reason why custom loop is faster? bad compiler? unsafe custom code? luck?(lucky cache hits)

Question

i just started learning assembly and making some custom loop for swapping two variables using C++ \'s asm{} body with Digital-Mars compiler in C-Free 5.0

Enabled th

Answer 1

I'm surprised that any of you guys got anything but zero cycles from the C code. Here, with gcc 4.6.3 and -O2, the loop vanishes away as there is no side-effect from it. Everything except the asm block is removed. I would be surprised if Digital Mars can't do such a trivial optimization; I bet you can try different optimization switches that will remove the C code, at which point such trivial comparison becomes impossible.

Your toy example is useless to compare compiler optimizations with hand-crafted assembly. Statistically speaking, compilers can consistently write better machine code than humans.