[Bug tree-optimization/123343] Loop unrolling before vectorization produces suboptimal RISC-V code

[rguenth at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=123343

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Last reconfirmed|                            |2026-01-04
                 CC|                            |rguenth at gcc dot gnu.org,
                   |                            |tnfchris at gcc dot gnu.org
     Ever confirmed|0                           |1
             Status|UNCONFIRMED                 |NEW

--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
W/o unrolling you get inner loop vectorization only(?), so with unrolling you'd
expect BB SLP to pick up the slack - for that you'd need to reject the outer
loop vectorization during costing or we need to somehow compare costs between
loop vectorization and vectorizing the loop BBs (we fall back to that
eventually, to get loop if-conversion benefits).