[Bug tree-optimization/114413] New: BB SLP sub-graph merging fails to CSE nodes

[Bug tree-optimization/114413] New: BB SLP sub-graph merging fails to CSE nodes

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114413

            Bug ID: 114413
           Summary: BB SLP sub-graph merging fails to CSE nodes
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: rguenth at gcc dot gnu.org
  Target Milestone: ---

The gcc.dg/vect/bb-slp-32.c shows that while we now discover both the store
and the reduction as BB vectorization opportunities we merge the SLP
instances into the same graph because they overlap but fail to unify
nodes within them so both costing and code-generation is off duplicating
the load and the adds:

  <bb 2> [local count: 1073741824]:
  _36 = {a_12(D), b_15(D), b_15(D), a_12(D)};
  _30 = {a_12(D), b_15(D), b_15(D), a_12(D)};
  p_10 = __builtin_assume_aligned (p_9(D), 16);
  vectp.4_27 = p_10;
  vect__1.5_28 = MEM <vector(4) int> [(int *)vectp.4_27];
  vect__2.6_29 = vect__1.5_28 + { 1, 2, 3, 4 };
  vect_tem0_13.7_31 = vect__2.6_29 + _30;
  vectp.11_33 = p_10;
  vect__7.12_34 = MEM <vector(4) int> [(int *)vectp.11_33];
  vect__8.13_35 = vect__7.12_34 + { 1, 2, 3, 4 };
  vect_tem3_22.14_37 = vect__8.13_35 + _36;
  _1 = *p_10;
  _2 = _1 + 1;
  tem0_13 = _2 + a_12(D);
  _3 = MEM[(int *)p_10 + 4B];
  _4 = _3 + 2;
  tem1_16 = _4 + b_15(D); 
  sum_17 = tem0_13 + tem1_16;
  _5 = MEM[(int *)p_10 + 8B];
  _6 = _5 + 3;
  tem2_19 = _6 + b_15(D);
  sum_20 = sum_17 + tem2_19;
  _7 = MEM[(int *)p_10 + 12B];
  _8 = _7 + 4;
  tem3_22 = _8 + a_12(D);
  _38 = VIEW_CONVERT_EXPR<vector(4) unsigned int>(vect_tem3_22.14_37);
  _39 = .REDUC_PLUS (_38);
  _40 = (int) _39;
  sum_23 = _40;
  MEM <vector(4) int> [(int *)&x] = vect_tem0_13.7_31;
  bar (&x);
  x ={v} {CLOBBER(eos)};

but the vectorization should be profitable, we CSE this to

foo:
.LFB0:
        .cfi_startproc
        pushq   %rbx
        .cfi_def_cfa_offset 16
        .cfi_offset 3, -16
        movd    %edx, %xmm2
        movd    %esi, %xmm0
        movdqa  %xmm2, %xmm3
        punpckldq       %xmm0, %xmm3
        punpckldq       %xmm2, %xmm0
        subq    $16, %rsp
        .cfi_def_cfa_offset 32
        movdqa  .LC0(%rip), %xmm1
        paddd   (%rdi), %xmm1
        punpcklqdq      %xmm3, %xmm0
        movq    %rsp, %rdi
        paddd   %xmm0, %xmm1
        movdqa  %xmm1, %xmm0
        movaps  %xmm1, (%rsp)
        psrldq  $8, %xmm0
        paddd   %xmm1, %xmm0
        movdqa  %xmm0, %xmm2
        psrldq  $4, %xmm2
        paddd   %xmm2, %xmm0
        movd    %xmm0, %ebx
        call    bar
        addq    $16, %rsp
        .cfi_def_cfa_offset 16
        movl    %ebx, %eax
        popq    %rbx
        .cfi_def_cfa_offset 8
        ret

in the end.