[Bug target/109812] GraphicsMagick resize is a lot slower in GCC 13.1 vs Clang 16 on Intel Raptor Lake

["hubicka at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109812

--- Comment #9 from Jan Hubicka <hubicka at gcc dot gnu.org> ---
Oddly enough simplified version of the loop SLP vectorizes for me:
struct rgb {unsigned char r,g,b;} *rgbs;
int *addr;
double *weights;
struct drgb {double r,g,b;};

struct drgb sum()
{
        struct drgb r;
        for (int i = 0; i < 100000; i++)
        {
          int j = addr[i];
          double w = weights[i];
          r.r += rgbs[j].r * w;
          r.g += rgbs[j].g * w;
          r.b += rgbs[j].b * w;
        }
        return r;
}
I get:
L2:
        movslq  (%r9,%rdx,4), %rax
        vmovsd  (%r8,%rdx,8), %xmm1
        incq    %rdx
        leaq    (%rax,%rax,2), %rax
        addq    %rsi, %rax
        movzbl  (%rax), %ecx
        vmovddup        %xmm1, %xmm4
        vmovd   %ecx, %xmm0
        movzbl  1(%rax), %ecx
        movzbl  2(%rax), %eax
        vpinsrd $1, %ecx, %xmm0, %xmm0
        vcvtdq2pd       %xmm0, %xmm0
        vfmadd231pd     %xmm4, %xmm0, %xmm2
        vcvtsi2sdl      %eax, %xmm5, %xmm0
        vfmadd231sd     %xmm1, %xmm0, %xmm3
        cmpq    $100000, %rdx
        jne     .L2


I think the actual loop is:
 <bb 53> [local count: 44202554]:
  _106 = _262->pixel;
  _109 = *source_231(D).columns;

  <bb 54> [local count: 401841405]:
  # pixel$green_332 = PHI <_124(89), pixel$green_265(53)>
  # i_357 = PHI <i_298(89), 0(53)>
  # pixel$red_371 = PHI <_119(89), pixel$red_263(53)>
  # pixel$blue_377 = PHI <_129(89), pixel$blue_267(53)>
  i.51_102 = (long unsigned int) i_357;
  _103 = i.51_102 * 16;
  _104 = _262 + _103;
  _105 = _104->pixel;
  _107 = _105 - _106;
  _108 = (long unsigned int) _107;
  _110 = _108 * _109;
  _112 = _110 + _621;
  weight_297 = _104->weight;
  _113 = _112 * 4;
  _114 = _276 + _113;
  _115 = _114->red;
  _116 = (int) _115;
  _117 = (double) _116;
  _118 = _117 * weight_297;
  _119 = _118 + pixel$red_371;
  _120 = _114->green;
 _121 = (int) _120;
  _122 = (double) _121;
  _123 = _122 * weight_297;
  _124 = _123 + pixel$green_332;
  _125 = _114->blue;
  _126 = (int) _125;
  _127 = (double) _126;
  _128 = _127 * weight_297;
  _129 = _128 + pixel$blue_377;
  i_298 = i_357 + 1;
  if (n_195 > i_298)
    goto <bb 89>; [89.00%]
  else
    goto <bb 118>; [11.00%]

  <bb 118> [local count: 44202554]:
  # _607 = PHI <_124(54)>
  # _606 = PHI <_119(54)>
  # _605 = PHI <_129(54)>
  goto <bb 55>; [100.00%]

  <bb 89> [local count: 357638851]:
  goto <bb 54>; [100.00%]


and SLP vectorizer seems to claim:
../magick/resize.c:1284:52: note:       _125 = _114->blue;
../magick/resize.c:1284:52: note:       _120 = _114->green;
../magick/resize.c:1284:52: note:       _115 = _114->red;
../magick/resize.c:1284:52: missed:   not consecutive access weight_297 =
_104->weight;
../magick/resize.c:1284:52: missed:   not consecutive access _105 =
_104->pixel;
../magick/resize.c:1284:52: missed:   not consecutive access _134->red =
iftmp.57_207;
../magick/resize.c:1284:52: missed:   not consecutive access _134->green =
iftmp.60_208;
../magick/resize.c:1284:52: missed:   not consecutive access _134->blue =
iftmp.63_209;
../magick/resize.c:1284:52: missed:   not consecutive access _134->opacity = 0;
../magick/resize.c:1284:52: missed:   not consecutive access _63 =
*source_231(D).columns;
../magick/resize.c:1284:52: missed:   not consecutive access _60 = _262->pixel;

Not sure if that is related to the real testcase:


struct rgb {unsigned char r,g,b;} *rgbs;
int *addr;
double *weights;
struct drgb {double r,g,b,o;};

struct drgb sum()
{
        struct drgb r;
        for (int i = 0; i < 100000; i++)
        {
          int j = addr[i];
          double w = weights[i];
          r.r += rgbs[j].r * w;
          r.g += rgbs[j].g * w;
          r.b += rgbs[j].b * w;
        }
        return r;
}

make us to miss the vectorization even though there is nothing using drgb->o:

sum:
.LFB0:
        .cfi_startproc
        movq    %rdi, %r8
        movq    weights(%rip), %rsi
        movq    addr(%rip), %rdi
        vxorps  %xmm2, %xmm2, %xmm2
        movq    rgbs(%rip), %rcx
        xorl    %edx, %edx
        .p2align 4
        .p2align 3
.L2:
        movslq  (%rdi,%rdx,4), %rax
        vmovsd  (%rsi,%rdx,8), %xmm0
        incq    %rdx
        leaq    (%rax,%rax,2), %rax
        addq    %rcx, %rax
        movzbl  (%rax), %r9d
        vcvtsi2sdl      %r9d, %xmm2, %xmm1
        movzbl  1(%rax), %r9d
        movzbl  2(%rax), %eax
        vfmadd231sd     %xmm0, %xmm1, %xmm3
        vcvtsi2sdl      %r9d, %xmm2, %xmm1
        vfmadd231sd     %xmm0, %xmm1, %xmm5
        vcvtsi2sdl      %eax, %xmm2, %xmm1
        vfmadd231sd     %xmm0, %xmm1, %xmm4
        cmpq    $100000, %rdx
        jne     .L2
        vmovq   %xmm4, %xmm4
        vunpcklpd       %xmm5, %xmm3, %xmm0
        movq    %r8, %rax
        vinsertf128     $0x1, %xmm4, %ymm0, %ymm0
        vmovupd %ymm0, (%r8)
        vzeroupper
        ret