Lazy context switching is a thing on pretty much every architecture with an FPU.
Some ARM ABIs end up passing floats in integer registers, but that's just for compatibility for code that doesn't assume the presence of an FPU and might be doing everything soft float.
My hunch says that chips affected by 4a could easily be fair game (4a is speculating reads into priviledged regs... I wonder if 4a would work on regs that are trapped, not inconceivable)