaining profiling counter, I will check if that's correct and we shall do
the same in vectorizer.  At least simply scaling down vect_loop is wrong. 

Reply via email to