[Bug tree-optimization/70729] Loop marked with omp simd pragma is not vectorized

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70729

--- Comment #13 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to Yuri Rumyantsev from comment #12)
> Created attachment 38367 [details]
> modified patch

The loop->aux flagging looks redundant to me.  Why is ->safelen only valid
before vectorization?  I suppose we're lucky that no pass before vectorization
applies any unrolling (like predictive commoning for example) as such pass
must adjust ->safelen accordingly.  But as LIM only cares for safelen > 0
_this_ property shouldn't change, not even by vectorization, no?

That said, if vectorization makes ->safelen invalid then the vectorizer
should adjust ->safelen properly (like any other passes invalidating it).

I suppose most of the testsuite fallout you see is from the pass re-ordering
(I didn't bootstrap/test that yet).  The fails need to be investigated,
but let's handle the pass-reordering separately and converge on a way
to use ->safelen from LIM first.