; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
; RUN: llc -mtriple=aarch64-unknown-linux-gnu -global-isel -global-isel-abort=2 < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-GI

; CHECK-GI:       warning: Instruction selection used fallback path for test_bit_sink_operand

; BIT Bitwise Insert if True
;
; 8-bit vectors tests

define <1 x i8> @test_bit_v1i8(<1 x i8> %A, <1 x i8> %B, <1 x i8> %C) {
; CHECK-SD-LABEL: test_bit_v1i8:
; CHECK-SD:       // %bb.0:
; CHECK-SD-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT:    ret
;
; CHECK-GI-LABEL: test_bit_v1i8:
; CHECK-GI:       // %bb.0:
; CHECK-GI-NEXT:    fmov x8, d0
; CHECK-GI-NEXT:    fmov x9, d1
; CHECK-GI-NEXT:    fmov x10, d2
; CHECK-GI-NEXT:    and w9, w10, w9
; CHECK-GI-NEXT:    bic w8, w8, w10
; CHECK-GI-NEXT:    orr w8, w9, w8
; CHECK-GI-NEXT:    fmov s0, w8
; CHECK-GI-NEXT:    ret
  %and = and <1 x i8> %C, %B
  %neg = xor <1 x i8> %C, <i8 -1>
  %and1 = and <1 x i8> %neg, %A
  %or = or <1 x i8> %and, %and1
  ret <1 x i8> %or
}

; 16-bit vectors tests

define <1 x i16> @test_bit_v1i16(<1 x i16> %A, <1 x i16> %B, <1 x i16> %C) {
; CHECK-SD-LABEL: test_bit_v1i16:
; CHECK-SD:       // %bb.0:
; CHECK-SD-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT:    ret
;
; CHECK-GI-LABEL: test_bit_v1i16:
; CHECK-GI:       // %bb.0:
; CHECK-GI-NEXT:    fmov x8, d0
; CHECK-GI-NEXT:    fmov x9, d1
; CHECK-GI-NEXT:    fmov x10, d2
; CHECK-GI-NEXT:    and w9, w10, w9
; CHECK-GI-NEXT:    bic w8, w8, w10
; CHECK-GI-NEXT:    orr w8, w9, w8
; CHECK-GI-NEXT:    fmov s0, w8
; CHECK-GI-NEXT:    ret
  %and = and <1 x i16> %C, %B
  %neg = xor <1 x i16> %C, <i16 -1>
  %and1 = and <1 x i16> %neg, %A
  %or = or <1 x i16> %and, %and1
  ret <1 x i16> %or
}

; 32-bit vectors tests

define <1 x i32> @test_bit_v1i32(<1 x i32> %A, <1 x i32> %B, <1 x i32> %C) {
; CHECK-SD-LABEL: test_bit_v1i32:
; CHECK-SD:       // %bb.0:
; CHECK-SD-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT:    ret
;
; CHECK-GI-LABEL: test_bit_v1i32:
; CHECK-GI:       // %bb.0:
; CHECK-GI-NEXT:    fmov x8, d0
; CHECK-GI-NEXT:    fmov x9, d1
; CHECK-GI-NEXT:    fmov x10, d2
; CHECK-GI-NEXT:    and w9, w10, w9
; CHECK-GI-NEXT:    bic w8, w8, w10
; CHECK-GI-NEXT:    orr w8, w9, w8
; CHECK-GI-NEXT:    fmov s0, w8
; CHECK-GI-NEXT:    mov v0.s[1], w8
; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 killed $q0
; CHECK-GI-NEXT:    ret
  %and = and <1 x i32> %C, %B
  %neg = xor <1 x i32> %C, <i32 -1>
  %and1 = and <1 x i32> %neg, %A
  %or = or <1 x i32> %and, %and1
  ret <1 x i32> %or
}

; 64-bit vectors tests

define <1 x i64> @test_bit_v1i64(<1 x i64> %A, <1 x i64> %B, <1 x i64> %C) {
; CHECK-SD-LABEL: test_bit_v1i64:
; CHECK-SD:       // %bb.0:
; CHECK-SD-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-SD-NEXT:    ret
;
; CHECK-GI-LABEL: test_bit_v1i64:
; CHECK-GI:       // %bb.0:
; CHECK-GI-NEXT:    fmov x8, d2
; CHECK-GI-NEXT:    fmov x9, d1
; CHECK-GI-NEXT:    fmov x10, d0
; CHECK-GI-NEXT:    and x9, x8, x9
; CHECK-GI-NEXT:    bic x8, x10, x8
; CHECK-GI-NEXT:    orr x8, x9, x8
; CHECK-GI-NEXT:    fmov d0, x8
; CHECK-GI-NEXT:    ret
  %and = and <1 x i64> %C, %B
  %neg = xor <1 x i64> %C, <i64 -1>
  %and1 = and <1 x i64> %neg, %A
  %or = or <1 x i64> %and, %and1
  ret <1 x i64> %or
}

define <2 x i32> @test_bit_v2i32(<2 x i32> %A, <2 x i32> %B, <2 x i32> %C) {
; CHECK-LABEL: test_bit_v2i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-NEXT:    ret
  %and = and <2 x i32> %C, %B
  %neg = xor <2 x i32> %C, <i32 -1, i32 -1>
  %and1 = and <2 x i32> %neg, %A
  %or = or <2 x i32> %and, %and1
  ret <2 x i32> %or
}

define <4 x i16> @test_bit_v4i16(<4 x i16> %A, <4 x i16> %B, <4 x i16> %C) {
; CHECK-LABEL: test_bit_v4i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-NEXT:    ret
  %and = and <4 x i16> %C, %B
  %neg = xor <4 x i16> %C, <i16 -1, i16 -1, i16 -1, i16 -1>
  %and1 = and <4 x i16> %neg, %A
  %or = or <4 x i16> %and, %and1
  ret <4 x i16> %or
}

define <8 x i8> @test_bit_v8i8(<8 x i8> %A, <8 x i8> %B, <8 x i8> %C) {
; CHECK-LABEL: test_bit_v8i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.8b, v1.8b, v2.8b
; CHECK-NEXT:    ret
  %and = and <8 x i8> %C, %B
  %neg = xor <8 x i8> %C, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
  %and1 = and <8 x i8> %neg, %A
  %or = or <8 x i8> %and, %and1
  ret <8 x i8> %or
}

; 128-bit vectors tests

define <2 x i64> @test_bit_v2i64(<2 x i64> %A, <2 x i64> %B, <2 x i64> %C) {
; CHECK-LABEL: test_bit_v2i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT:    ret
  %and = and <2 x i64> %C, %B
  %neg = xor <2 x i64> %C, <i64 -1, i64 -1>
  %and1 = and <2 x i64> %neg, %A
  %or = or <2 x i64> %and, %and1
  ret <2 x i64> %or
}

define <4 x i32> @test_bit_v4i32(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C) {
; CHECK-LABEL: test_bit_v4i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT:    ret
  %and = and <4 x i32> %C, %B
  %neg = xor <4 x i32> %C, <i32 -1, i32 -1, i32 -1, i32 -1>
  %and1 = and <4 x i32> %neg, %A
  %or = or <4 x i32> %and, %and1
  ret <4 x i32> %or
}

define <8 x i16> @test_bit_v8i16(<8 x i16> %A, <8 x i16> %B, <8 x i16> %C) {
; CHECK-LABEL: test_bit_v8i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT:    ret
  %and = and <8 x i16> %C, %B
  %neg = xor <8 x i16> %C, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
  %and1 = and <8 x i16> %neg, %A
  %or = or <8 x i16> %and, %and1
  ret <8 x i16> %or
}

define <16 x i8> @test_bit_v16i8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) {
; CHECK-LABEL: test_bit_v16i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    bit v0.16b, v1.16b, v2.16b
; CHECK-NEXT:    ret
  %and = and <16 x i8> %C, %B
  %neg = xor <16 x i8> %C, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
  %and1 = and <16 x i8> %neg, %A
  %or = or <16 x i8> %and, %and1
  ret <16 x i8> %or
}

define <4 x i32> @test_bit_sink_operand(<4 x i32> %src, <4 x i32> %dst, <4 x i32> %mask, i32 %scratch) {
; CHECK-LABEL: test_bit_sink_operand:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    sub sp, sp, #32
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    cmp w0, #0
; CHECK-NEXT:    mov w9, wzr
; CHECK-NEXT:    cinc w8, w0, lt
; CHECK-NEXT:    asr w8, w8, #1
; CHECK-NEXT:  .LBB11_1: // %do.body
; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    bit v1.16b, v0.16b, v2.16b
; CHECK-NEXT:    add x10, sp, #16
; CHECK-NEXT:    mov x11, sp
; CHECK-NEXT:    bfi x10, x9, #2, #2
; CHECK-NEXT:    bfi x11, x9, #2, #2
; CHECK-NEXT:    add w9, w9, #1
; CHECK-NEXT:    cmp w9, #5
; CHECK-NEXT:    str q1, [sp, #16]
; CHECK-NEXT:    str w0, [x10]
; CHECK-NEXT:    ldr q1, [sp, #16]
; CHECK-NEXT:    str q0, [sp]
; CHECK-NEXT:    str w8, [x11]
; CHECK-NEXT:    ldr q0, [sp]
; CHECK-NEXT:    b.ne .LBB11_1
; CHECK-NEXT:  // %bb.2: // %do.end
; CHECK-NEXT:    mov v0.16b, v1.16b
; CHECK-NEXT:    add sp, sp, #32
; CHECK-NEXT:    ret

entry:
  %0 = xor <4 x i32> %mask, <i32 -1, i32 -1, i32 -1, i32 -1>
  %div = sdiv i32 %scratch, 2
  br label %do.body

do.body:
  %dst.addr.0 = phi <4 x i32> [ %dst, %entry ], [ %vecins, %do.body ]
  %src.addr.0 = phi <4 x i32> [ %src, %entry ], [ %vecins1, %do.body ]
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
  %vbsl3.i = and <4 x i32> %src.addr.0, %mask
  %vbsl4.i = and <4 x i32> %dst.addr.0, %0
  %vbsl5.i = or <4 x i32> %vbsl3.i, %vbsl4.i
  %vecins = insertelement <4 x i32> %vbsl5.i, i32 %scratch, i32 %i.0
  %vecins1 = insertelement <4 x i32> %src.addr.0, i32 %div, i32 %i.0
  %inc = add nuw nsw i32 %i.0, 1
  %exitcond.not = icmp eq i32 %inc, 5
  br i1 %exitcond.not, label %do.end, label %do.body

do.end:
  ret <4 x i32> %vecins
}