AMDGPU/GlobalISel: Fix test failure in release build

The annoying behavior where the output is different due to the
legality check struck again, plus the subtarget predicate wasn't
really correctly set for DS FP atomics.

Some of the FP min/max instructions seem to be in the gfx6/gfx7
manuals, but IIRC this might have been one of the cases where the
manual got ahead of the actual hardware support, but I've left these
as-is for now since the assembler tests seem to expect them.