[Bug tree-optimization/115484] New: AVX vectorization is limited to 3 comparisons

[Bug tree-optimization/115484] New: AVX vectorization is limited to 3 comparisons

[andi-gcc at firstfloor dot org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

            Bug ID: 115484
           Summary: AVX vectorization is limited to 3 comparisons
           Product: gcc
           Version: 15.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: andi-gcc at firstfloor dot org
  Target Milestone: ---

With current trunk, but also older gcc

int f(char *s)
{
        int c = 0;
        int i;
        for (i = 0; i < 64; i++) {
                c |=  (*s == ',' || *s == '|' || *s == '!' /* || *s == '*' */);
                s++;
        }
        return c;
}

vectorizes with -O3 -mavx2  -fopt-info-optall-all tvcmp.c

tvcmp.c:6:16: optimized: loop vectorized using 16 byte vectors
tvcmp.c:2:5: note: vectorized 1 loops in function.
tvcmp.c:7:10: optimized: loop with 3 iterations completely unrolled (header
execution count 16535624)


but when the fourth comparison is commented in it doesn't:

BB 3 is always executed in loop 1
loop 1's coldest_outermost_loop is 1, hotter_than_inner_loop is NULL
tvcmp.c:6:16: missed: couldn't vectorize loop
tvcmp.c:6:16: missed: not vectorized: unsupported control flow in loop.
tvcmp.c:2:5: note: vectorized 0 loops in function.
tvcmp.c:10:9: note: ***** Analysis failed with vector mode V16QI
tvcmp.c:10:9: note: ***** Skipping vector mode V16QI, which would repeat the
analysis for V16QI

[Bug tree-optimization/115484] if-to-switch prevents AVX vectorization

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|AVX vectorization is        |if-to-switch prevents AVX
                   |limited to 3 comparisons    |vectorization
     Ever confirmed|0                           |1
   Last reconfirmed|                            |2024-06-14
             Blocks|                            |53947
           Keywords|                            |missed-optimization
             Status|UNCONFIRMED                 |NEW
             Target|                            |x86_64-*-*

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
The issue seems to be that if-to-switch creates a switch () once you get to
four 
conditions and switch statements are not handled by the pre-vectorizer
if-conversion (or by vectorization natively).


Referenced Bugs:

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

[Bug tree-optimization/115484] [11/12/13/14/15 regression] if-to-switch prevents AVX vectorization

[sjames at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

Sam James <sjames at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|if-to-switch prevents AVX   |[11/12/13/14/15 regression]
                   |vectorization               |if-to-switch prevents AVX
                   |                            |vectorization

--- Comment #2 from Sam James <sjames at gcc dot gnu.org> ---
GCC 8 vectorises it: https://godbolt.org/z/Y8Pvxsh5c.

[Bug tree-optimization/115484] [13/14/15 regression] if-to-switch prevents AVX vectorization

[sjames at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

Sam James <sjames at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|[11/12/13/14/15 regression] |[13/14/15 regression]
                   |if-to-switch prevents AVX   |if-to-switch prevents AVX
                   |vectorization               |vectorization

--- Comment #3 from Sam James <sjames at gcc dot gnu.org> ---
(In reply to Sam James from comment #2)
> GCC 8 vectorises it: https://godbolt.org/z/Y8Pvxsh5c.

Not only does 8 vectorise it, but so does GCC 11, GCC 12. So, 9/13/14/15 are
broken.

[Bug tree-optimization/115484] [13/14/15 regression] if-to-switch prevents AVX vectorization

[sjames at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

--- Comment #4 from Sam James <sjames at gcc dot gnu.org> ---
Not only does 8 vectorise it, but so does GCC 11, GCC 12. So, 9/10/13/14/15 are
broken.

[Bug tree-optimization/115484] [13/14/15 regression] if-to-switch prevents AVX vectorization

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

--- Comment #5 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
(In reply to Sam James from comment #2)
> GCC 8 vectorises it: https://godbolt.org/z/Y8Pvxsh5c.

The if-to-switch was not until GCC 11: r11-5605-g03eb09292ef228.
What made GCC 9 fail was the conversion from bool to int though:
/app/example.c:2:5: missed:   not vectorized: relevant stmt not supported:
patt_29 = (int) patt_30;

But that worked in GCC 8. Though that was fixed in GCC 11.

If you replace `c|=` with:
```
                c |=  (*s == ',' | *s == '|' | *s == '!' | *s == '*');
```

GCC 11+ is able to vectorize it again. But the original testcase fails now due
to if-to-switch .

[Bug tree-optimization/115484] [13/14/15 regression] if-to-switch prevents AVX vectorization

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |pinskia at gcc dot gnu.org
   Target Milestone|---                         |13.4

[Bug tree-optimization/115484] [13/14/15 regression] if-to-switch prevents AVX vectorization

[andi-gcc at firstfloor dot org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115484

--- Comment #6 from Andi Kleen <andi-gcc at firstfloor dot org> ---
As an interesting but irrelevant side comment clang seems to have the same bug.