Microbench results for ADD_INT:
https://github.com/python/cpython/pull/25090#issuecomment-810441738

I have a few others like this lined up -- Mark recommended submitting them one at a time to make review easier.

My philosophy here (which I learned from Tim Peters in the early 2000s) is that even though each individual improvement has no measurable effect on a general benchmark (as shown in the same comment), the combined effect of a number of tiny improvements can be significant.

We have reached a point where there are very few individual changes possible that still have a significant effect, but we should not use this as an excuse to stop trying to improve performance.

I have mislaid the results that made me think this particular opcode is a good candidate; I will go back to reproduce that result and get back to you here.