Having said that, there is also a difference between optimizations that are intended for real-world application improvements (which are supposed to do what you describe above) and optimizations that are intended purely to improve benchmark results. Without knowing how/why this particular compiler optimization arose, it is not possible to determine which case applies here.
So you admit that there's no data to back up any wrong doing. That's what I thought.
If you are including me as "usual suspects" in this case, you clearly have no idea of my background and motivation.
I wasn't specifically, but letting you know that if you believe yourself to fall into that category, it says more about your proclivity to jump to conclusions than it does mine.
As others have suggested though, the timings of the compiler change raise suspicions.
There's nothing suspicious that I have seen - and that's the bottom line. Compilers are meant to accelerate code, and most of the time they do that by removing instructions. Since you seem to infer that you have experience in this area, and at the same time evoke disgust at being lumped together with the "usual suspects", it baffles me that we're even still having this conversation.
Market Data 
Markets 
AI
