[Bug target/122014] (AArch64) Optimize 8-bit and 16-bit popcount as special cases

pinskia at gcc dot gnu.org gcc-bugzilla@gcc.gnu.org
Sun Sep 21 07:11:35 GMT 2025


https://gcc.gnu.org/bugzilla/show_bug.cgi?id=122014

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|                            |missed-optimization

--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
So for the 8bit and 16bit modes. Basically comes down to the other elements of
the vector are dont care.

In the case of a load, zero extend is the best but in the case of moving from a
registerdup is better.


More information about the Gcc-bugs mailing list