[Bug tree-optimization/92335] [10/11/12 Regression] sinking of loads happen too early which causes vectorization not to be done

[Bug tree-optimization/92335] [10/11/12 Regression] sinking of loads happen too early which causes vectorization not to be done

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|                            |missed-optimization
      Known to work|                            |7.3.0
            Summary|missed transformation to    |[10/11/12 Regression]
                   |branchless                  |sinking of loads happen too
                   |                            |early which causes
                   |                            |vectorization not to be
                   |                            |done
      Known to fail|                            |10.1.0
   Target Milestone|---                         |10.4

--- Comment #4 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
I looked into this and find we are sinking the load of y[i] too early.
That is using -fno-tree-sink, we are able to produce the optimized code.
It would also mean it is a regression even and yes the testcase in comment #3
was able to produce vectorized code in GCC 7.3.0.

[Bug tree-optimization/92335] [10/11/12 Regression] sinking of loads happen too early which causes vectorization not to be done

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Blocks|                            |53947
           Priority|P3                          |P2
   Last reconfirmed|2019-11-04 00:00:00         |2022-1-21


Referenced Bugs:

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

[Bug tree-optimization/92335] [10/11/12/13 Regression] sinking of loads happen too early which causes vectorization not to be done

[jakub at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

Jakub Jelinek <jakub at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|10.4                        |10.5

--- Comment #5 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
GCC 10.4 is being released, retargeting bugs to GCC 10.5.

[Bug tree-optimization/92335] [11/12/13/14 Regression] sinking of loads happen too early which causes vectorization not to be done

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|10.5                        |11.5

--- Comment #6 from Richard Biener <rguenth at gcc dot gnu.org> ---
GCC 10 branch is being closed.

[Bug tree-optimization/92335] [11/12/13/14 Regression] sinking of loads happen too early which causes vectorization not to be done

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Assignee|unassigned at gcc dot gnu.org      |rguenth at gcc dot gnu.org
             Status|NEW                         |ASSIGNED

--- Comment #7 from Richard Biener <rguenth at gcc dot gnu.org> ---
I have a patch to fix this.

[Bug tree-optimization/92335] [11/12/13/14 Regression] sinking of loads happen too early which causes vectorization not to be done

[cvs-commit at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

--- Comment #8 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by Richard Biener <rguenth@gcc.gnu.org>:

https://gcc.gnu.org/g:399c8dd44ff44f4b496223c7cc980651c4d6f6a0

commit r14-2927-g399c8dd44ff44f4b496223c7cc980651c4d6f6a0
Author: Richard Biener <rguenther@suse.de>
Date:   Thu Jul 27 15:34:12 2023 +0200

    tree-optimization/92335 - Improve sinking heuristics for vectorization

    The following delays sinking of loads within the same innermost
    loop when it was unconditional before.  That's a not uncommon
    issue preventing vectorization when masked loads are not available.

            PR tree-optimization/92335
            * tree-ssa-sink.cc (select_best_block): Before loop
            optimizations avoid sinking unconditional loads/stores
            in innermost loops to conditional executed places.

            * gcc.dg/tree-ssa/ssa-sink-10.c: Disable vectorizing.
            * gcc.dg/tree-ssa/predcom-9.c: Clone from ssa-sink-10.c,
            expect predictive commoning to happen instead of sinking.
            * gcc.dg/vect/pr65947-3.c: Ajdust.

[Bug tree-optimization/92335] [11/12/13 Regression] sinking of loads happen too early which causes vectorization not to be done

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
      Known to work|                            |14.0
            Summary|[11/12/13/14 Regression]    |[11/12/13 Regression]
                   |sinking of loads happen too |sinking of loads happen too
                   |early which causes          |early which causes
                   |vectorization not to be     |vectorization not to be
                   |done                        |done

--- Comment #9 from Richard Biener <rguenth at gcc dot gnu.org> ---
Fixed for GCC 14, very unlikely to be backported.

[Bug tree-optimization/92335] [11/12/13 Regression] sinking of loads happen too early which causes vectorization not to be done

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92335

--- Comment #10 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
*** Bug 95084 has been marked as a duplicate of this bug. ***