https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117709
--- Comment #1 from Robin Dapp <rdapp at gcc dot gnu.org> --- We're not emitting the VEC_COND because type_mode_padding_p is false. My check compares the precision of the scalar type vs the precision of the vector mode's inner mode which is both 32 here: int vs E_V64SImode. So it seems we have a case now where we're not padding but still require zeroing.
