[Bug tree-optimization/107009] New: massive unnecessary code blowup in vectorizer

["drepper.fsp+rhbz at gmail dot com" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107009

            Bug ID: 107009
           Summary: massive unnecessary code blowup in vectorizer
           Product: gcc
           Version: 13.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: drepper.fsp+rhbz at gmail dot com
  Target Milestone: ---

Given an annotated saxpy function:

#include <cstdlib>

void saxpy(size_t n, float* __restrict res, float a, const float* __restrict x,
const float* __restrict y)
{
  if (n == 0 || n % 8 != 0)
    __builtin_unreachable();
  res = (float*)__builtin_assume_aligned(res, 32);
  x = (const float*) __builtin_assume_aligned(x, 32);
  y = (const float*) __builtin_assume_aligned(y, 32);
  for (size_t i = 0; i < n; ++i)
    res[i] = a * x[i] + y[i];
}


Compiling this with the gcc 12.2.1 version from Fedora 36 leads to the
expected, guided result (although the shrq isn't necessary…) with -O3:

_Z5saxpymPffPKfS1_:
        .cfi_startproc
        shrq    $3, %rdi
        vbroadcastss    %xmm0, %ymm0
        xorl    %eax, %eax
        salq    $5, %rdi
        .p2align 4
        .p2align 3
.L2:
        vmovaps (%rdx,%rax), %ymm1
        vfmadd213ps     (%rcx,%rax), %ymm0, %ymm1
        vmovaps %ymm1, (%rsi,%rax)
        addq    $32, %rax
        cmpq    %rdi, %rax
        jne     .L2
        vzeroupper
        ret

The the current trunk gcc the result is massively bigger and given the guidance
in the sources none of the extra code is necessary.

_Z5saxpymPffPKfS1_:
.LFB22:
        .cfi_startproc
        movq    %rdi, %r8
        movq    %rdx, %rdi
        movq    %rcx, %rdx
        leaq    -1(%r8), %rax
        cmpq    $6, %rax
        jbe     .L7
        movq    %r8, %rcx
        vbroadcastss    %xmm0, %ymm2
        xorl    %eax, %eax
        shrq    $3, %rcx
        salq    $5, %rcx
        .p2align 4
        .p2align 3
.L3:
        vmovaps (%rdi,%rax), %ymm1
        vfmadd213ps     (%rdx,%rax), %ymm2, %ymm1
        vmovaps %ymm1, (%rsi,%rax)
        addq    $32, %rax
        cmpq    %rcx, %rax
        jne     .L3
        movq    %r8, %rax
        andq    $-8, %rax
        testb   $7, %r8b
        je      .L18
        vzeroupper
.L2:
        movq    %r8, %rcx
        subq    %rax, %rcx
        leaq    -1(%rcx), %r9
        cmpq    $2, %r9
        jbe     .L5
        vmovaps (%rdx,%rax,4), %xmm3
        vshufps $0, %xmm0, %xmm0, %xmm1
        movq    %rcx, %r9
        vfmadd132ps     (%rdi,%rax,4), %xmm3, %xmm1
        andq    $-4, %r9
        vmovaps %xmm1, (%rsi,%rax,4)
        addq    %r9, %rax
        andl    $3, %ecx
        je      .L16
.L5:
        vmovss  (%rdi,%rax,4), %xmm1
        leaq    0(,%rax,4), %rcx
        leaq    1(%rax), %r9
        vfmadd213ss     (%rdx,%rax,4), %xmm0, %xmm1
        vmovss  %xmm1, (%rsi,%rcx)
        cmpq    %r8, %r9
        jnb     .L16
        vmovss  4(%rdi,%rcx), %xmm1
        addq    $2, %rax
        vfmadd213ss     4(%rdx,%rcx), %xmm0, %xmm1
        vmovss  %xmm1, 4(%rsi,%rcx)
        cmpq    %r8, %rax
        jnb     .L16
        vmovss  8(%rdx,%rcx), %xmm4
        vfmadd132ss     8(%rdi,%rcx), %xmm4, %xmm0
        vmovss  %xmm0, 8(%rsi,%rcx)
.L16:
        ret
        .p2align 4
        .p2align 3
.L18:
        vzeroupper
        ret
        .p2align 4
        .p2align 3
.L7:
        xorl    %eax, %eax
        jmp     .L2