The `fsh` instruction stores a half-precision floating-point value from register _xd_ to memory at address _xs1_ + _imm_. `fsh` does not modify the bits being transferred; in particular, the payloads of non-canonical NaNs are preserved. `fsh` ignores all but the lower 16 bits in _fs2_. `fsh` is only guaranteed to execute atomically if the effective address is naturally aligned.
fsh fs2, imm(xs1)Type: