Adding a performance debug listener to ChampSim #648

It's hard to figure out why a given instruction has a delay at a given stage in ChampSim. The best method I'm aware of right now to resolve this is to decipher what's going on in that section of ChampSim, then add a bunch of print statements to figure out which of all the possible bottlenecks is the actual bottleneck. I'm going through this in one of my current projects, so I'm interested in creating a listener that will do this automatically. I'm opening this as an issue to see if there's interest in adding this as a feature to ChampSim and to see if there are any refinements or feature requests from the community for a tool like this one.

This would give a microscopic view of performance in ChampSim (e.g., what are the bottlenecks stopping this particular instruction) as opposed to the macroscopic view of performance given by CPI Stacks (e.g., what are the major bottlenecks across the entire program).