A really interesting in-depth question was posted over at stackoverflow.com asking why 1 loop seems to be so much slower than 2 loops. The discussion on the page goes into great and interesting detail on what’s going on behind the scenes and why there is such a decrease in speed between 1 and 2+ loops. Interestingly, it seems that the answer has something to do with the CPU cache and the way it handles the memory.

Why is one loop so much slower than two loops? (stackoverflow.com)