https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107905
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Keywords| |missed-optimization, ra
Component|target |middle-end
--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
I looked at the code generation and there is not much difference between GCC
and LLVM really.
The only difference I see some register allocation difference when it comes to
mask and name. GCC uses two extra registers to store those.
I don't see that causing a 2x slow down though.
