[Bug target/125247] SVE vectorization fails for loop with distance -8 dependence and mixed-type struct — legality analysis bailout, not cost-model

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=125247

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Target|                            |aarch64
             Blocks|                            |53947
   Last reconfirmed|                            |2026-05-11
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
On x86 we vectorize it:

t.c:11:23: optimized: loop vectorized using 16 byte vectors and unroll factor 8
t.c:11:23: optimized: epilogue loop vectorized using masked 16 byte vectors and
unroll factor 8
t.c:11:23: optimized: loop vectorized using 16 byte vectors and unroll factor 8
t.c:11:23: optimized: epilogue loop vectorized using masked 16 byte vectors and
unroll factor 8

and we split the loop

t.c:12:41: optimized: loop split

Confirmed for the aarch64 observation.


Referenced Bugs:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53947
[Bug 53947] [meta-bug] vectorizer missed-optimizations