https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71977
--- Comment #2 from Peter Bergner <bergner at gcc dot gnu.org> --- (In reply to Michael Meissner from comment #1) > Note in terms of the code in general, you have to make sure that the float > value is converted to vector form before you do AND/OR/etc. on it. This is > because within the register, 32-bit floats are actually stored as 64-bit > double precision values. I have a work in progress patch that I need to get back to once these other bugs I'm working on get fixed/resolved. I'll try and see what happens with it when using -mcpu=power9.
