[Bug middle-end/116575] New: [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[Bug middle-end/116575] New: [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[tnfchris at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

            Bug ID: 116575
           Summary: [15 Regression] blender in SPEC2017 ICE in
                    vect_analyze_slp
           Product: gcc
           Version: 15.0
            Status: UNCONFIRMED
          Keywords: ice-on-valid-code
          Severity: normal
          Priority: P3
         Component: middle-end
          Assignee: unassigned at gcc dot gnu.org
          Reporter: tnfchris at gcc dot gnu.org
  Target Milestone: ---
            Target: aarch64*

Blender from spec2017 ICEs when compiled with -Ofast -flto -mcpu=neoverse-v1
with

during GIMPLE pass: vect
blender/source/blender/editors/object/object_bake_api.c: In function
'write_internal_bake_pixels':
blender/source/blender/editors/object/object_bake_api.c:173:13: internal
compiler error: in vect_analyze_slp, at tree-vect-slp.cc:4765
  173 | static bool write_internal_bake_pixels(
      |             ^
0x1c0a0f7 internal_error(char const*, ...)
       
/opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/diagnostic-global-context.cc:492
0x7bb0c7 fancy_abort(char const*, int, char const*)
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/diagnostic.cc:1658
0xfaf1bb vect_analyze_slp(vec_info*, unsigned int)
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vect-slp.cc:4765
0xf83a6b vect_analyze_loop_2
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vect-loop.cc:2862
0xf85123 vect_analyze_loop_1
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vect-loop.cc:3409
0xf85857 vect_analyze_loop(loop*, vec_info_shared*)
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vect-loop.cc:3567
0xfc3cef try_vectorize_loop_1
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vectorizer.cc:1068
0xfc3cef try_vectorize_loop
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vectorizer.cc:1184
0xfc4223 execute
        /opt/buildAgent/work/5c94c4ced6ebfcd0/gcc/tree-vectorizer.cc:1300

Creating a reducer and bisecting

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|---                         |15.0
                 CC|                            |pinskia at gcc dot gnu.org
          Component|middle-end                  |tree-optimization

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[tnfchris at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

--- Comment #1 from Tamar Christina <tnfchris at gcc dot gnu.org> ---
---
int a;
float *b, *c;
void d() {
  char *e;
  for (; a; a++, b += 4, c += 4)
    if (*e++) {
      float *f = c;
      f[0] = b[0];
      f[1] = b[1];
      f[2] = b[2];
      f[3] = b[3];
    }
}

compiled with -mcpu=neoverse-v1 -Ofast reproduces the ICE

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
     Ever confirmed|0                           |1
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2024-09-03

--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Tamar Christina from comment #1)
> compiled with -mcpu=neoverse-v1 -Ofast reproduces the ICE

here is a better testcase with no undefinedness:
```
int a;
float *b, *c;
void d(char * __restrict e) {
  for (; a; a++, b += 4, c += 4)
    if (*e++) {
      float *f = c;
      f[0] = b[0];
      f[1] = b[1];
      f[2] = b[2];
      f[3] = b[3];
    }
}
```

Just `-O3  -march=armv9-a` is needed.

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

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

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

--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
I will have a look.

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
OK, so we fail single-lane SLP discovery where we succeeded with multi-lane.
This is because the loads appear permuted during discovery and we have a
masked load feeding a masked store.  But we do not handle permuting masked
operations so for single-lane discovery it appears as such.

I'll for now avoid the situation and leave the actual fix for later.

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 ICE in vect_analyze_slp

[cvs-commit at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

--- Comment #5 from GCC 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:ac6cd62a351a8f1f3637a2552c74eb5eb51cfdda

commit r15-3411-gac6cd62a351a8f1f3637a2552c74eb5eb51cfdda
Author: Richard Biener <rguenther@suse.de>
Date:   Tue Sep 3 09:23:20 2024 +0200

    tree-optimization/116575 - avoid ICE with SLP mask_load_lane

    The following avoids performing re-discovery with single lanes in
    the attempt to for the use of mask_load_lane as rediscovery will
    fail since a single lane of a mask load will appear permuted which
    isn't supported.

            PR tree-optimization/116575
            * tree-vect-slp.cc (vect_analyze_slp): Properly compute
            the mask argument for vect_load/store_lanes_supported.
            When the load is masked for now avoid rediscovery.

            * gcc.dg/vect/pr116575.c: New testcase.

[Bug tree-optimization/116575] [15 Regression] blender in SPEC2017 fails to use mask_load_lanes

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116575

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|ice-on-valid-code           |missed-optimization
            Summary|[15 Regression] blender in  |[15 Regression] blender in
                   |SPEC2017 ICE in             |SPEC2017 fails to use
                   |vect_analyze_slp            |mask_load_lanes

--- Comment #6 from Richard Biener <rguenth at gcc dot gnu.org> ---
I've morphed this into the appropriate missed-optimization bug.