https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117733
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Ever confirmed|0 |1
Last reconfirmed| |2026-02-16
Status|UNCONFIRMED |NEW
--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
alternatively using ld5 and vectorizing this as SLP reduction with delayed
summation across lanes could work (but that's sth we do not support right now).
Iterating over single vs. multi-lane SLP and comparing costs would possibly
help.
