search for: axfkvb

...interest bystander: I suspect you compiled > the source without any optimizations applied - I tried to replicate this > behaviour and found the optimzer happily replaces both the inner loops you > had with a constant, and thus I got the same time on both loops. (e.g. see > http://goo.gl/aXFkVb ) > > Benchmarks of this nature where the run time is so small are notoriously > prone to measurement errors, so I'd be a little careful drawing conclusions > from the sample you listed. Also; what architecture did you measure on, and > what spec machine? > > Not at all to...

Hi, I have been studying LLVM infrastructure from past 1 month and trying out some hands on to get familiar with it. I am keen to propose loop reversal pass in LLVM as a part of GSoC 2015. Following are the details of my proposal. A for loop can run in two ways – it can count up or it can count down. 1. for(i=0; i<10 ;i++) {// Do something} 2. for(i=9; i--;) {// Do something}