On 28-02-2014 12:07, R Vidya wrote:
Hi
Agree, I am also seeing performance improvement with x86_64 approach
The advantage I am seeing with this approach is that it avoids scanning duplicate
chars in the needle via hash table/dictionary in addition to loop unrolling.
Adhemerval ,
Lets push the current implementation and work on similar approach for Power7
shortly. thanks.
Regards
Vidya
Hi Vidya,
Since you will work on new implementation based on Ondrej comments, I'll wait for it to avoid
push a patch that will be replaced shortly.