https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118166
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Ever confirmed|0 |1
Status|UNCONFIRMED |WAITING
Last reconfirmed| |2024-12-22
--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Do you have a benchmark where using SSE would be better than the scalar
instructions? Especially considering there are more than 2 ALUs which would
cause the code that you provided right now be better with the scalar
instructions because there is no movement between the 2 register sets.
