[Bug tree-optimization/96738] GCC generates worse assembly than clang and It fails to vectorized code compared to clang

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=96738

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1
   Last reconfirmed|                            |2020-08-25

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
GCC fails to SLP vectorize this because SLP discovery fails for this reduction
scheme.  The only think clang vectorizes seems to be the mask reduction
and the store.

We're not falling back to scalar operand construction for the mask and
for some reason.