[Bug rtl-optimization/114556] New: weird loop unrolling when there's attribute aligned in side the loop

[Bug rtl-optimization/114556] New: weird loop unrolling when there's attribute aligned in side the loop

[liuhongt at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114556

            Bug ID: 114556
           Summary: weird loop unrolling when there's attribute aligned in
                    side the loop
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: rtl-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: liuhongt at gcc dot gnu.org
  Target Milestone: ---

v32qi
zzzzz (void* pa, void* pb, void* pc)
{
    v32qi __attribute__((aligned(64))) a;
    v32qi __attribute__((aligned(64))) b;
    v32qi __attribute__((aligned(64))) c;
    __builtin_memcpy (&a, pa, sizeof (a));
    __builtin_memcpy (&b, pb, sizeof (a));
    __builtin_memcpy (&c, pc, sizeof (a));
    #pragma GCC unroll 8
    for (int i = 0; i != 2048; i++)
      a += b;
      return a;
}

-O2 -mavx2, we have 

zzzzz:
        vmovdqu (%rsi), %ymm1
        vpaddb  (%rdi), %ymm1, %ymm0
        movl    $2041, %eax
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        jmp     .L2
.L3:
        vpaddb  %ymm0, %ymm1, %ymm0
        subl    $8, %eax
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
        vpaddb  %ymm0, %ymm1, %ymm0
.L2:
        vpaddb  %ymm0, %ymm1, %ymm0
        cmpl    $1, %eax
        jne     .L3
        ret

But shouldn't it better with

zzzzz:
        vmovdqu (%rsi), %ymm1
        vmovdqu (%rdi), %ymm0
        movl    $2048, %eax
.L2:
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        vpaddb  %ymm1, %ymm0, %ymm0
        subl    $8, %eax
        jne     .L2
        ret

[Bug middle-end/114556] weird loop unrolling when there's attribute aligned inside the loop

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114556

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
          Component|rtl-optimization            |middle-end

--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
The first difference (with/without aligned) comes from expand so moving this to
the middle-end ...

[Bug middle-end/114556] weird loop unrolling when there's attribute aligned inside the loop

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114556

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
     Ever confirmed|0                           |1
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2024-04-03

--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
without the align:

Inserting a partition copy on edge BB2->BB3 : PART.0 = PART.3
Inserting a value copy on edge BB2->BB3 : PART.1 = 2048


vs with:

Inserting a partition copy on edge BB3->BB3 : PART.7 = PART.0
Inserting a partition copy on edge BB2->BB3 : PART.7 = PART.3
Inserting a value copy on edge BB2->BB3 : PART.1 = 2048


Basically out of ssa is doing an extra move because it could not "merge" the
loop induction variable for the (vector) addition due to the different
alignment requirements ... 

And then things go down hill from there.