[Bug tree-optimization/110452] New: Bad vectorization of invariant masks

[rguenth at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110452

            Bug ID: 110452
           Summary: Bad vectorization of invariant masks
           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: ---

When we have loop like

double a[1024], b[1024], c[1024];

void foo (int flag, int n)
{
  _Bool x = flag == 3;
  for (int i = 0; i < n; ++i)
    a[i] = (x ? b[i] : c[i]) * 42.;
}

and build it with -O2 -ftree-vectorize -march=znver4 (to avoid unswitching)
we get

  _55 = _2 ? -1 : 0;
  vect_cst__56 = {_55, _55, _55, _55, _55, _55, _55, _55};

  <bb 3> [local count: 567644343]:
  # i_14 = PHI <i_11(9), 0(21)>
  # vectp_b.10_49 = PHI <vectp_b.10_50(9), &b(21)>
  # vectp_c.13_52 = PHI <vectp_c.13_53(9), &c(21)>
  # vectp_a.18_62 = PHI <vectp_a.18_63(9), &a(21)>
  # ivtmp_65 = PHI <ivtmp_66(9), 0(21)>
  vect_iftmp.12_51 = MEM <vector(8) double> [(double *)vectp_b.10_49];
  iftmp.0_9 = b[i_14];
  vect_iftmp.15_54 = MEM <vector(8) double> [(double *)vectp_c.13_52];
  iftmp.0_8 = c[i_14];
  vect_patt_13.16_59 = VEC_COND_EXPR <vect_cst__56, vect_iftmp.12_51,
vect_iftmp.15_54>;
  iftmp.0_3 = _2 ? iftmp.0_9 : iftmp.0_8;

so the invariant but not constant condition _2 on the COND_EXPR is vectorized
as

  _55 = _2 ? -1 : 0;
  vect_cst__56 = {_55, _55, _55, _55, _55, _55, _55, _55};

unfortunately that leads to very bad generated code

        cmpl    $3, %edi
        sete    %cl
        movl    %ecx, %esi
        leal    (%rsi,%rsi), %eax
        leal    0(,%rsi,4), %r9d
        leal    0(,%rsi,8), %r8d
        orl     %esi, %eax
        orl     %r9d, %eax
        movl    %ecx, %r9d
        orl     %r8d, %eax
        movl    %ecx, %r8d
        sall    $4, %r9d
        sall    $5, %r8d
        sall    $6, %esi
        orl     %r9d, %eax
        orl     %r8d, %eax
        movl    %ecx, %r8d
        orl     %esi, %eax
        sall    $7, %r8d
        orl     %r8d, %eax
        kmovb   %eax, %k1