Eh, somewhere in the middle. Someone else put ‘-ffast-math’ in a compile line and it poisons FP math far away with no recompile?

I believe it’s a necessary price in this case, but it does highlight how suboptimal it is to pay the price in other cases.

It's fair to point out that shared objects surface the problem here, but I don't know if I would lay the blame with them: the underlying problem is that a FPU control register isn't (and can't be) meaningfully isolated. Python needs to use shared objects for loadable extensions, but the contaminating code might be statically linked into that shared object.

(I don't say this because I want to excuse dynamic linking, which I also generally dislike! Only that I think the problem is somewhere else in this particular case.)