When, if ever, is loop unrolling still useful?

Question

I've been trying to optimize some extremely performance-critical code (a quick sort algorithm that's being called millions and millions of times inside a monte carlo simulation) by loop unrolling. Given the quality of branch predictors on modern hardware, when, if ever, is loop unrolling still a useful optimization?

Answer 1

Well when you tried loop unrolling, did it make any difference or were you unable to discern any difference in performance ? So first question, you should be able to answer on your own.

Loop unrolling can help if your loops are small - like 2 to 4, you could just expand the loop contents whatever number of times you need to execute the loop. Obviously you can do loop unrolling only if you know number of executions of the loop body in advance.